AU2022247651B2 - Air-conditioning system, refrigerant amount estimation method for air-conditioning system, air conditioner, and refrigerant amount estimation method for air conditioner - Google Patents

Abstract

This air-conditioning system has: an air conditioner, which has refrigerant circuit formed by connecting at least one indoor unit to an outdoor unit by means of refrigerant piping, with a prescribed amount of refrigerant filling the refrigerant circuit; and a server, which is communicably connected with the air conditioner. The air conditioner has a first communication unit that detects a state quantity associated with control of the air conditioner, acquires a detected detection value, and transmits the acquired detection value to the server. The server has: a second communication unit that receives the detection value from the air conditioner; an estimation unit that, when a state quantity related to the amount of refrigerant filling the refrigerant circuit is set as a first characteristic amount, uses a detection value of the first characteristic amount to estimate a remaining refrigerant amount of the refrigerant remaining in the refrigerant circuit; and an discrimination unit that discriminates whether the detection value of the first characteristic amount is a detection value that should be used to estimate the remaining refrigerant amount. Consequently, an estimation accuracy for the remaining refrigerant amount can be increased even in a situation in which a characteristic amount used to estimate the remaining refrigerant amount is influenced by another defect.

Description

DESCRIPTION TITLE OF THE INVENTION: AIR CONDITIONING SYSTEM, REFRIGERANT AMOUNT ESTIMATION METHOD FOR AIR CONDITIONING SYSTEM, AIR CONDITIONER, AND REFRIGERANT AMOUNT ESTIMATION METHOD FOR AIR CONDITIONER

Field

[0001] The present invention relates to an air

conditioning system, a refrigerant amount estimation method

for an air conditioning system, an air conditioner, and a

refrigerant amount estimation method for an air

conditioner.

Background

[0002] In recent years, in a multi-room air conditioner

having a structure in which a plurality of indoor units are

connected to an outdoor unit, various methods for detecting

an amount of refrigerant that is filled in a refrigerant

circuit have been proposed. Patent Literature 1 discloses

a method for determining an amount of refrigerant by using

a degree of supercooling of a refrigerant at an outlet of a

condenser on the basis of, for example, a refrigerant

circuit that is used as a predetermined condition.

[0003] In addition, the present inventor discloses, in

Patent Literature 2, a method for generating, on the basis

of multiple regression analysis, a model for estimating an

amount of refrigerant of a refrigerant that remains in a

refrigerant circuit by using a feature value of the

refrigerant circuit related to the amount of refrigerant

and estimating a remaining refrigerant amount by using the

model.

Citation List

Patent Literature

[0004] Patent Literature 1: Japanese Laid-open Patent

Publication No. 2006-23072

Patent Literature 2: Japanese Laid-open Patent

Publication No. 2021-156528

[0004a] Any discussion of the prior art throughout the

specification should in no way be considered as an

admission that such prior art is widely known or forms part

of common general knowledge in the field.

Summary

Technical Problem

[0005] In the above described estimation model that

estimates the remaining refrigerant amount, the remaining

refrigerant amount is estimated by using a feature value

that has a correlation with the remaining refrigerant

amount from among a plurality of feature values that are

related to the refrigerant circuit. However, in some

cases, these feature values may also have a correlation

with an abnormal state, such as, a failure occurring in a

compressor, that is other than a decrease in the remaining

refrigerant amount of refrigerant caused by a refrigerant

leakage. Accordingly, in the case where one of the feature

values that has a correlation with the remaining

refrigerant amount is changed caused by a factor other than

the refrigerant leakage, for example, caused by a failure

of a device constituting the refrigerant circuit, an

erroneous estimation result may possibly be obtained for

the remaining refrigerant amount. In addition, in the case

where a feature value that is other than the feature value

that has a correlation with the remaining refrigerant

amount is changed caused by a factor other than the

refrigerant leakage, a feature value that has a correlation

with a leakage of a refrigerant and that is seemingly

normal may also affected by a factor other than the refrigerant leakage.

[00061 Accordingly, the present invention has been conceived in light of the circumstances described above and an object thereof is to provide an air conditioning system, a refrigerant amount estimation method for an air conditioning system, an air conditioner, and a refrigerant amount estimation method for an air conditioner that allow for improvement in accuracy of estimating a remaining refrigerant amount even when a feature value that is used to estimate the remaining refrigerant amount is affected by another problem. Solution to Problem

[0007] According to one aspect of the present invention, there is provided an air conditioning system comprising: an air conditioner that includes a refrigerant circuit that is constituted to have a structure in which at least one indoor unit is connected to an outdoor unit by a refrigerant pipe and a predetermined amount of refrigerant is filled; and a server that is communicably connected to the air conditioner, wherein the air conditioner includes a detection unit that detects a state quantity related to control of the air conditioner, an acquisition unit that acquires a detection value that has been detected by the detection unit, and a first communication unit that transmits the detection value that has been acquired by the acquisition unit to the server, and the server includes a second communication unit that receives the detection value from the air conditioner, an estimation unit that estimates a remaining refrigerant amount of the refrigerant that remains in the refrigerant circuit by using a detection value of a first feature value in a case where a state quantity related to an amount of the refrigerant that is filled in the refrigerant circuit is indicated by the first feature value, and a determination unit that determines by using a second feature value whether or not the detection value of the first feature value is a detection value that is to be used to estimate the remaining refrigerant amount performed by the estimation unit, the second feature value being obtained when the refrigerant circuit is operated normally and when only the remaining refrigerant amount is changed.

[0007a] According to another aspect of the present

invention, there is provided a refrigerant amount

estimation method that is implemented by an air

conditioning system that includes

an air conditioner that includes

a refrigerant circuit that is constituted to have

a structure in which at least one indoor unit is connected

to an outdoor unit by a refrigerant pipe and a

predetermined amount of refrigerant is filled, and

a server that is communicably connected to the

air conditioner, the refrigerant amount estimation method

for the air conditioning system comprising:

detecting, performed by a detection unit included in

the air conditioner, a state quantity related to control of

the air conditioner;

acquiring, performed by an acquisition unit included

in the air conditioner, a detection value of the detected

state quantity;

transmitting, performed by a first communication unit

included in the air conditioner, the acquired detection value to the server; receiving, performed by a second communication unit included in the server, the detection value from the air conditioner; determining by using a second feature value, performed by a determination unit included in the server, whether or not a detection value of a first feature value is a detection value that is to be used to estimate a remaining refrigerant amount in a case where a state quantity related to an amount of the refrigerant that is filled in the refrigerant circuit is indicated by the first feature value, the second feature value being obtained when the refrigerant circuit is operated normally and when only the remaining refrigerant amount is changed; and estimating, performed by an estimation unit included in the server, the remaining refrigerant amount of the refrigerant that remains in the refrigerant circuit by using the detection value of the first feature value.

[0007b] According to another aspect of the present invention, there is provided an air conditioner that includes a refrigerant circuit that is constituted to have a structure in which at least one indoor unit is connected to an outdoor unit by a refrigerant pipe and a predetermined amount of refrigerant is filled, the air conditioner comprising: a detection unit that detects a state quantity related to control of the air conditioner; an acquisition unit that acquires a detection value that has been detected by the detection unit; an estimation unit that estimates a remaining refrigerant amount of the refrigerant that remains in the refrigerant circuit by using a detection value of a first feature value in a case where a state quantity related to an amount of the refrigerant that is filled in the refrigerant circuit is indicated by the first feature value; and a determination unit that determines by using a second feature value whether or not the detection value of the first feature value is a detection value that is to be used to estimate the remaining refrigerant amount performed by the estimation unit, the second feature value being obtained when the refrigerant circuit is operated normally and when only the remaining refrigerant amount is changed.

[0007c] According to another aspect of the present invention, there is provided a refrigerant amount estimation method for estimating a remaining refrigerant amount in an air conditioner that includes a refrigerant circuit that is constituted to have a structure in which at least one indoor unit is connected to an outdoor unit by a refrigerant pipe and a predetermined amount of refrigerant is filled or estimating a remaining refrigerant amount in an air conditioning system that includes the air conditioner, the refrigerant amount estimation method for the air conditioner comprising: detecting a state quantity related to control of the air conditioner; acquiring a detection value of the detected state quantity; determining by using a second feature value whether or not a detection value of a first feature value is a detection value that is to be used to estimate the remaining refrigerant amount in a case where a state quantity related to an amount of the refrigerant that is filled in the refrigerant circuit is indicated by the first feature value, the second feature value being obtained when the refrigerant circuit is operated normally and when only the remaining refrigerant amount is changed; and estimating the remaining refrigerant amount of the refrigerant that remains in the refrigerant circuit by using the detection value of the first feature value.

Advantageous Effects of Invention

[00081 As an aspect of certain preferred embodiments of

the present invention, accuracy of estimating a remaining

refrigerant amount is improved even when a feature value

that is used to estimate the remaining refrigerant amount

is affected by another problem.

[0008a] Unless the context clearly requires otherwise,

throughout the description and the claims, the words "comprise", "comprising", and the like are to be construed

in an inclusive sense as opposed to an exclusive or

exhaustive sense; that is to say, in the sense of

"including, but not limited to".

Brief Description of Drawings

[00091 FIG. 1 is a diagram illustrating one example of

an air conditioner according to the present embodiment.

FIG. 2 is a diagram illustrating one example of an

outdoor unit and an indoor unit.

FIG. 3 is a block diagram illustrating one example of

a control circuit included in the outdoor unit.

FIG. 4 is a Mollier diagram illustrating a state of a

change in a refrigerant in the air conditioner.

FIG. 5 is a diagram illustrating one example of a

first feature value that is used for first to third cooling

purpose estimation models and a second feature value that

is used for a cooling time determination model.

FIG. 6 is a diagram illustrating one example of a

first feature value that is used for first to third heating

purpose estimation models and a second feature value that

is used for a heating time determination model.

FIG. 7A is a diagram illustrating one example in which an estimation result obtained by the first cooling purpose estimation model and an estimation result obtained by the second cooling purpose estimation model are not interpolated by a sigmoid curve. FIG. 7B is a diagram illustrating one example in which the estimation result obtained by the first cooling purpose estimation model and the estimation result obtained by the second cooling purpose estimation model are interpolated by a sigmoid curve. FIG. 8A is a diagram illustrating one example in which an estimation result obtained by the first heating purpose estimation model and an estimation result obtained by the second heating purpose estimation model are not interpolated by a sigmoid curve. FIG. 8B is a diagram illustrating one example in which the estimation result obtained by the first heating purpose estimation model and the estimation result obtained by the second heating purpose estimation model are interpolated by a sigmoid curve. FIG. 9 is a diagram illustrating one example of a distribution method of detection values of the second feature values in the determination model. FIG. 10 is a diagram illustrating an example of anomaly detection by an outlier. FIG. 11 is a flowchart illustrating one example of a processing operation performed by the control circuit related to an estimation process. FIG. 12 is a flowchart illustrating one example of a processing operation performed by the control circuit related to a multiple regression analysis process. FIG. 13 is a diagram illustrating one example of a failure decision table included in a control unit.

FIG. 14 is a diagram illustrating one example of an air conditioning system according to a second embodiment. Description of Embodiments

[0010] Preferred embodiments of an air conditioning system, a refrigerant amount estimation method for an air conditioning system, an air conditioner, and a refrigerant amount estimation method for an air conditioner will be explained in detail with reference to accompanying drawings. Furthermore, the disclosed technology is not limited to the present embodiments. Furthermore, the embodiments described below may also be appropriately modified as long as the embodiments do not conflict with each other.

[0011] First Embodiment <Configuration of air conditioner> FIG. 1 is a diagram illustrating one example of an air conditioner 1 according to the present embodiment. The air conditioner 1 illustrated in FIG. 1 includes a single piece of an outdoor unit 2, and N indoor units 3 (N is a natural number equal to or larger than 2). The outdoor unit 2 is connected to each of the indoor units 3 in a parallel manner via a liquid pipe 4 and a gas pipe 5. Then, a refrigerant circuit 6 in the air conditioner 1 is formed by connecting the outdoor unit 2 and the indoor unit 3 to each other by refrigerant pipes, such as the liquid pipe 4 and the gas pipe 5.

[0012] <Configuration of outdoor unit> FIG. 2 is a diagram illustrating one example of the outdoor unit 2 and the N indoor units 3. The outdoor unit 2 includes a compressor 11, a four-way valve 12, an outdoor heat exchanger 13, an outdoor unit expansion valve 14, a first shut-off valve 15, a second shut-off valve 16, an accumulator 17, an outdoor unit fan 18, and a control circuit 19. The compressor 11, the four-way valve 12, the outdoor heat exchanger 13, the outdoor unit expansion valve

14, the first shut-off valve 15, the second shut-off valve

16, and the accumulator 17 as described above are connected

to each other by each of refrigerant pipes that will be

described in detail below, and forms an outdoor side

refrigerant circuit that constitutes a part of the

refrigerant circuit.

[0013] The compressor 11 is, for example, a variable

capacity compressor of a pressurized container type in

which operation capacity is able to be changed in

accordance with drive of a motor (not illustrated) for

which a rotation speed is controlled by an inverter. The

compressor 11 is connected to a first port 12A of the four

way valve 12 by a discharge pipe 21 at the refrigerant

discharge side of the compressor 11. In addition, the

compressor 11 is connected to a refrigerant outflow side of

the accumulator 17 by a suction pipe 22 at the refrigerant

suction side of the compressor 11.

[0014] The four-way valve 12 is a valve for changing a

flow direction of a refrigerant flowing in the refrigerant

circuit 6, and includes the first to fourth ports 12A to

12D. The first port 12A is connected to the refrigerant

discharge side of the compressor 11 by the discharge pipe

21. The second port 12B is connected to one of the

refrigerant inlet and outlet of the outdoor heat exchanger

13 by an outdoor refrigerant pipe 23. The third port 12C

is connected to the refrigerant inflow side of the

accumulator 17 by an outdoor refrigerant pipe 26. Then,

the fourth port 12D is connected to the second shut-off

valve 16 by an outdoor gas pipe 24.

[0015] The outdoor heat exchanger 13 performs heat

exchange between the refrigerant and outside air that is taken into the interior of the outdoor unit 2 caused by a rotation of the outdoor unit fan 18. The outdoor heat exchanger 13 is connected to the second port 12B of the four-way valve 12 by the outdoor refrigerant pipe 23 at one of the refrigerant inlet and outlet of the outdoor heat exchanger 13. The outdoor heat exchanger 13 is connected to the first shut-off valve 15 by an outdoor liquid pipe 25 at the other of the refrigerant inlet and outlet of the outdoor heat exchanger 13. The outdoor heat exchanger 13 functions as a condenser when the air conditioner 1 performs a cooling operation, and functions as an evaporator when the air conditioner 1 performs a heating operation.

[0016] The outdoor unit expansion valve 14 is an

electronic expansion valve that is arranged in the outdoor

liquid pipe 25 and that is driven by a pulse motor (not

illustrated). The outdoor unit expansion valve 14 adjusts

an amount of refrigerant flowing into the outdoor heat

exchanger 13 or an amount of refrigerant flowing out from

the outdoor heat exchanger 13 as a result of the degree of

opening of the outdoor unit expansion valve 14 being

adjusted in accordance with the number of pulses given to

the pulse motor. The degree of opening of the outdoor unit

expansion valve 14 is adjusted such that, when the air

conditioner 1 performs a heating operation, a degree of

superheat of refrigerant at the refrigerant suction side of

the compressor 11 reaches a target degree of suction

superheat. In addition, the degree of opening of the

outdoor unit expansion valve 14 is set to be fully opened

when the air conditioner 1 performs a cooling operation.

[0017] The accumulator 17 is connected to the third port

12C of the four-way valve 12 by the outdoor refrigerant

pipe 26 at the refrigerant inflow side of the accumulator

17. Furthermore, the accumulator 17 is connected to the

refrigerant inflow side of the compressor 11 by the suction

pipe 22 at the refrigerant outflow side of the accumulator

17. The accumulator 17 separates the refrigerant that has

flowed from the outdoor refrigerant pipe 26 into the

interior of the accumulator 17 into a gas refrigerant and a

liquid refrigerant, and allows only the gas refrigerant to

be sucked into the compressor 11.

[0018] The outdoor unit fan 18 is made of a resin

material and is arranged in the vicinity of the outdoor

heat exchanger 13. The outdoor unit fan 18 takes outside

air into the interior of the outdoor unit 2 from a suction

port (not illustrated) in accordance with a rotation of a

fan motor (not illustrated), and discharges the outside air

that has been subjected to heat exchange with the

refrigerant in the outdoor heat exchanger 13 to the outside

of the outdoor unit 2 from a wind outlet (not illustrated).

[0019] In addition, a plurality of sensors are arranged

in the outdoor unit 2. In the discharge pipe 21, a

discharge pressure sensor 31 that detects a discharge

pressure that is a pressure of the refrigerant that is

discharged from the compressor 11, and a discharge

temperature sensor 32 that detects a temperature of the

refrigerant that is discharged from the compressor 11, that

is, a discharge temperature, are arranged. In the vicinity

of a refrigerant inflow port of the accumulator 17

connected to the outdoor refrigerant pipe 26, a suction

pressure sensor 33 that detects a suction pressure that is

a pressure of the refrigerant that is sucked into the

compressor 11, and a suction temperature sensor 34 that

detects a temperature of the refrigerant that is sucked

into the compressor 11 are arranged.

[0020] In the outdoor liquid pipe 25 located between the outdoor heat exchanger 13 and the outdoor unit expansion valve 14, a refrigerant temperature sensor 35 that is used to detect a temperature of the refrigerant that flows into the outdoor heat exchanger 13 or a temperature of the refrigerant that flows out of the outdoor heat exchanger 13 is arranged. Then, in the vicinity of the suction port (not illustrated) of the outdoor unit 2, an outdoor air temperature sensor 36 that detects a temperature of outside air that flows into the interior of the outdoor unit 2, that is, an outdoor air temperature, is arranged.

[0021] The control circuit 19 controls the entirety of the air conditioner 1. FIG. 3 is a block diagram illustrating one example of the control circuit 19 included in the outdoor unit 2. The control circuit 19 includes an acquisition unit 41, a communication unit 42, a storage unit 43, a control unit 44, an estimation unit 45, and a determination unit 46. The acquisition unit 41 acquires sensor values of the detection units that are the various kinds of sensors described above. The communication unit 42 is a communication interface for performing communication with a communication unit included in each of the indoor units 3. The storage unit 43 is, for example, a flash memory, and stores therein a control program of the outdoor unit 2, an operating state quantity, such as detection values corresponding to detection signals received from the various kinds of sensors, a drive state of each of the compressor 11 and the outdoor unit fan 18, operation information (for example, including operation and stop information, an operation mode, such as cooling or heating, and the like) that is transmitted from each of the indoor units 3, rated capacity of the outdoor unit 2, requested capacity of each of the indoor units 3, and the like. Furthermore, the storage unit 43 includes an anomaly log storage unit 43A that stores therein an anomaly log that will be described later.

[00221 The control unit 44 periodically (for example,

every 30 seconds) acquires the detection values that are

obtained by the various kinds of sensors via the

communication unit 42, and receives, via the communication

unit 42, an input of a signal including the operating state

quantity that is transmitted from each of the indoor units

3. The control unit 44 performs, on the basis of the

various kinds of input information, adjustment of the

degree of opening of the outdoor unit expansion valve 14

and drive control of the compressor 11.

[0023] The estimation unit 45 includes an estimation

model 45A that estimates a refrigerant shortage rate of the

refrigerant circuit 6 by using the detection value of a

first feature value obtained in the case where an operating

state quantity related to an amount of the refrigerant in

the refrigerant circuit 6 is indicated by the first feature

value. In the present embodiment, for example, a relative

amount of refrigerant is used as an amount of refrigerant

that remains in the refrigerant circuit 6. Specifically,

the estimation model 45A is a model that estimates the

refrigerant shortage rate of the refrigerant circuit 6

(indicating an amount of decrease from a defined amount,

where 100% indicates that the defined amount of refrigerant

is filled. The same applies hereinafter). The estimation

model 45A includes a first cooling purpose estimation model

45A1, a second cooling purpose estimation model 45A2, a

third cooling purpose estimation model 45A3, a first

heating purpose estimation model 45A4, a second heating

purpose estimation model 45A5, and a third heating purpose

estimation model 45A6. Each of the estimation models will

be described in detail later.

[0024] The determination unit 46 includes a determination model 46A that determines whether or not the detection value of the first feature value is a detection value that is to be used to estimate the refrigerant shortage rate performed by the estimation unit 45 by using the detection value of a second feature value from among the operating state quantities. The determination model 46A includes a cooling time determination model 46B that is used when the air conditioner 1 performs a cooling operation, and a heating time determination model 46C that is used when the air conditioner 1 performs a heating operation. Each of the determination models will be described in detail later.

[0025] <Configuration of indoor unit> As illustrated in FIG. 2, the indoor unit 3 includes an indoor heat exchanger 51, an indoor unit expansion valve 52, a liquid pipe connection portion 53, a gas pipe connection portion 54, and an indoor unit fan 55. The indoor heat exchanger 51, the indoor unit expansion valve 52, the liquid pipe connection portion 53, and the gas pipe connection portion 54 are connected to each other by each of the refrigerant pipes that will be described later, and constitutes an indoor unit refrigerant circuit that forms a part of the refrigerant circuit 6.

[0026] The indoor heat exchanger 51 performs heat exchange between the refrigerant and indoor air that is taken into the interior of the indoor unit 3 from a suction port (not illustrated) caused by a rotation of the indoor unit fan 55. The indoor heat exchanger 51 is connected to the liquid pipe connection portion 53 by an indoor liquid pipe 56 at one of the refrigerant inlet and outlet of the indoor heat exchanger 51. In addition, the indoor heat exchanger 51 is connected to the gas pipe connection portion 54 by an indoor gas pipe 57 at the other of the refrigerant inlet and outlet of the indoor heat exchanger 51. The indoor heat exchanger 51 functions as a condenser when the air conditioner 1 performs a heating operation. In contrast, the indoor heat exchanger 51 functions as an evaporator when the air conditioner 1 performs a cooling operation.

[0027] The indoor unit expansion valve 52 is arranged in the indoor liquid pipe 56, and is an electronic expansion valve. When the indoor heat exchanger 51 functions as an evaporator, that is, when the indoor unit 3 performs a cooling operation, the degree of opening of the indoor unit expansion valve 52 is adjusted such that the degree of superheat of refrigerant at the refrigerant outlet side (at the side of the gas pipe connection portion 54) of the indoor heat exchanger 51 reaches the target degree of superheat of the refrigerant. In addition, when the indoor heat exchanger 51 functions as a condenser, that is, when the indoor unit 3 performs a heating operation, the degree of opening of the indoor unit expansion valve 52 is adjusted such that the degree of supercooling of the refrigerant at the refrigerant outlet side (at the side of the liquid pipe connection portion 53) of the indoor heat exchanger 51 reaches the target degree of supercooling of the refrigerant. Here, the target degree of superheat of the refrigerant and the target degree of supercooling of the refrigerant are the degree of superheat of refrigerant and the degree of supercooling of the refrigerant that are needed to exhibit sufficient cooling capacity and heating capacity in the indoor unit 3.

[0028] The indoor unit fan 55 is made of a resin material and is arranged in the vicinity of the indoor heat exchanger 51. The indoor unit fan 55 takes indoor air into the interior of the indoor unit 3 from a suction port (not illustrated) as a result of being rotated by a fan motor

(not illustrated), and discharges the indoor air that has

been subjected to heat exchange with the refrigerant in the

indoor heat exchanger 51 from a wind outlet (not

illustrated).

[0029] Various kinds of sensors are arranged in the

indoor unit 3. In the indoor liquid pipe 56, a liquid side

refrigerant temperature sensor 61 that detects a

temperature of the refrigerant that flows into the indoor

heat exchanger 51 (heat exchange inlet temperature at the

side of the indoor unit at the time of a cooling

operation), or a temperature of the refrigerant that flows

out of the indoor heat exchanger 51 (heat exchange outlet

temperature at the side of the indoor unit at the time of a

heating operation) is arranged between the indoor heat

exchanger 51 and the indoor unit expansion valve 52. In

the indoor gas pipe 57, a gas side temperature sensor 62

that detects a temperature of the refrigerant that flows

out of the indoor heat exchanger 51 (heat exchange outlet

temperature at the side of the indoor unit at the time of a

cooling operation), or a temperature of the refrigerant

that flows into the indoor heat exchanger 51 (heat exchange

inlet temperature at the side of the indoor unit at the

time of a heating operation) is arranged. In the vicinity

of the suction port (not illustrated) of the indoor unit 3,

a suction temperature sensor 63 that detects a temperature

of the indoor air that flows into the interior of the

indoor unit 3, that is, a suction temperature, is arranged.

[0030] <Operation of refrigerant circuit>

In the following, the flow of the refrigerant in the

refrigerant circuit 6 and an operation of each of the units

when the air conditioner 1 according to the present embodiment performs an air conditioning operation will be described. In addition, arrows illustrated in FIG. 1 indicate the flow of the refrigerant at the time of a heating operation.

[0031] When the air conditioner 1 performs a heating operation, the four-way valve 12 is switched such that the first port 12A and the fourth port 12D communicate with each other and the second port 12B and the third port 12C communicate with each other. Accordingly, the refrigerant circuit 6 enters a heating cycle in which each of the indoor heat exchangers 51 functions as a condenser, and the outdoor heat exchanger 13 functions as an evaporator. In addition, for convenience of description, the flow of the refrigerant at the time of a heating operation is indicated by solid arrows illustrated in FIG. 2.

[0032] If the compressor 11 is driven when the refrigerant circuit 6 is in the state described above, the refrigerant that has been discharged from the compressor 11 flows through the discharge pipe 21 into the four-way valve 12, flows through the outdoor gas pipe 24 from the four-way valve 12, and flows into the gas pipe 5 via the second shut-off valve 16. The refrigerant that flows through the gas pipe 5 is branched off and flows into each of the indoor unit 3 via each of the gas pipe connection portions 54. The refrigerant that has flowed into each of the indoor units 3 flows through each of the indoor gas pipes 57 and flows into each of the indoor heat exchangers 51. The refrigerant that has flowed into each of the indoor heat exchangers 51 is subjected to heat exchange with the indoor air that is taken into the interior of each of the indoor units 3 as a result of a rotation of each of the indoor unit fans 55, and is then condensed. In other words, each of the indoor heat exchangers 51 functions as a condenser, and the indoor air that is heated by the refrigerant in each of the indoor heat exchangers 51 is blown into a room from a wind outlet (not illustrated), so that the room in which each of the indoor units 3 is installed is heated.

[00331 The refrigerant that has flowed into each of the indoor liquid pipes 56 from the respective indoor heat exchangers 51 is depressurized by passing through the respective indoor unit expansion valves 52 for which the degree of opening is adjusted such that the degree of supercooling of the refrigerant at the refrigerant outlet side of each of the indoor heat exchangers 51 reaches the target degree of supercooling of the refrigerant. Here, the target degree of supercooling of the refrigerant is defined on the basis of the cooling capacity that is needed in each of the indoor units 3.

[0034] The refrigerant that has been depressurized by each of the indoor unit expansion valves 52 flows out to the liquid pipe 4 from each of the indoor liquid pipes 56 via each of the liquid pipe connection portions 53. The refrigerants that are joined at the liquid pipe 4 flow into the outdoor unit 2 via the first shut-off valve 15. The refrigerant that has flowed into the first shut-off valve 15 of the outdoor unit 2 flows through the outdoor liquid pipe 25 and depressurized by passing through the outdoor unit expansion valve 14. The refrigerant that has been depressurized by the outdoor unit expansion valve 14 flows through the outdoor liquid pipe 25 into the outdoor heat exchanger 13, is subjected to heat exchange with the outside air that has flowed into from the suction port (not illustrated) of the outdoor unit 2 as a result of a rotation of the outdoor unit fan 18, and is then evaporated. The refrigerant that has flowed out to the outdoor refrigerant pipe 26 from the outdoor heat exchanger

13 flows into the four-way valve 12, the outdoor

refrigerant pipe 26, the accumulator 17, and the suction

pipe 22 in this order, is sucked into the compressor 11 and

is then compressed again, and flows out to the outdoor gas

pipe 24 by way of the first port 12A and the fourth port

12D of the four-way valve 12.

[00351 Furthermore, when the air conditioner 1 performs

a cooling operation, the four-way valve 12 is switched such

that the first port 12A and the second port 12B communicate

with each other and the third port 12C and the fourth port

12D communicate with each other. Accordingly, the

refrigerant circuit 6 enters a cooling cycle in which each

of the indoor heat exchangers 51 functions as an evaporator

and the outdoor heat exchanger 13 functions as a condenser.

In addition, for convenience of description, the flow of

the refrigerant at the time of a cooling operation is

indicated by dashed arrows illustrated in FIG. 2.

[00361 If the compressor 11 is driven when the

refrigerant circuit 6 is in the state described above, the

refrigerant that has been discharged from the compressor 11

flows through the discharge pipe 21 into the four-way valve

12, flows through the outdoor refrigerant pipe 26 from the

four-way valve 12, and flows into the outdoor heat

exchanger 13. The refrigerant that has flowed into the

outdoor heat exchanger 13 is subjected to heat exchange

with outdoor air that is taken into the interior of the

outdoor unit 2 as a result of a rotation of the outdoor

unit fan 18, and is then condensed. In other words, the

outdoor heat exchanger 13 functions as a condenser, and the

indoor air that is heated by the refrigerant in the outdoor

heat exchanger 13 is blown out of the room from a wind

outlet (not illustrated).

[0037] The refrigerant that has flowed from the outdoor

heat exchanger 13 into the outdoor liquid pipe 25 is

depressurized by passing through the outdoor unit expansion

valve 14 in which the degree of opening is fully opened.

The refrigerant that has been depressurized by the outdoor

unit expansion valve 14 flows through the liquid pipe 4 via

the first shut-off valve 15 and is branched off and flows

into each of the indoor units 3. The refrigerant that has

flowed into each of the indoor units 3 flows through the

indoor liquid pipe 56 by way of each of the liquid pipe

connection portions 53, and is depressurized by passing

through the indoor unit expansion valve 52 in which the

degree of opening is adjusted such that the degree of

supercooling of the refrigerant at the refrigerant outlet

of the indoor heat exchanger 51 reaches the target degree

of supercooling of the refrigerant. The refrigerant that

has been depressurized by the indoor unit expansion valve

52 flows through the indoor liquid pipe 56 into the indoor

heat exchanger 51, is subjected to heat exchange with the

indoor air that has flowed into from the suction port (not

illustrated) of the indoor unit 3 as a result of a rotation

of the indoor unit fan 55, and is then evaporated. In

other words, each of the indoor heat exchangers 51

functions as an evaporator, and the indoor air that is

cooled by the refrigerant in each of the indoor heat

exchangers 51 is blown into the room from a wind outlet

(not illustrated), so that the room in which each of the

indoor units 3 is installed is cooled.

[0038] The refrigerant that flows into the gas pipe 5

from the indoor heat exchanger 51 via the gas pipe

connection portion 54 flows through the outdoor gas pipe 24

via the second shut-off valve 16 of the outdoor unit 2, and

flows into the fourth port 12D of the four-way valve 12.

The refrigerant that has flowed into the fourth port 12D of

the four-way valve 12 flows into the refrigerant inflow

side of the accumulator 17 from the third port 12C. The

refrigerant that has flowed from the refrigerant inflow

side of the accumulator 17 flows in via the suction pipe

22, is sucked by the compressor 11, and is then compressed

again.

[00391 The acquisition unit 41 included in the control

circuit 19 acquires sensor values of the discharge pressure

sensor 31, the discharge temperature sensor 32, the suction

pressure sensor 33, the suction temperature sensor 63, the

refrigerant temperature sensor 35, and the outdoor air

temperature sensor 36 that are included in the outdoor unit

2. Furthermore, the acquisition unit 41 acquires sensor

values of the liquid side refrigerant temperature sensor

61, the gas side temperature sensor 62, and the suction

temperature sensor 63 that are included in each of the

indoor units 3.

[0040] FIG. 4 is a Mollier diagram illustrating a

cooling cycle of the air conditioner 1. At the time of a

cooling operation performed by the air conditioner 1, the

outdoor heat exchanger 13 functions as a condenser, and the

indoor heat exchanger 51 functions as an evaporator. In

addition, at the time of a heating operation performed by

the air conditioner 1, the outdoor heat exchanger 13

functions as an evaporator, and the indoor heat exchanger

51 functions as a condenser.

[0041] The compressor 11 compresses a low-temperature

and low-pressure gas refrigerant that flows in from the

evaporator, and discharges a high-temperature and high

pressure gas refrigerant (a refrigerant that enters the

state at a point B in FIG. 4). Moreover, the temperature

of the gas refrigerant that is discharged from the compressor 11 is a discharge temperature, and the discharge temperature is detected by the discharge temperature sensor

32.

[0042] The condenser performs heat exchange between the

high-temperature and high-pressure gas refrigerant received

from the compressor 11 and air, and then condenses the gas

refrigerant. At this time, in the condenser, after the

entirety of the gas refrigerant turns into a liquid

refrigerant as a result of a change in latent heat, the

temperature of the liquid refrigerant is decreased as a

result of a change in sensible heat, so that the

refrigerant enters in a supercooled state (a state at a

point C in FIG. 4). Moreover, the temperature at which the

gas refrigerant is changed to the liquid refrigerant caused

by the change in latent heat is a high pressure saturation

temperature, and the temperature of the refrigerant in the

supercooled state at an outlet of the condenser is the

temperature at the heat exchange outlet. The high pressure

saturation temperature is a temperature that corresponds to

a pressure value (a pressure value P2 represented by "HPS"

in FIG. 4) that has been detected by the discharge pressure

sensor 31. The heat exchange outlet temperature is the

temperature of the refrigerant that flows through the

outdoor liquid pipe 25 and is detected by the refrigerant

temperature sensor 35.

[0043] The expansion valve depressurizes the low

temperature and high-pressure refrigerant that has flowed

from the condenser, so that a gas-liquid two-phase

refrigerant in which gas and liquid are mixed is obtained

(a refrigerant that enters the state at a point D in FIG.

4).

[0044] The evaporator performs heat exchange between the

gas-liquid two-phase refrigerant that has flowed into the evaporator and air, and then evaporates the refrigerant.

At this time, in the evaporator, after the entirety of the

gas-liquid two-phase refrigerant turns into a gas

refrigerant as a result of a change in latent heat, the

temperature of the gas refrigerant increases as a result of

a change in latent heat, so that the refrigerant enters in

a superheated state (a state at a point A in FIG. 4) and is

sucked into the compressor 11. Moreover, the temperature

at which the liquid refrigerant is changed to the gas

refrigerant as the result of the change in latent heat is a

low pressure saturation temperature. The low pressure

saturation temperature is a temperature that corresponds to

a pressure value (a pressure value P1 represented by "LPS"

in FIG. 4) that has been detected by the suction pressure

sensor 33. In addition, the temperature of the refrigerant

that is superheated by the evaporator and sucked into the

compressor 11 is a suction temperature. The suction

temperature is detected by the suction temperature sensor

34.

[0045] In addition, the degree of supercooling of the

refrigerant that is in the supercooled state at the time of

the refrigerant that flows out from the condenser is able

to be calculated by substacting the temperature (the heat

exchange outlet temperature described above) of the

refrigerant at a refrigerant outlet of the heat exchanger

that functions as a condenser from the high pressure

saturation temperature. Furthermore, the degree of suction

superheat of the refrigerant that is in the superheated

state at the time of the refrigerant that flows out from

the evaporator is able to be calculated by subtracting the

suction temperature from the low pressure saturation

temperature.

[0046] <First feature value>

FIG. 5 is a diagram illustrating one example of the

first feature value that is used for the first to the third

cooling purpose estimation models 45A1, 45A2, and 45A3 and

the second feature value that is used for the cooling time

determination model 46B. The first feature value is

present as an operating state quantity that is used for the

estimation model 45A. Examples of the first feature value

that is used for the first to the third cooling purpose

estimation models 45A1, 45A2, and 45A3 include a rotation

speed of the compressor 11, a high pressure saturation

temperature, a suction temperature, a low pressure

refrigerant temperature, a degree of supercooling of a

refrigerant (outdoor heat exchange subcool), and an outdoor

air temperature. The rotation speed of the compressor 11

is detected by a rotation speed sensor (not illustrated) of

the compressor 11. The high pressure saturation

temperature is a value that is obtained by converting the

pressure value that has been detected by the discharge

pressure sensor 31 to a temperature. The suction

temperature is detected by the suction temperature sensor

34. The low pressure refrigerant temperature is a

temperature of the refrigerant that is superheated by the

evaporator and that is then sucked into the compressor 11.

The degree of supercooling of the refrigerant is a value

that has been calculated using an expression indicated by,

for example, (the high pressure saturation temperature

the outdoor heat exchange outlet temperature). The outdoor

air temperature is detected by the outdoor air temperature

sensor 36. The outdoor heat exchange outlet temperature is

detected by the refrigerant temperature sensor 35.

Moreover, for example, an operating state quantity

including the first feature value that is used for the

first to the third cooling purpose estimation models 45A1,

45A2, and 45A3 is periodically detected by a detection

unit, such as the rotation speed sensor, the discharge

pressure sensor 31, the suction temperature sensor 34, the

outdoor air temperature sensor 36, or the refrigerant

temperature sensor 35. In addition, in the case where the

air conditioner 1 is being operated, the control unit 44

instructs the detection unit to periodically (for example,

every 10 minutes) acquire the operating state quantity.

The detection unit that has received the instruction

detects the operating state quantity from various kinds of

sensors that are provided in the air conditioner 1.

Information on acquisition time is also added to the

operating state quantity that has been periodically

acquired.

[0047] FIG. 6 is a diagram illustrating one example of

the first feature value that is used for the first to the

third heating purpose estimation models 45A4, 45A5, and

45A6, and the second feature value that is used for the

heating time determination model 46C. Examples of the

first feature value that is used for the first to the third

heating purpose estimation models 45A4, 45A5, and 45A6

include the degree of opening of the outdoor unit expansion

valve 14, the rotation speed of the compressor 11, the

degree of suction superheat, and the outdoor air

temperature. The degree of opening of the outdoor unit

expansion valve 14 is the number of pulses that the control

unit 44 gives to a stepping motor (not illustrated) of the

outdoor unit expansion valve 14. The rotation speed of the

compressor 11 is detected by the rotation speed sensor (not

illustrated) of the compressor 11. The degree of suction

superheat is a value that has been calculated using an

expression indicated by, for example, (the suction

temperature - the low pressure saturation temperature).

The outdoor air temperature is detected by the outdoor air

temperature sensor 36. The suction temperature is detected

by the suction temperature sensor 34, and the low pressure

saturation temperature is a value that is obtained by

converting the pressure value that has been detected by the

suction pressure sensor 33 to a temperature. Moreover, for

example, the operating state quantity including the first

feature value that is used for the first to the third

heating purpose estimation models 45A4, 45A5, and 45A6 is

periodically detected by the detection unit, such as the

rotation speed sensor, the suction temperature sensor 34,

or the outdoor air temperature sensor 36.

[0048] <Second feature value>

The second feature value is present as an operating

state quantity that is used for the determination model

46A. the second feature value that is used to generate the

determination model 46A is a value that is obtained when,

for example, the refrigerant circuit 6 is implemented on a

computer, numerical analysis is performed (hereinafter,

performing the numerical analysis is sometimes referred to

as performing a simulation), an operation of the

refrigerant circuit 6 is normal, and only a remaining

refrigerant amount is changed. Moreover, the second

feature value that is used to generate the determination

model 46A will be referred to as a simulation value

(sometimes simply referred to as a "value"). The second

feature value includes at least a single piece of the

operating state quantity that is included in the first

feature value, and includes at least a single piece of the

operating state quantity that is not included in the first

feature value. As will be described later, the generated

determination model 46A is applied to a value of the second

feature value (hereinafter, also referred to as a detection value of the second feature value) that is detected by the detection unit. The determination model 46A calculates an outlier of the detection value of the second feature value.

The determination unit 46 that will be described later

determines, on the basis of the value of the outlier,

whether or not the detection value of the first feature

value that is acquired by the detection unit at the same

time as the detection value of the second feature value is

a detection value that is to be used to estimate the

refrigerant shortage rate by the estimation unit 45.

[0049] The second feature value is detected by the

detection unit at the same timing as the first feature

value. Specifically, the second feature value is included

in the operating state quantity that is instructed by the

control unit 44 to be periodically acquired by the

detection unit (for example, every 10 minutes). Examples

of the second feature value that is used for the cooling

time determination model 46B includes, as illustrated in

FIG. 5, the rotation speed of the compressor 11, the high

pressure saturation temperature, the suction temperature,

the low pressure refrigerant temperature, the outdoor air

temperature, the discharge pressure, and the heat exchange

outlet temperature. The rotation speed of the compressor

11 is detected by the rotation speed sensor (not

illustrated) of the compressor 11. The high pressure

saturation temperature is a value that is obtained by

converting the pressure value that has been detected by the

discharge pressure sensor 31 to a temperature. The suction

temperature is detected by the suction temperature sensor

34. The low pressure refrigerant temperature is the

temperature of the refrigerant that is superheated by the

evaporator and that is then sucked into the compressor 11.

The outdoor air temperature is detected by the outdoor air temperature sensor 36. The discharge pressure is a pressure value that has been detected by the discharge pressure sensor 31. The heat exchange outlet temperature is detected by the refrigerant temperature sensor 35.

[00501 In addition, examples of the second feature value

that is used for the heating time determination model 46C

include, as illustrated in FIG. 6, the degree of opening of

the outdoor unit expansion valve 14, the rotation speed of

the compressor 11, the outdoor air temperature, the

discharge temperature, the suction temperature, the low

pressure saturation temperature, and the suction pressure

(LPS). The degree of opening of the outdoor unit expansion

valve 14 is detected by a sensor (not illustrated). The

rotation speed of the compressor 11 is detected by the

rotation speed sensor (not illustrated) of the compressor

11. The outdoor air temperature is detected by the outdoor

air temperature sensor 36. The discharge temperature is

detected by the discharge temperature sensor 32. The

suction temperature is detected by the suction temperature

sensor 34. The low pressure saturation temperature is a

value that is obtained by converting the pressure value

that has been detected by the suction pressure sensor 33 to

a temperature. The suction pressure is the pressure value

that has been detected by the suction pressure sensor 33.

Moreover, for example, the operating state quantity

including the second feature value that is used for the

heating time determination model 46C is periodically

detected by the detection unit, such as the rotation speed

sensor, the suction temperature sensor 34, the outdoor air

temperature sensor 36, or the suction pressure sensor 33.

[0051] Examples of the second feature value that is

commonly used in both of the cooling time determination

model 46B and the heating time determination model 46C include the rotation speed of the compressor 11 and the suction temperature that are the operating state quantity at the side of the outdoor unit 2.

[0052] In addition, examples of the second feature value that is commonly used in both of the cooling time determination model 46B and the heating time determination model 46C include the operating state quantity at the side of the indoor unit 3 including, for example, a heat exchange inlet temperature at the indoor unit side (at the time of a cooling operation: detected by the liquid side refrigerant temperature sensor 61, and at the time of a heating operation: detected by the gas side temperature sensor 62), a heat exchange outlet temperature at the indoor unit side (at the time of a cooling operation: detected by the gas side temperature sensor 62, and at the time of a heating operation: detected by the liquid side refrigerant temperature sensor 61), and the degree of opening of the indoor unit expansion valve 52. Moreover, as the second feature value at the side of the indoor unit 3, for example, the heat exchange inlet temperature at the indoor unit side, the heat exchange outlet temperature at the indoor unit side, and the degree of opening of the indoor unit expansion valve 52 are exemplified; however, these are the feature values that are able to be acquired even when each of the indoor units 3 has a different type, such as a duct type or ceiling cassette type.

[0053] <Configuration of estimation model> The estimation model 45A is generated by using a detection value of the first feature value. The estimation unit 45 estimates a refrigerant shortage rate of the refrigerant circuit 6 by applying, to the estimation model 45A, the detection value of the first feature value acquired at a timing that is different from a timing at which the estimation model 45A is generated.

[0054] The estimation model 45A is generated by a multiple regression analysis method that is a kind of a regression analysis method by using an arbitrary operating state quantity (detection value of the first feature value) from among a plurality of operating state quantities. In the multiple regression analysis method, the estimation model 45A is generated by selecting a regression equation, in which a P value (a value that indicates a degree of influence of the operating state quantity exerted on the accuracy of the generated estimation model (predetermined weight parameter)) is the smallest value and a correction value R2 (a value that indicates the accuracy of the generated estimation model 45A) is the largest value in a range of 0.9 to 1.0, from among regression equations that are obtained from a plurality of simulation results (results obtained by reproducing the refrigerant circuit 6 by a numerical calculation and calculating values of the operating state quantity with respect to the remaining amount of refrigerant). Here, the P value and the correction value R2 are values that are related to the accuracy of the estimation model 45A at the time of generation of the estimation model 45A based on the multiple regression analysis method, and the accuracy of the generated estimation model 45A is increased as the P value is smaller and the correction value R2 approaches 1.0. As a result, in the case where the refrigerant shortage rate at the time of a cooling operation is in a range of 0 to 30%, for example, the operating state quantities, such as the degree of supercooling of the refrigerant, the outdoor air temperature, the high pressure saturation temperature, and the rotation speed of the compressor 11, are used as the first feature value. In the case where the refrigerant shortage rate at the time of a cooling operation is in a range of 40 to 70%, for example, the operating state quantity, such as the suction temperature, the outdoor air temperature, and the rotation speed of the compressor 11, is used as the first feature value. In the case where the refrigerant shortage rate at the time of a heating operation is in a range of 0 to 20%, for example, as the operating state quantity, the degree of opening of the outdoor unit expansion valve 14 is used as the first feature value. Moreover, in the case where the refrigerant shortage rate at the time of a heating operation is in a range of 30% to 70%, for example, the operating state quantities, such as the degree of suction superheat (the suction temperature - the low pressure saturation temperature), the outdoor air temperature, the rotation speed of the compressor 11, and the degree of opening of the outdoor unit expansion valve 14, are used as the first feature value.

[00551 The estimation model 45A includes, as described

above, the first cooling purpose estimation model 45A1, the

second cooling purpose estimation model 45A2, the third

cooling purpose estimation model 45A3, the first heating

purpose estimation model 45A4, the second heating purpose

estimation model 45A5, and the third heating purpose

estimation model 45A6. In the present embodiment, each of

the estimation models is generated by using a simulation

result that will be described later, and is stored in the

estimation unit 45 included in the control circuit 19 in

the air conditioner 1 in advance.

[00561 The first cooling purpose estimation model 45A1

is the estimation model 45A that is effective in the case

where the refrigerant shortage rate is in a range of 0% to

30% (a first range), and is a first regression equation that is able to estimate the refrigerant shortage rate with high accuracy. The first regression equation is, for example, (al x the degree of supercooling of the refrigerant) + (a2 x the outdoor air temperature) + (a3 x the high pressure saturation temperature) + (a4 x the rotation speed of the compressor 11) + a5. It is assumed that the coefficients al to a5 are determined when the estimation models are generated. The estimation unit 45 calculates the refrigerant shortage rate of the refrigerant circuit 6 at the present time by substituting, into the first regression equation, the degree of supercooling of the refrigerant, the outdoor air temperature, the high pressure saturation temperature, and the rotation speed of the compressor 11 at the current time that are acquired by the acquisition unit 41. Moreover, the reason for substituting the degree of supercooling of the refrigerant, the outdoor air temperature, the high pressure saturation temperature, and the rotation speed of the compressor 11 is to use the first feature value that is used to generate the first cooling purpose estimation model 45A1. The degree of supercooling of the refrigerant is able to be calculated using an expression indicated by, for example, (the high pressure saturation temperature - the heat exchange outlet temperature). The outdoor air temperature is detected by the outdoor air temperature sensor 36. The high pressure saturation temperature is a value obtained by converting the pressure value that has been detected by the discharge pressure sensor 31 to a temperature. The rotation speed of the compressor 11 is detected by the rotation speed sensor (not illustrated) of the compressor 11.

[0057] The second cooling purpose estimation model 45A2 is the estimation model 45A that is effective in the case where the refrigerant shortage rate is in a range of 40% to

70% (a second range), and is a second regression equation

that is able to estimate the refrigerant shortage rate with

high accuracy. The second regression equation is, for

example, (all x the suction temperature) + (a12 x the

outdoor air temperature) + (a13 x the rotation speed of the

compressor 11) + a14. It is assumed that the coefficients

all to a14 are determined when the estimation models are

generated. The estimation unit 45 calculates the

refrigerant shortage rate of the refrigerant circuit 6 at

the present time by substituting, into the second

regression equation, the suction temperature, the outdoor

air temperature, and the rotation speed of the compressor

11 at the current time that are acquired by the acquisition

unit 41. Moreover, the reason for substituting the suction

temperature, the outdoor air temperature, and the rotation

speed of the compressor 11 is to use the feature value that

has been used to generate the second cooling purpose

estimation model 45A2. The suction temperature is detected

by the suction temperature sensor 34. The outdoor air

temperature is detected by the outdoor air temperature

sensor 36. The rotation speed of the compressor 11 is

detected by the rotation speed sensor (not illustrated) of

the compressor 11.

[00581 Incidentally, as described above, the refrigerant

shortage rate that is able to be obtained by the first

regression equation is in a range of 0% to 30%, and the

refrigerant shortage rate that is able to be obtained by

the second regression equation is in a range of 40% to 70%.

In this case, in the case where the refrigerant shortage

rate is in a range of 30% to 40%, if the first regression

equation is used, the refrigerant shortage rate is

calculated as 30%, whereas, if the second regression

equation is used, the refrigerant shortage rate is calculated as 40%. In other words, in the case where the refrigerant shortage rate is in a range of 30% to 40%, both of the degree of supercooling of the refrigerant exhibiting a high contribution rate when the refrigerant shortage rate is equal to or less than 30%, and the suction temperature exhibiting a high contribution rate when the refrigerant shortage rate is equal to or larger than 40% are less likely to be changed, so that it is not possible to generate an effective estimation model. Therefore, if the first regression equation or the second regression equation is used, the refrigerant shortage rate largely differs depending on which model is used as illustrated in FIG. 7A.

[00591 The third cooling purpose estimation model 45A3 is a cooling time refrigerant shortage rate calculation formula that is able to cover the refrigerant shortage rate in a range of 0% to 70% that includes a range in which it is not able to estimate the refrigerant shortage rate by using any of the first regression equation and the second regression equation as described above. As illustrated in FIG. 7B, the cooling time refrigerant shortage rate calculation formula continuously connects a refrigerant shortage rate that is the estimation result obtained by the first regression equation and a refrigerant shortage rate that is the estimation result obtained by the second regression equation, by a sigmoid curve using a sigmoid coefficient. Specifically, the cooling time refrigerant shortage rate calculation formula is (the sigmoid coefficient x the refrigerant shortage rate obtained by the first regression equation) + ((1 - the sigmoid coefficient) x refrigerant shortage rate obtained by the second regression equation). The estimation unit 45 calculates the refrigerant shortage rate of the refrigerant circuit 6 at the present time by substituting the current operating state quantity acquired by the acquisition unit 41 into the first regression equation and the second regression equation, and then substituting each of the calculated refrigerant shortage rates into the cooling time refrigerant shortage rate calculation formula.

[00601 Here, the sigmoid coefficient is calculated by using one of the operating state quantities. In the present embodiment, by taking into consideration that, if the subcool reaches 0, a result obtained by the first regression equation is approximately constant, a calculation formula is determined such that the sigmoid coefficient is 0.5 when the subcool is subcool is 5° C.

[0061] p = 1 / (1 + exp (- (sc - 5)))

p: sigmoid coefficient sc: subcool value

[0062] As a result of determining the sigmoid coefficient in this way and using the sigmoid coefficient for the third cooling purpose estimation model 45A3, when the refrigerant shortage rate is in a range of 0% to 30%, that is, when the refrigerant shortage rate is in the first range, the estimated value of the first cooling purpose estimation model 45A1 is dominant in the estimated value obtained by the third cooling purpose estimation model 45A3, and, when the refrigerant shortage rate is in a range of 40% to 70%, that is, when the refrigerant shortage rate is in the second range, the estimated value of the second cooling purpose estimation model 45A2 is dominant in the estimated value obtained by the third cooling purpose estimation model 45A3.

[00631 In addition, the sigmoid coefficient need not always be calculated by the method as described above, but the sigmoid coefficient may be calculated such that, when the actual refrigerant shortage rate is equal to or larger than 30%, that is, when the actual refrigerant shortage rate is not in the first range, the estimated value of the second cooling purpose estimation model 45A2 is dominant in the estimated value obtained by the third cooling purpose estimation model 45A3, and when the actual refrigerant shortage rate is equal to or less than 40%, that is, when the actual refrigerant shortage rate is not in the second range, the estimated value of the first cooling purpose estimation model 45A1 is dominant in the estimated value obtained by the third cooling purpose estimation model

45A3.

[0064] The first heating purpose estimation model 45A4

is the estimation model 45A that is effective in the case

where the refrigerant shortage rate is in a range of 0% to

20% (a third range), and is a fourth regression equation

that is able to estimate the refrigerant shortage rate with

high accuracy. The fourth regression equation is, for

example, (a31 x the degree of opening of the outdoor unit

expansion valve 14) + a32. The estimation unit 45

calculates the refrigerant shortage rate by substituting,

into the fourth regression equation, the current degree of

opening of the outdoor unit expansion valve 14 that has

been acquired by the acquisition unit 41. Moreover, the

reason for substituting the degree of opening of the

outdoor unit expansion valve 14 is to use the feature value

that has been used to generate the first heating purpose

estimation model 45A4.

[0065] The second heating purpose estimation model 45A5

is the estimation model 45A that is effective in the case

where the refrigerant shortage rate is in a range of 30% to

70% (a fourth range), and is a fifth regression equation

that is able to estimate the refrigerant shortage rate with

high accuracy. The fifth regression equation is, for example, (a4l x the degree of suction superheat) + (a42 x the outdoor air temperature) + (a43 x the rotation speed of the compressor 11) + (a44 x the degree of opening of the outdoor unit expansion valve 14) + a45. It is assumed that the coefficients a41 to a45 are determined when the estimation models are generated. The estimation unit 45 calculates the refrigerant shortage rate of the refrigerant circuit 6 at the present time by substituting, into the fifth regression equation, the degree of suction superheat, the outdoor air temperature, the rotation speed of the compressor 11, and the degree of opening of the expansion valve at the main side that are acquired by the acquisition unit 41. Moreover, the reason for substituting the degree of suction superheat, the outdoor air temperature, the rotation speed of the compressor 11, and the degree of opening of the outdoor unit expansion valve 14 is to use the feature value that has been used to generate the second heating purpose estimation model 45A5. The degree of suction superheat is able to be calculated using an expression indicated by, for example, (the suction temperature - the low pressure saturation temperature). The outdoor air temperature is detected by the outdoor air temperature sensor 36. The rotation speed of the compressor 11 is detected by the rotation speed sensor (not illustrated) of the compressor 11. The degree of opening of the outdoor unit expansion valve 14 is detected by a sensor (not illustrated).

[00661 In addition, as described above, the refrigerant shortage rate that is able to be obtained by the fourth regression equation is 0% to 20%, and the refrigerant shortage rate that is able to be obtained by the fifth regression equation is 30% to 70%. In this case, in the case where the refrigerant shortage rate is in a range of

20% to 30%, if the fourth regression equation is used, the refrigerant shortage rate is calculated as 20%, whereas, if the fifth regression equation is used, the refrigerant shortage rate is calculated as 30%. In other words, in the case where the refrigerant shortage rate is in a range of 20% to 30%, both of the degree of opening of the outdoor unit expansion valve 14 exhibiting a high contribution rate when the refrigerant shortage rate is equal to or less than 20%, and the degree of suction superheat exhibiting a high contribution rate when the refrigerant shortage rate is equal to or larger than 30% are less likely to be changed, so that it is not possible to generate an effective estimation model. Therefore, if the fourth regression equation or the fifth regression equation is used, the refrigerant shortage rate largely differs depending on which model is used as illustrated in FIG. 8A.

[0067] The third heating purpose estimation model 45A6 is a heating time refrigerant shortage rate calculation formula that is able to cover the refrigerant shortage rate in a range of 0% to 70% that includes a range in which it is not able to estimate the refrigerant shortage rate by using any of the fourth regression equation and the fifth regression equation as described above. As illustrated in FIG. 8B, the heating time refrigerant shortage rate calculation formula continuously connects a refrigerant shortage rate that is the estimation result obtained by the fourth regression equation and a refrigerant shortage rate that is the estimation result obtained by the fifth regression equation by a sigmoid curve using a sigmoid coefficient. Specifically, the heating time refrigerant shortage rate calculation formula is (the sigmoid coefficient x the refrigerant shortage rate obtained by the fifth regression equation) + ((1 - the sigmoid coefficient) x the refrigerant shortage rate obtained by the fourth regression equation). The estimation unit 45 calculates the refrigerant shortage rate of the refrigerant circuit 6 at the present time by substituting the current operating state quantity acquired by the acquisition unit 41 into the fourth regression equation and the fifth regression equation, and then substituting each of the calculated refrigerant shortage rates into the heating time refrigerant shortage rate calculation formula.

[00681 Here, the sigmoid coefficient is calculated by

using one of the operating state quantities, in the same

manner as in the cooling operation. In the present

embodiment, by taking into consideration that a result

obtained by the fourth regression equation is approximately

constant if the degree of opening of the outdoor unit

expansion valve 14 is fully opened when the degree of

opening of the outdoor unit expansion valve 14 is indicated

by 0 in a case of a fully closed state and is indicated by

100 in a case of a fully opened state, a calculation

formula is determined such that the sigmoid coefficient is

0.5 when the degree of opening of the outdoor unit

expansion valve 14 is 90.

[00691 p = 1 / (1 + exp (- (D / 10 - 45)))

p: sigmoid coefficient

D: the degree of opening of the outdoor unit

expansion valve 14

[0070] As a result of determining the sigmoid

coefficient in this way and using the sigmoid coefficient

for the third heating purpose estimation model 45A6, when

the refrigerant shortage rate is in a range of 0% to 20%,

that is, when the refrigerant shortage rate is in the third

range, the estimated value of the first heating purpose

estimation model 45A4 is dominant in the estimated value obtained by the third heating purpose estimation model

45A6, and, when the refrigerant shortage rate is in a range

of 30% to 70%, that is, the refrigerant shortage rate is in

the fourth range, estimated value of the second heating

purpose estimation model 45A5 is dominant in the estimated

value obtained by the third heating purpose estimation

model 45A6.

[0071] In addition, the sigmoid coefficient need not

always be calculated by the method as described above, but

the sigmoid coefficient may be calculated such that, when

the actual refrigerant shortage rate is equal to or larger

than 20%, that is, when the actual refrigerant shortage

rate is not in the third range, the estimated value of the

second heating purpose estimation model 45A5 is dominant in

the estimated value obtained by the third heating purpose

estimation model 45A6, and when the actual refrigerant

shortage rate is equal to or less than 30%, that is, when

the actual refrigerant shortage rate is not the fourth

range, the estimated value of the first heating purpose

estimation model 45A4 is dominant in the estimated value

obtained by the third heating purpose estimation model

45A6.

[0072] As described above, at the time of a cooling

operation, the refrigerant shortage rate is estimated by

using the first regression equation, the second regression

equation, and the cooling time refrigerant shortage rate

calculation formula. In the case where a value of the

degree of supercooling of the refrigerant at the time of

the cooling operation is larger than a first threshold (Tvl

in FIG. 7A and FIG. 7B), it is possible to estimate the

refrigerant shortage rate with good accuracy by selecting

the first regression equation rather than selecting the

second regression equation. In addition, in the case where the value of the degree of supercooling of the refrigerant at the time of the cooling operation is smaller than the first threshold, it is possible to estimate the refrigerant shortage rate with good accuracy by selecting the second regression equation rather than selecting the first regression equation. Furthermore, in the case where the value of the degree of supercooling of the refrigerant at the time of the cooling is near the first threshold, the estimated value of the refrigerant shortage rate largely varies depending on the regression equation to be used.

Accordingly, at the time of the cooling operation, the

cooling time refrigerant shortage rate calculation formula

that includes the first regression equation and the second

regression equation is selected. Consequently, it is

possible to estimate the refrigerant shortage rate at the

time of the cooling operation with good accuracy.

[0073] In addition, at the time of a heating operation,

the refrigerant shortage rate is estimated by using the

fourth regression equation, the fifth regression equation,

and the heating time refrigerant shortage rate calculation

formula. In the case where the degree of opening of the

outdoor unit expansion valve 14 at the time of the heating

operation is less than a second threshold (Tv2 in FIG. 8A

and FIG. 8B), it is possible to estimate the refrigerant

shortage rate with good accuracy by selecting the fourth

regression equation rather than selecting the fifth

regression equation. In addition, in the case where the

degree of opening of the outdoor unit expansion valve 14 at

the time of the heating operation is not less than the

second threshold, it is possible to estimate the

refrigerant shortage rate with good accuracy by selecting

the fifth regression equation rather than selecting the

fourth regression equation. Furthermore, in the case where the value of the degree of opening of the outdoor unit expansion valve 14 at the time of the heating operation is near the second threshold, the estimated value of the refrigerant shortage rate largely varies depending on the regression equation to be used. Accordingly, at the time of the heating operation, the heating time refrigerant shortage rate calculation formula that includes the fourth regression equation and the fifth regression equation is selected. Consequently, it is possible to estimate the refrigerant shortage rate at the time of the heating operation with good accuracy.

[0074] <Configuration of determination model>

The determination model 46A is generated by using a

simulation value that is a value of the second feature

value that is obtained as a result of a simulation of an

operation of the refrigerant circuit 6 when the refrigerant

circuit 6 is operated normally and when only the remaining

refrigerant amount is changed. The determination unit 46

calculates an outlier by applying detection value of the

second feature value that has been acquired from the air

conditioner 1 that is in operation to the determination

model 46A. The determination unit 46 determines, on the

basis of the value of the outlier, whether or not the

detection value of the first feature value that has been

acquired by the detection unit at the same time as the

detection value of the second feature value is a detection

value that is to be used to estimate the refrigerant

shortage rate performed by the estimation unit 45.

[0075] To generate the determination model 46A, for

example, a Kernel density estimation method is used. The

Kernel density estimation method is a method for estimating

a density function of the entire distribution from limited

sample points. The determination model 46A calculates a degree of deviation (hereinafter, also referred to as an

"outlier") from a local maximum value (a center of a

cluster (a set of data having similarities)) of the density

function on the basis of the density function of the entire

distribution that has been estimated from the limited

sample points. Then, if data targeted for determination is

input, the determination model 46A calculates an outlier of

the input data, and determines whether or not the outlier

is within a predetermined range (whether or not the data

targeted for determination is included in the cluster).

[0076] FIG. 9 is a diagram illustrating one example of a

distribution of the detection values of the second feature

values. As illustrated in FIG. 9, the determination model

46A recognizes, as a single cluster, a set of the values of

the second feature values (hereinafter, also referred to as

"simulation values of the second feature values") that are

obtained by a simulation, and classifies the cluster as a

normal state. A condition for the simulation is that the

refrigerant circuit 6 is in a steady state (in a state in

which a fill volume of a refrigerant is a defined amount),

or the state in which a fill volume of a refrigerant is

decreased (refrigerant leakage state). The simulation

values of the second feature value in the steady state are

values of the second feature values that are obtained by a

simulation that is performed by assuming a state in which

each of the components (the refrigerant circuit 6, the

compressor, the expansion valve, etc.) constituting the air

conditioner 1 are operated normally. In addition, the

simulation values of the second feature values in the

refrigerant leakage state are values of the second feature

values that are obtained by a simulation that is performed

by assuming a state in which each of the components (the

refrigerant circuit 6, the compressor, the expansion valve, etc.) constituting the air conditioner are operated normally and by assuming a state in which only an amount of refrigerant remaining in the refrigerant circuit 6 is changed (decreased). Furthermore, if a detection value of the second feature value that deviates from the cluster that is classified as normal by the determination model 46A is input, the detection value is classified as abnormal.

Moreover, the detection value that is classified as

abnormal is a detection value that deviates from the

cluster that is classified as normal when the detection

value is plotted on a graph as illustrated in FIG. 9. In

addition, abnormal mentioned here indicates a state in

which a failure is highly likely to have occurred in a

device constituting the refrigerant circuit.

[0077] The determination model 46A calculates an outlier

by applying the detection value of the second feature value

that has been acquired from the air conditioner 1 that is

in operation. Specifically, the determination model 46A

adopts the values of the second feature values that are

used to generate the determination model 46A as normal

sample values (the cluster that has been classified as

normal), and calculates an outlier that indicates the

degree of deviation related to the detection values of the

second feature values that have been acquired by the

acquisition unit 41 included in the air conditioner 1 that

is in operation. The outlier is obtained by quantifying a

distance that indicates a degree of deviation from the

center of the cluster that is classified as normal, and the

degree of deviation is increased as the absolute value of

the quantified value is larger. As a result, as the degree

of deviation is increased, the possibility that the

detection value of the second feature value is abnormal is

increased.

[0078] FIG. 10 is a diagram illustrating an example of

anomaly detection obtained by the outlier. The

determination unit 46 classifies the detection value of the

second feature value as normal in the case where the

outlier of the detection value of the second feature value

is larger than, for example, "-150" (in the case where the

absolute value of the outlier is less than 150), and

classifies the detection value of the second feature value

as abnormal in the case where the outlier of the detection

value of the second feature value is equal to or less than,

for example, "-150" (in the case where the absolute value

of the outlier is equal to or larger than 150). Moreover,

an outlier threshold X can be set to a certain value by

which normal data is not erroneously detected as abnormal

based on, for example, a result of verification of values

that are actually determined as abnormal and that are

obtained by collecting failure histories of the air

conditioner 1. Therefore, in the case where the detection

value of the second feature value is classified as

abnormal, the determination unit 46 does not cause the

estimation unit 45 to perform estimation operation of the

refrigerant shortage rate by using the detection value of

the first feature value that is acquired at the same time

as the detection value of the second feature value.

Furthermore, the determination unit 46 stores the detection

value of the second feature value that has been classified

as abnormal in the anomaly log storage unit 43A as an

anomaly log.

[0079] If the absolute value of the calculated outlier

is less than the outlier threshold X, for example, 150, the

determination unit 46 classifies the detection value of the

second feature value as normal. In this case, the

determination unit 46 causes the estimation unit 45 to perform an estimation operation of the refrigerant shortage rate by using the detection value of the first feature value that is acquired at the same time as the detection value of the second feature value.

[00801 In addition, for convenience of description, the

outlier threshold X is set to, for example, "-150", but the

threshold may appropriately be adjusted on the basis of the

result of collecting failure histories and verifying the

values that are actually determined as abnormal.

[0081] <Operation of estimation process>

FIG. 11 is a flowchart illustrating one example of a

processing operation related to an estimation process

performed by the control circuit 19. Moreover, it is

assumed that the estimation unit 45 included in the control

circuit 19 stores therein the first cooling purpose

estimation model 45A1, the second cooling purpose

estimation model 45A2, the third cooling purpose estimation

model 45A3, the first heating purpose estimation model

45A4, the second heating purpose estimation model 45A5, the

third heating purpose estimation model 45A6 that are

generated in advance. Furthermore, it is assumed that the

determination unit 46 included in the control circuit 19

stores therein the cooling time determination model 46B and

the heating time determination model 46C that are generated

in advance. The estimation process is periodically

performed, for example, in a predetermined period of time

(for example, night time) once a day with respect to

operating state quantities that are sequentially detected

every 10 minutes in 24 hours by the detection unit.

Moreover, the night time is described as an example of the

predetermined period of time; however, for example, the

operating state quantities corresponding to one day are

acquired after the operation of the air conditioner 1 is stopped in the night time that is a period of time in which operation frequency of the air conditioner 1 is low. In addition, as the predetermined period of time, it is possible to determine a predetermined time in which the operation is not performed instead of the night time by checking the working states of the air conditioner 1 for, for example, one month.

[0082] In FIG. 11, the control unit 44 included in the

control circuit 19 collects the operating state quantities

as pieces of operation data by way of the acquisition unit

41 (Step Sl). The control unit 44 performs a data

filtering process for extracting an arbitrary operating

state quantity from among the collected pieces of operation

data (Step S12). The control unit 44 performs a data

cleansing process (Step S13). Furthermore, the

determination unit 46 uses the determination model 46A and

performs a determination process for classifying whether

the detection value of the second feature value obtained

after the data cleansing process is normal or abnormal

(Step S14).

[0083] The control unit 44 determines whether the

detection value of the second feature value has been

classified as normal or abnormal (Step S15). If the

detection value of the second feature value has been

classified as normal at Step S15, the estimation unit 45

performs a remaining refrigerant amount estimation process

for applying, to each of the estimation models, the

detection value of the first feature value that is acquired

at the same time as the detection value of the second

feature value that has been classified as normal (Step

S16). Then, the estimation unit 45 calculates the

refrigerant shortage rate of the refrigerant circuit 6

(Step S17), and ends the processing operation illustrated in FIG. 11.

[0084] In addition, if the detection value of the second

feature value has been classified as abnormal at Step S15,

the determination unit 46 performs an abnormality output

process for storing the detection value of the second

feature value that has been classified as abnormal in the

anomaly log storage unit 43A and outputting an alert (Step

S18), and then, ends the processing operation illustrated

in FIG. 11.

[0085] The data filtering process is a process for,

instead of using all of the plurality of operating state

quantities, extracting, on the basis of a predetermined

filter condition, only a part of the operating state

quantities (the detection value of the first feature value

and the detection value of the second feature value) that

are needed to perform the determination process on the

second feature value or that is needed to calculate the

refrigerant shortage rate from among the plurality of

operating state quantities. By substituting, into the

generated estimation model 45A and the determination model

46A, the detection value of the first feature value and the

detection value of the second feature value that haven been

subjected to the data filtering process, which will be

described later, (obtained by subtracting an abnormal value

and an outstanding value), it is possible to more

accurately perform the determination process by using the

second feature value and perform estimating the refrigerant

shortage rate performed by using the first feature value.

[0086] The predetermined filter condition includes a

first filter condition, a second filter condition, and a

third filter condition. The first filter condition is a

filter condition for data that is extracted commonly among,

for example, all of the operation modes of the air conditioner 1. The second filter condition is a filter condition for data that is extracted at the time of the cooling operation. The third filter condition is a filter condition for data that is extracted at the time of the heating operation.

[0087] The first filter condition is, for example, a drive state of the compressor 11, identification of an operation mode, elimination of a special operation, elimination of a missing value included in an acquired value, selection of a small value of an amount of change in an operating state quantity that largely affects generation of each of the regression equations, or the like. The drive state of the compressor 11 is a condition that is needed to be determined because of an inability to estimate the refrigerant shortage rate unless the refrigerant circulates in the refrigerant circuit 6 as a result of stable operation of the compressor, and is a filter condition that is provided to eliminate an operating state quantity that has been detected in a transition period, such as at the time of a start-up of the compressor 11.

[0088] The identification of the operation mode is a filter condition for extracting only an operating state quantity that has been acquired at the time of the cooling operation and at the time of the heating operation. Therefore, the operating state quantity that has been acquired at the time of a dehumidification operation or an air supply operation is eliminated. The elimination of the special operation is a filter condition for excluding the operating state quantity that is acquired at the time of the special operation, such as an oil recovery operation or a defrosting operation, in which the state of the refrigerant circuit 6 is largely different from the state at the time of a cooling operation and at the time of a heating operation. The elimination of the missing value is a filter condition for excluding the operating state quantity that includes a missing value because accuracy may possibly be decreased if, in the case where a missing value is included in the operating state quantity that is used to determine the refrigerant shortage rate, each or the regression equation is generated by using the operating state quantity.

[00891 The selection of the small value of the amount of change in the operating state quantity that is substituted in each of the regression equations or each of the refrigerant shortage rate calculation formulas is a filter condition for extracting only an operating state quantity in the case where the operation state of the air conditioner 1 is stable, and is a condition that is needed to improve the accuracy of estimation performed by using each of the regression equations and each of the refrigerant shortage rate calculation formulas. Moreover, the operating state quantity that has large influence is, for example, the degree of supercooling of the refrigerant that is used when the refrigerant shortage rate at the time of a cooling operation is in a range of 0 to 30%, the suction temperature that is used when the refrigerant shortage rate at the time of a cooling operation is in a range of 40 to 70%, the degree of suction superheat at the time of a heating operation, or the like.

[00901 The second filter condition includes, for example, elimination of the heat exchange outlet temperature, abnormality of the subcool, abnormality of the discharge temperature, or the like.

[0091] The elimination of the heat exchange outlet temperature is a filter condition that takes into consideration the fact that, as a result of the outdoor air temperature sensor 36 and the refrigerant temperature sensor 35 are arranged at positions that are close to each other, the heat exchange outlet temperature that has been detected by the refrigerant temperature sensor 35 at the time of a cooling operation does not become lower than the outdoor air temperature that has been detected by the outdoor air temperature sensor 36, and is a filter condition for excluding the heat exchange outlet temperature that is lower than the outdoor air temperature.

[0092] The abnormality of the subcool is a filter

condition for excluding, when the degree of supercooling of

the refrigerant that is abnormally high or abnormally low

has been detected, this state that has occurred caused by

an extremely large or small cooling load. The abnormality

of the discharge temperature is a filter condition for

excluding the discharge temperature that has been detected

when what is called an out-of-gas state is detected in

which the amount of refrigerant that is sucked into the

compressor 11 is decreased due to a small cooling load.

[0093] The third filter condition is, for example,

abnormality of a discharge temperature or the like. The

third filter condition is a filter condition for excluding

a discharge temperature that has been detected when, the

discharge temperature is decreased by reducing the rotation

speed of, for example, the compressor 11 in the case where

the discharge temperature is increased caused by a large

heating load at the time of a heating operation and

discharge temperature protection control is performed.

[0094] The data cleansing process is a process for

excluding the detection value of the first feature value

that may lead to erroneous estimation, instead of using all

of the acquired detection values of the first feature

values for estimation of the refrigerant shortage rate. In addition, the data cleansing process is also a process for excluding the detection value of the second feature value that may lead to erroneous determination, instead of using all of the acquired detection values of the second feature values for the determination process. Specifically, the data cleansing process includes noise suppression that is performed by smoothing the acquired operating state quantities, data amount limitation, or the like. The noise suppression performed by smoothing data is a process for preventing noise by calculating a mean value in a subject interval and calculating a moving average of, for example, the degree of supercooling of the refrigerant, the suction temperature, and the degree of suction superheat in each of the models. The data amount limitation is a process for eliminating data, for example, whose amount is small because reliability of this kind of data is low. For example, if the number of pieces of data remaining after the filtering process performed on the pieces of input data with an amount corresponding to one day is equal to or larger than X, the data is used for the estimation process on the refrigerant shortage rate or is used for the determination process on the second feature value, and, if the number of pieces of data is smaller than X, all of the pieces of the data obtained on that day are not used. In other words, in the data cleansing process, it is possible to more accurately estimate the refrigerant shortage rate by substituting, into the estimation model 45A, the operating state quantities from which the abnormal value and the outstanding value are excluded, and it is possible to more accurately determine the second feature value by substituting, into the determination model 46A, the operating state quantities from which the abnormal value and the outstanding value are excluded.

[00951 The determination process is a process for

calculating the degree of deviation (outlier) from a local

maximum value (the center of a cluster) of the density

function on the basis of the density function of the entire

distribution that has been estimated from the simulation

values of the second feature values, and determining

whether the outlier is within a predetermined range

(whether data targeted for determination is included in the

cluster). The outlier is calculated by applying, to the

determination model 46A, the detection values of the second

feature values that have been acquired from the air

conditioner 1 that is in operation. In the determination

process, the outlier from the detection value of the second

feature value is calculated by using the value of the

second feature value, which has been used to generate the

determination model 46A, as the normal sample value.

Furthermore, in the determination process, if the absolute

value of the calculated outlier is equal to or larger than

the absolute value of the outlier threshold X, the

detection value of the second feature value is classified

as abnormal. Furthermore, in the determination process, if

the absolute value of the calculated outlier is less than

the absolute value of the outlier threshold X, the

detection value of the second feature value is classified

as normal.

[00961 FIG. 12 is a flowchart illustrating one example

of the processing operation related to the remaining

refrigerant amount estimation process performed by the

control circuit 19. The estimation of the remaining

refrigerant amount is a process for calculating the

refrigerant shortage rate of the refrigerant circuit 6 at

the present time by substituting, into each of the

regression equations or each of the refrigerant shortage rate calculation formulas of the estimation model 45A, the detection value of the first feature value that is acquired at the same time as the detection value of the second feature value that is classified as normal in the determination process from among the current operating state quantities (sensor values) that are subjected to the data filtering process and the data cleansing process. In FIG. 12, the estimation unit 45 included in the control circuit 19 determines whether or not the acquired first feature value is acquired during a cooling operation (Step S21). If the acquired first feature value is acquired during a cooling operation (Yes at Step S21), the estimation unit 45 applies the first feature value to each of the first cooling purpose estimation model 45A1 to the third cooling purpose estimation model 45A3 (Step S22).

[0097] If the acquired first feature value is not acquired during a cooling operation (No at Step S21), that is, if the acquired first feature value is acquired during a heating operation, the estimation unit 45 applies the first feature value to each of the first heating purpose estimation model 45A4 to the third heating purpose estimation model 45A6 (Step S23). Then, the estimation unit 45 calculates the refrigerant shortage rate at the present time by combining the result obtained by applying the first feature value to each of the first cooling purpose estimation model 45A1 to the third cooling purpose estimation model 45A3 and the result obtained by applying the first feature value to each of the first heating purpose estimation model 45A4 to the third heating purpose estimation model 45A6 (Step S24), and ends the processing operation illustrated in FIG. 12.

[0098] In the abnormality output process, the detection value of the second feature that is classified as abnormal in the determination process is stored as an anomaly log in the anomaly log storage unit 43A, and an alarm is output. As a result, it is possible to recognize abnormality of the detection value of the second feature value.

[00991 <Failure decision method> The estimation unit 45 calculates the current refrigerant shortage rate of the refrigerant circuit 6, and notifies the control unit 44 of the calculated refrigerant shortage rate. Furthermore, the determination unit 46 classifies the current second feature value as normal or abnormal, and notifies the control unit 44 of the classification result. The control unit 44 determines, on the basis of the refrigerant shortage rate calculated by the estimation unit 45, whether the amount of refrigerant is abnormal or normal, and outputs the determination result as a refrigerant amount determination result. The control unit 44 outputs the state of the air conditioner 1 on the basis of the refrigerant amount determination result and the classification result that is obtained by the determination unit 46. FIG. 13 is a diagram illustrating one example of a failure decision table 44A included in the control unit 44.

[0100] The control unit 44 refers to the failure decision table 44A and determines, in the case where the refrigerant amount determination result is abnormal and the classification result obtained by the determination unit 46 is abnormal, that detection of a refrigerant leakage is caused by another failure, and then, outputs an alarm that indicates the determination content. The control unit 44 refers to the failure decision table 44A and determines, in the case where the refrigerant amount determination result is abnormal and the classification result obtained by the determination unit 46 is normal, that a refrigerant leakage has been detected, and then, outputs an alarm that indicates the determination content. In addition, the control unit 44 refers to the failure decision table 44A and determines, in the case where the refrigerant amount determination result is normal and the classification result obtained by the determination unit 46 is abnormal, that a failure other than a refrigerant leakage has been detected, and then, outputs an alarm that indicates the determination result. In addition, the control unit 44 refers to the failure decision table 44A, and determines, if the refrigerant amount determination result is normal and the classification result obtained by the determination unit 46 is normal, that this state is the steady state.

[0101] <Effects of first embodiment>

In the air conditioner 1 according to the first

embodiment, the value of the second feature value that is

used to generate the determination model 46A is defined as

a normal sample value, and an outlier of the detection

value of the second feature value is calculated.

Furthermore, in the air conditioner 1, if the absolute

value of the calculated outlier is equal to or larger than

the absolute value of the outlier threshold X, the

detection value of the second feature value is classified

as abnormal. Furthermore, in the air conditioner 1, the

detection value of the first feature value that is acquired

at the same time as the detection value of the second

feature value that is classified as abnormal is not used

for the estimation model 45A. As a result, it is possible

to prevent an erroneous refrigerant shortage rate from

being estimated.

[0102] For example, in the case where, when the

refrigerant shortage rate is estimated by the estimation

model 45A that has been generated by the linear analysis obtained from the multiple regression analysis, the first feature value is changed as a result of a failure that is other than a refrigerant leakage and that has occurred together with a refrigerant leakage, it may also be conceivable that the refrigerant shortage rate is estimated as a small value even though the refrigerant shortage rate is originally increased (= abnormal) depending on the degree of a change in each of the feature values. For example, it may also be conceivable that the refrigerant shortage rate is estimated as a small value (= normal) as a result of a change in the rotation speed of the compressor and the suction temperature caused by a failure other than a refrigerant leakage, and as a result of the amount of change in each of the values being canceled out. However, in the air conditioner 1 according to the present embodiment, the detection value of the first feature value that is acquired at the same time as the detection value of the second feature value that has been classified as abnormal by the determination model 46A that is generated by the non-linear analysis, such as the Kernel density estimation method, is not used. As a result, it is possible to prevent an erroneous refrigerant shortage rate from being estimated.

[0103] In addition, originally, if the estimation model 45A that is generated by the linear analysis is used, it may also be conceivable that the refrigerant shortage rate is estimated to increase (= abnormal) even though the refrigerant shortage rate is a small value (= normal). For example, it may also be conceivable that the refrigerant shortage rate is erroneously estimated to increase as a result of a change in the rotation speed of the compressor caused by a failure other than the refrigerant leakage. However, in the air conditioner 1 according to the first embodiment, the detection value of the first feature value that is acquired at the same time as the detection value of the second feature value that is classified as abnormal by the determination model 46A that is generated by the non linear analysis is not used for the estimation model 45A. As a result, it is possible to prevent an erroneous refrigerant shortage rate from being estimated.

[0104] If the absolute value of the calculated outlier is less than the absolute value of the outlier threshold, the determination model 46A included in the air conditioner 1 classifies the detection value of the second feature value as normal. Then, the air conditioner 1 calculates the refrigerant shortage rate of the refrigerant circuit 6 by performing the multiple regression analysis on the detection value of the first feature value that is acquired at the same time as the detection value of the second feature value that is classified as normal. As a result, it is possible to accurately estimate the refrigerant shortage rate of the refrigerant circuit 6.

[0105] The determination model 46A that is mounted on the air conditioner 1 is generated by the non-linear analysis, such as the Kernel density estimation method, by using a part of the detection value of the first feature value that is used for the estimation model 45A and by using the value of the second feature value that includes operating state quantity that largely affects a cooling cycle operation. The determination model 46A classifies the detection value of the second feature value as normal or abnormal. Then, in the estimation model 45A, the estimation model 45A is generated by using the detection value of the first feature value that is acquired at the same time as the detection value of the second feature value that is classified as normal, instead of using all of the operating state quantities. As a result, it is possible to generate the estimation model 45A with high accuracy.

[0106] In the present embodiment, each of the regression equations of the estimation model 45A is generated by using the feature value that is obtained by a simulation, and, in the feature value that is obtained by the simulation, an abnormal value and a value that is extremely larger or smaller than other values are not included. The detection value of the operating state quantity obtained by performing the data filtering process and the data cleansing process and excluding an abnormal value and an outstanding value is substituted into each of the regression equations or each of the refrigerant shortage rate calculation formulas of the estimation model 45A that is generated by using the feature value obtained by the simulation as described above. At this time, by substituting only the detection value of the first feature value that is acquired at the same time as the detection value of the second feature value that is classified as normal by using the determination model 46A, it is possible to more accurately estimate the refrigerant shortage rate.

[0107] The determination model 46A is generated by using the feature value that is obtained by the simulation, and, in the feature value that is obtained by the simulation, an abnormal value and a value that is extremely larger or smaller than other values are not included. By applying the detection value of the second feature value obtained by performing the data filtering process and the data cleansing process and excluding an abnormal value and an outstanding value as described above to the determination model 46A that is generated by using the feature value that does not include the abnormal value and the outstanding value, it is possible to more accurately determine the detection value of the second feature value. Furthermore, by performing the data filtering process and the data cleansing process, the control circuit 19 is able to decrease an amount of data that is used to calculate the outlier by the determination model 46A, so that it is possible to reduce the time needed for the calculation of the outlier by using the determination model 46A and it is possible to reduce a load applied on the control circuit 19.

[0108] In addition, in the present embodiment, as the second feature value, the operating state quantities illustrated in FIG. 5 and FIG. 6 are used; however, if the determination model 46A is generated by detecting a larger volume of operating state quantity by mounting a larger number of sensors on the refrigerant circuit, and if the determination model 46A generated in this way is used, it is possible to increase a possibility of detection of various failures. In addition, regarding the first feature value, by narrowing down to the state quantity that has the correlation with a decrease in an amount of refrigerant, it is possible to a remaining refrigerant amount with good accuracy.

[0109] Moreover, in the first embodiment described above, a case has been described as an example in which the simulation result of each of the operating state quantities is obtained at the design stage of the air conditioner 1, and the control circuit 19 stores the estimation model 45A and the determination model 46A that are obtained by causing an information processing apparatus, such as a server, having a learning function to learn a simulation result. Instead of this, it may be possible to provide a server 120 that is connected to the air conditioner 1 by a communication network 110, and cause the server 120 to generate the estimation model 45A and the determination model 46A and transmit an estimation result of the estimation model 45A to the air conditioner 1, and an embodiment thereof will be described below.

[0110] Second Embodiment

<Configuration of air conditioning system>

FIG. 14 is a diagram illustrating one example of an

air conditioning system 100 according to a second

embodiment. In addition, by assigning the same reference

numerals to components having the same configuration as

those in the air conditioner 1 according to the first

embodiment, overlapped descriptions of the configuration

and the operation thereof will be omitted. The air

conditioning system 100 illustrated in FIG. 14 includes the

air conditioner 1, the communication network 110, and the

server 120. The air conditioner 1 includes the compressor

11, the outdoor unit 2 that includes the outdoor heat

exchanger 13 and the outdoor unit expansion valve 14, the

indoor unit 3 that includes the indoor heat exchanger 51,

and a control circuit 19A. The air conditioner 1 includes

the refrigerant circuit 6 that is constituted by connecting

both of the outdoor unit 2 and the indoor unit 3 by

refrigerant pipes, such as the liquid pipe 4 and the gas

pipe 5, and a predetermined amount of refrigerant is filled

in the refrigerant circuit 6. The control circuit 19A

includes the acquisition unit 41, the communication unit 42

that is the first communication unit, the storage unit 43,

and the control unit 44. In addition, it is assumed that

the control circuit 19A does not include the estimation

unit 45, the determination unit 46, and the anomaly log

storage unit 43A.

[0111] The server 120 includes a generation unit 121, a communication unit 121A that is a second communication unit, an estimation unit 122, a determination unit 123, and a storage unit 124. The storage unit 124 includes an anomaly log storage unit 124A. The generation unit 121 generates the estimation model 45A by a multiple regression analysis method by using a detection value or a simulation value of the first feature value related to estimation of the refrigerant shortage rate of the refrigerant that is filled in the refrigerant circuit 6. Moreover, the estimation model 45A includes, for example, the first cooling purpose estimation model 45A1, the second cooling purpose estimation model 45A2, the third cooling purpose estimation model 45A3, the first heating purpose estimation model 45A4, the second heating purpose estimation model 45A5, and the third heating purpose estimation model 45A6 that are described in the first embodiment. The estimation unit 122 stores therein the estimation model 45A that has been generated by the generation unit 121. Furthermore, the generation unit 121 generates the determination model 46A by the Kernel density estimation method by using the second feature value. In addition, the determination model 46A includes, for example, the cooling time determination model 46B and the heating time determination model 46C that are described in the first embodiment.

[01121 The determination unit 123 stores therein the determination model 46A that has been generated by the generation unit 121. The determination unit 123 classifies the detection value of the second feature value as normal or abnormal by using the determination model 46A. In the case where the detection value of the second feature value is classified as abnormal, the determination unit 123 stores the detection value of the second feature value that has been classified as abnormal in the anomaly log storage unit 124A as an anomaly log.

[0113] Furthermore, the estimation unit 122 calculates

the refrigerant shortage rate in the refrigerant circuit 6

included in the air conditioner 1 by using the detection

value of the first feature value that is acquired at the

same time as the detection value of the second feature

value that is classified as normal by the determination

model 46A and by using the received estimation model 45A.

The communication unit 121A transmits the refrigerant

shortage rate that has been calculated by the estimation

unit 122 to the air conditioner 1 via the communication

network 110.

[0114] The generation unit 121 generates or updates the

cooling time determination model 46B by using the values of

the second feature values obtained by a simulation

performed in the steady state and the refrigerant leakage

state at the time of a cooling operation performed when the

refrigerant circuit 6 is in a normal state.

[0115] The generation unit 121 periodically collects the

operating state quantities at the time of a cooling

operation from a standard machine (installed in a test room

or the like of a manufacturing company) of the air

conditioner 1 that is able to measure the steady state and

the refrigerant leakage state at the time of a cooling

operation when the refrigerant circuit 6 is in a normal

state, and generates or updates the cooling time

determination model 46B by using a comparison result, which

has been obtained by comparing a classification result that

indicates normal or abnormal and that is obtained by the

cooling time determination model 46B to an actually

measured classification result, and by using the collected

operating state quantities. As a result, it is possible to

generate the cooling time determination model 46B with high accuracy.

[0116] The generation unit 121 periodically collects the operating state quantities at the time of a cooling operation from the standard machine (installed in the test room or the like of the manufacturing company) of the air conditioner 1 that is able to measure the refrigerant shortage rate of the refrigerant circuit 6, and generates or updates the first cooling purpose estimation model 45A1, the second cooling purpose estimation model 45A2, and the third cooling purpose estimation model 45A3 by using a comparison result, which has been obtained by comparing the refrigerant shortage rate that is estimated by each of the estimation models that are included in the estimation model 45A to an actually measured refrigerant shortage rate, and by using the collected operating state quantities. In addition, as in the first embodiment, it may be possible to obtain, by a simulation, the operating state quantity that is used to generate each of the estimation models, and then, the generation unit 121 may generate each of the estimation models that are included in the estimation model 45A by using each of the operating state quantities that are obtained by the simulation.

[0117] The generation unit 121 generates or updates the heating time determination model 46C by using the values of the second feature values that are obtained by a simulation in the steady state and the refrigerant leakage state at the time of a heating operation when the refrigerant circuit 6 is in the normal.

[0118] The generation unit 121 periodically collects the operating state quantities at the time of a heating operation from the standard machine (installed in the test room or the like of the manufacturing company) of the air conditioner 1 that is able to measure the steady state and the refrigerant leakage state at the time of a heating operation when the refrigerant circuit 6 is in the normal state, and generates or updates the heating time determination model 46C by using a comparison result, which has been obtained by comparing the classification result that indicates normal or abnormal and that is obtained by the heating time determination model 46C to the actually measured classification result, and by using the collected operating state quantities. As a result, it is possible to generate the heating time determination model 46C with high accuracy.

[0119] The generation unit 121 periodically collects the operating state quantities at the time of a heating operation from the standard machine of the air conditioner 1 described above, and generates the first heating purpose estimation model 45A4, the second heating purpose estimation model 45A5, and the third heating purpose estimation model 45A6 by using a comparison result, which has been obtained by comparing the refrigerant shortage rate that is estimated by each of the estimation models that are included in the estimation model 45A to the actually measured refrigerant shortage rate, and by using the collected operating state quantities. In addition, as in the first embodiment, it may be possible to obtain, by a simulation, the operating state quantities that is used to generate each of the estimation models 45A, and then, the generation unit 121 may generate each of the estimation models that are included in the estimation model 45A by using each of the operating state quantities that are obtained by the simulation.

[0120] The generation unit 121 generates the determination model 46A by using the feature value that has been obtained by the simulation, and the value of the feature value that has been obtained by the simulation does not include an abnormal value and an extremely large or small value as compared to other values. By applying the detection value of the second feature value from which the abnormal value and the outstanding value are excluded by performing the data filtering process and the data cleansing process as described above to the determination model 46A that is generated by using the value of the feature value that does not include the abnormal value and the outstanding value, it is possible to implement further accurate determination of the detection value of the second feature value. Furthermore, if, in the generation unit

121, the data filtering process and the data cleansing

process is performed on the second feature value as

described in the first embodiment, it is possible to

decrease an amount of data that is used to calculate the

outlier by the determination model 46A. As a result, it is

possible to reduce the time needed to calculate the outlier

by the determination model 46A and it is thus possible to

reduce a usage rate of the server 120, so that it is

possible to reduce the cost needed to calculate the outlier

in a case of a measured rate system in which cost is

increased in accordance with an amount used by the server

120.

[0121] <Effects of second embodiment>

The server 120 according to the second embodiment

generates the determination model 46A by using the values

of the second feature values that are obtained by the

simulation in the steady state and the refrigerant leakage

state when the refrigerant circuit 6 is in the normal

state, and stores the generated determination model 46A in

the determination unit 123. The determination unit 123

included in the server 120 is able to classify, by using the stored determination model 46A, whether each of the detection values of the second feature values that are acquired at a different timing is normal or abnormal.

[0122] The server 120 generates the estimation model 45A by using the value of the first feature value that has been acquired from the air conditioner 1, and stores the generated estimation model 45A in the estimation unit 122. The server 120 estimates the refrigerant shortage rate by using the stored estimation model 45A, and transmits the estimation result to the air conditioner 1 via the communication network 110. As a result, the air conditioner 1 is able to recognize the refrigerant shortage rate of the refrigerant circuit 6.

[0123] In addition, a case has been described as an example in which, in the air conditioner 1 according to the first and the second embodiments, the estimation model 45A and the determination model 46A that are used to estimate the refrigerant shortage rate occurring in the case where the N indoor units 3 are connected to the single outdoor unit 2. In contrast, the air conditioner 1 constituted such that the single outdoor unit 2 and the single indoor unit 3 are connected is also able to estimate the refrigerant shortage rate by using the same method as that described in the first embodiment or the second embodiment. The air conditioner 1 having this configuration will be described as a third embodiment below. Third Embodiment

[0124] In the case where a ratio of the number of one outdoor units to the number of indoor units is one to one, the control circuit includes a fourth cooling purpose estimation model that estimates a refrigerant shortage rate at the time of a cooling operation at the present time, and a fifth heating purpose estimation model that estimates a refrigerant shortage rate at the time of a heating operation at the present time. In addition, for convenience of description, by assigning the same reference numerals to components having the same configuration as those in the air conditioner 1 according to the first embodiment, overlapped descriptions of the configuration and the operation thereof will be omitted. The air conditioner 1 according to the third embodiment is different from the air conditioner 1 according to the first embodiment in that the number of the indoor units 3 to be provided is one, the fourth cooling purpose estimation model that has been generated by using an operating state quantity that is different from the operating state quantities that are used in the first to the third cooling purpose estimation models 45A1, 45A2, and 45A3 is used, and the fourth heating purpose estimation model that has been generated by using an operating state quantity that is different from the operating state quantities that are used in the first to the third heating purpose estimation models 45A4, 45A5, and 45A6 is used.

[0125] The fourth cooling purpose estimation model is a seventh regression equation that has been generated by using the multiple regression analysis method. The seventh regression equation is, for example, (a71 x the outdoor heat exchange temperature) - (a72 x the outdoor air temperature) - (a73 x the discharge temperature) + (a74 x

the rotation speed of the compressor 11) - (a75 x the degree of opening of the expansion valve) + a76. It is assumed that the coefficients a71 to a75 are determined at the time of generation of the estimation model. The estimation unit 45 calculates the refrigerant shortage rate at the present time by substituting, into the seventh regression equation, the detection value of the first feature value that is acquired at the same time as the detection value of the second feature value that has been classified as normal in the determination model 46A from among the current operating state quantities that are subjected to data cleansing, that is, for example, the outdoor heat exchange temperature, the outdoor air temperature, the discharge temperature, the rotation speed of the compressor 11, and the degree of opening of the expansion valve. Moreover, the reason for substituting the outdoor heat exchange temperature, the outdoor air temperature, the discharge temperature, the rotation speed of the compressor 11, and the degree of opening of the expansion valve is to use the feature value that is used to generate the fourth cooling purpose estimation model. In addition, the outdoor heat exchange temperature is detected by the refrigerant temperature sensor 35.

[0126] The fourth heating purpose estimation model is an

eighth regression equation that has been generated by using

the multiple regression analysis method. The eighth

regression equation is, for example, (a81 x the indoor heat

exchange temperature) + (a82 x the rotation speed of the

compressor 11) + (a83 x the outdoor air temperature) - (a84

x the outdoor heat exchange temperature) - (a85 x the

degree of opening of the expansion valve) + a86. It is

assumed that the coefficients a81 to a85 are determined at

the time of generation of the estimation model. The

estimation unit 45 calculates the refrigerant shortage rate

at the present time by substituting, into the eighth

regression equation, the detection value of the first

feature value that is acquired at the same time as the

detection value of the second feature value that has been

classified as normal in the determination model 46A from among the current operating state quantities that are subjected to data cleansing, that is, for example, the indoor heat exchange temperature, the rotation speed of the compressor 11, the outdoor air temperature, the outdoor heat exchange temperature, the outdoor air temperature, the discharge temperature, and the degree of opening of the expansion valve. Moreover, the reason for substituting the indoor heat exchange temperature, the rotation speed of the compressor 11, the outdoor air temperature, the outdoor heat exchange temperature, the outdoor air temperature, the discharge temperature, and the degree of opening of the expansion valve is to use the feature value that is used to generate the fourth heating purpose estimation model. In addition, the indoor heat exchange temperature at the time of a heating operation is able to be converted from the pressure value that has been detected by the discharge pressure sensor 31.

[0127] In addition, in the present embodiment, a case

has been described as an example in which a relative amount

of refrigerant that represents an amount of refrigerant

remaining in the refrigerant circuit 6 is estimated.

Specifically, a case has been described as an example in

which the refrigerant shortage rate, which is the ratio of

the amount of refrigerant that has leaked to the outside

from the refrigerant circuit 6 to a fill volume (initial

value) at the time at which a refrigerant is filled in the

refrigerant circuit 6, is estimated and provided. However,

the present invention is not limited to this, and it may be

possible to provide an amount of refrigerant that has

leaked to the outside from the refrigerant circuit 6 by

multiplying the initial value by the estimated refrigerant

shortage rate. In addition, it may be possible to generate

an estimation model for estimating an absolute amount of the refrigerant that has leaked to the outside from the refrigerant circuit 6 or an absolute amount of the refrigerant that remains in the refrigerant circuit 6, and provide an estimation result that is obtained by the estimation model. In the case where an estimation model for estimating an absolute amount of the refrigerant that has leaked to the outside from the refrigerant circuit 6 or an absolute amount of the refrigerant that remains in the refrigerant circuit 6 is generated, in addition to each of the operating state quantities as described above, volumes of the outdoor heat exchanger 13 and each of the indoor heat exchangers 51 and a volume of the liquid pipe 4 may be considered.

[0128] <Modification>

Furthermore, in the present embodiment, for example, a

case has been described as an example in which the

estimation result of the first cooling purpose estimation

model 45A1 and the estimation result of the second cooling

purpose estimation model 45A2 are interpolated by the

sigmoid coefficients; however, the example is not limited

to the sigmoid coefficients, and, for example, an

interpolate method, such as linear interpolate, may be

used, and appropriate modifications are possible.

[0129] In the present embodiment, some of simulation

results are used from among the plurality of simulation

results, instead of using all of the simulation results.

For example, the first cooling purpose estimation model

45A1 that is used when the refrigerant shortage rate at the

time of a cooling operation is in a range of 0 to 30%, the

second cooling purpose estimation model 45A2 that is used

when the refrigerant shortage rate is in a range of 40 to

70%, the third cooling purpose estimation model 45A3 that

is used when the refrigerant shortage rate is in a range of

30 to 40% are generated in a separate manner. Therefore,

the operating state quantities are prepared by simulations,

so that it is possible to easily collect a needed amount of

operating state quantities as compared to a case in which

the operating state quantities are collected by operating

the air conditioner 1.

[0130] In the present embodiment, a case has been

described as an example in which the estimation model 45A

and the determination model 46A are generated by the server

120 or the control circuit 19; however, a user may

calculate the estimation model 45A and the determination

model 46A from the simulation result. Furthermore, in the

present embodiment, a case has been described as an example

in which each of the estimation models is generated by

using the multiple regression analysis method; however, it

may be possible to generate the estimation model by using

support vector regression (SVR), a neural network (NN), or

the like of a machine learning model that can perform a

general regression analysis method. At this time, at the

time of selection of a feature value, instead of the P

value and the correction value R2 that are used in the

multiple regression analysis method, a general method (a

forward feature selection method, a backward feature

elimination, or the like) for selecting a feature value

such that accuracy of the estimation model is improved may

be used.

[0131] Furthermore, in the present embodiment, a case

has been described as an example in which the determination

model 46A is generated by using the Kernel density

estimation method; however, the example is not limited to

the Kernel density estimation method as long as a non

linear analysis method is used, and appropriate

modifications are possible.

[0132] Furthermore, in the present embodiment, a case

has been described as an example in which the air

conditioner 1 is constituted such that the one or more

indoor units 3 are connected to the single outdoor unit 2;

however, the embodiment may also be applicable to the air

conditioner 1 in which the one or more indoor units 3 are

connected to the two or more outdoor units 2.

[0133] In the first embodiment, a case has been

described as an example in which the simulation result of

each of the operating state quantities is obtained at the

design stage of the air conditioner 1, and the control

circuit 19 stores therein the estimation model 45A and the

determination model 46A that are obtained by causing an

information processing apparatus, such as a server, having

a learning function to learn a simulation result. However,

it may be possible to provide a server that is connected to

the air conditioner 1 via a communication network, and the

server may generate and transmit the estimation model 45A

and the determination model 46A to the air conditioner 1.

In addition, the air conditioner 1 may store the estimation

model 45A and the determination model 46A that are received

from the server in the control circuit 19.

[0134] The refrigerant circuit 6 is constituted such

that at least the one indoor unit 3 that is connected to at

least the one outdoor unit 2 is connected by a refrigerant

pipe. Therefore, the estimation model 45A is able to

estimate the refrigerant shortage rate by using the

detection value of the first feature value of the single

representative outdoor unit 2 among at least the one

outdoor unit 2 and the detected value of the first feature

value of the single representative indoor unit 3 among at

least the one indoor unit 3. In addition, it is assumed

that the representative outdoor unit 2 is selected from at least the one outdoor unit 2 that is in operation on the basis of an arbitrary rule, and the representative indoor unit 3 is also selected from at least the one indoor unit 3 that is in operation on the basis of an arbitrary rule.

The arbitrary rule is, for example, ascending order of

identification numbers that are assigned to the devices.

[0135] Each of the components in the units illustrated

in the drawings is not always physically configured as

illustrated in the drawings. In other words, the specific

shape of a separate or integrated unit is not limited to

the drawings; however, all or part of the unit can be

configured by functionally or physically separating or

integrating any of the units depending on various kinds of

loads or use conditions.

[0136] Furthermore, all or any part of various

processing functions performed by each unit may also be

executed by a central processing unit (CPU) (or, a

microcomputer, such as a micro processing unit (MPU) or a

micro controller unit (MCU)). In addition, all or any part

of various processing functions may also be, of course,

executed by programs analyzed and executed by the CPU (or

the microcomputer, such as the MPU or the MCU), or executed

by hardware by wired logic.

[0137] Furthermore, in each of the embodiments described

above, it is assumed that the refrigerant shortage rate

corresponds to an amount of reduction from a defined amount

in the case where the defined amount of the refrigerant

that is filled is defined as 100%. Instead of this, it may

be possible to estimate the refrigerant shortage rate by

using the method described in the present embodiment

immediately after the defined amount of the refrigerant is

filled in the refrigerant circuit 6, and set the obtained

estimation result as 100%. For example, if the refrigerant shortage rate that is estimated immediately after the defined amount of refrigerant is filled in the refrigerant circuit 6 is 90%, that is, if it is estimated that the amount of refrigerant that is currently filled in the refrigerant circuit 6 is smaller than the defined amount by

10%, it may be possible to set the amount of refrigerant

that is smaller than the defined amount by as 100%. By

adjusting the refrigerant amount that is set as 100% to the

estimation result, it is possible to more accurately

estimate the refrigerant shortage rate.

Reference Signs List

[0138] 1 air conditioner

2 outdoor unit

3 indoor unit

41 acquisition unit

44 control unit

45 estimation unit

45A estimation model

46 determination unit

46A determination model

46B cooling time determination model

46C heating time determination model

100 air conditioning system

120 server

121 generation unit

121A communication unit

122 estimation unit

123 determination unit

Claims (38)

1. An air conditioning system comprising:

an air conditioner that includes a refrigerant circuit

that is constituted to have a structure in which at least

one indoor unit is connected to an outdoor unit by a

refrigerant pipe and a predetermined amount of refrigerant

is filled; and

a server that is communicably connected to the air

conditioner, wherein

the air conditioner includes

a detection unit that detects a state quantity

related to control of the air conditioner,

an acquisition unit that acquires a detection

value that has been detected by the detection unit, and

a first communication unit that transmits the

detection value that has been acquired by the acquisition

unit to the server, and

the server includes

a second communication unit that receives the

detection value from the air conditioner,

an estimation unit that estimates a remaining

refrigerant amount of the refrigerant that remains in the

refrigerant circuit by using a detection value of a first

feature value in a case where a state quantity related to

an amount of the refrigerant that is filled in the

refrigerant circuit is indicated by the first feature

value, and

a determination unit that determines by using a

second feature value whether or not the detection value of

the first feature value is a detection value that is to be

used to estimate the remaining refrigerant amount performed

by the estimation unit, the second feature value being

obtained when the refrigerant circuit is operated normally and when only the remaining refrigerant amount is changed.

2. The air conditioning system according to claim 1,

wherein, in a case where, from among the state quantities,

state quantities that include at least one state quantity

that is included in the first feature value and at least

one state quantity that is not included in the first

feature value are indicated by the second feature value,

the determination unit determines, by using a detection

value of the second feature value, whether or not the

detection value of the first feature value is the detection

value that is to be used to estimate the remaining

refrigerant amount.

3. The air conditioning system according to claim 2,

wherein the number of state quantities included in the

second feature value is larger than the number of state

quantities included in the first feature value.

4. The air conditioning system according to claim 2 or 3,

wherein

the estimation unit

includes an estimation model that is generated by

using the first feature value, and

estimates the remaining refrigerant amount by

applying the detection value of the first feature value to

the estimation model, and

the determination unit

includes a determination model that is generated

by using the second feature value, and

determines, by applying the detection value of

the second feature value to the determination model,

whether or not the detection value of the first feature value is to be used to estimate the remaining refrigerant amount performed by the estimation unit.

5. The air conditioning system according to claim 4,

wherein

the determination model calculates, by adopting the

second feature value that is used to generate the

determination model as a normal sample value, an outlier

that indicates a degree of deviation from the normal sample

value related to the detection value of the second feature

value from among the detection values acquired by the

acquisition unit, and,

when an absolute value of the calculated outlier is

larger than a predetermined threshold, the determination

unit does not estimate the remaining refrigerant

amount performed by the estimation unit by using the

detection value of the first feature value that is acquired

at the same time as the detection value of the second

feature value, and,

when the absolute value of the calculated outlier is

less than the predetermined threshold, the determination

unit estimates the remaining refrigerant amount performed

by the estimation unit by using the detection value of the

first feature value that is acquired at the same time as

the detection value of the second feature value.

6. The air conditioning system according to claim 1, 2,

3, or 5, wherein, before the remaining refrigerant amount

is estimated by the estimation unit, the determination unit

determines whether or not the detection value of the first

feature value is to be used.

7. The air conditioning system according to claim 4, wherein, before the remaining refrigerant amount is estimated by the estimation unit, the determination unit determines whether or not the detection value of the first feature value is to be used.

8. The air conditioning system according to claim 4, wherein the second feature value that is used to generate the determination model is a value that is obtained from a result of a simulation of an operation of the refrigerant circuit when the operation of the refrigerant circuit is normal and only the remaining refrigerant amount has been changed.

9. The air conditioning system according to claim 4, wherein the outdoor unit includes a compressor, the detection unit includes a suction temperature sensor that detects a suction temperature that is a temperature of the refrigerant that is sucked into the compressor, and the second feature value includes a rotation speed of the compressor and the suction temperature.

10. The air conditioning system according to claim 9, wherein the determination model includes a heating time determination model that is used when the air conditioner performs a heating operation, and a cooling time determination model that is used when the air conditioner performs a cooling operation, and the second feature value that is used by the heating time determination model is different from the second feature value that is used by the cooling time determination model except for the rotation speed of the compressor and the suction temperature.

11. The air conditioning system according to claim 10, wherein the outdoor unit further includes an outdoor heat exchanger, and an outdoor unit expansion valve, the detection unit further includes a discharge temperature sensor that detects a discharge temperature that is a temperature of the refrigerant that is discharged from the compressor, a discharge pressure sensor that detects a discharge pressure that is a pressure of the refrigerant that is discharged from the compressor, and a suction pressure sensor that detects a suction pressure that is a pressure of the refrigerant that is sucked into the compressor, the discharge temperature, the suction pressure, a low pressure saturation temperature that is calculated by using the suction pressure, and a degree of opening of the outdoor unit expansion valve are included as the second feature value that is used for the heating time determination model, and the heat exchange outlet temperature of the outdoor heat exchanger, a high pressure saturation temperature that is calculated by using the discharge pressure, and the discharge pressure are included as the second feature value that is used for the cooling time determination model.

12. The air conditioning system according to claim 4, wherein the indoor unit includes an indoor heat exchanger, and an indoor unit expansion valve, the detection unit includes a refrigerant temperature sensor that detects an indoor unit side heat exchange inlet temperature that is a temperature of the refrigerant flowing into the indoor heat exchanger at the time of a heating operation, and an indoor unit side heat exchange outlet temperature that is a temperature of the refrigerant flowing out from the indoor heat exchanger at the time of the heating operation, and the second feature value includes the indoor unit side heat exchange inlet temperature, the indoor unit side heat exchange outlet temperature, and a degree of opening of the indoor unit expansion valve.

13. The air conditioning system according to claim 4,

wherein

the estimation model is generated by using linear

analysis, and

the determination model is generated by using non

linear analysis.

14. The air conditioning system according to claim 5, 8,

9, 10, 11, or 12, wherein

the estimation model is generated by using linear

analysis, and

the determination model is generated by using non

linear analysis.

15. A refrigerant amount estimation method that is implemented by an air conditioning system that includes an air conditioner that includes a refrigerant circuit that is constituted to have a structure in which at least one indoor unit is connected to an outdoor unit by a refrigerant pipe and a predetermined amount of refrigerant is filled, and a server that is communicably connected to the air conditioner, the refrigerant amount estimation method for the air conditioning system comprising: detecting, performed by a detection unit included in the air conditioner, a state quantity related to control of the air conditioner; acquiring, performed by an acquisition unit included in the air conditioner, a detection value of the detected state quantity; transmitting, performed by a first communication unit included in the air conditioner, the acquired detection value to the server; receiving, performed by a second communication unit included in the server, the detection value from the air conditioner; determining by using a second feature value, performed by a determination unit included in the server, whether or not a detection value of a first feature value is a detection value that is to be used to estimate a remaining refrigerant amount in a case where a state quantity related to an amount of the refrigerant that is filled in the refrigerant circuit is indicated by the first feature value, the second feature value being obtained when the refrigerant circuit is operated normally and when only the remaining refrigerant amount is changed; and estimating, performed by an estimation unit included in the server, the remaining refrigerant amount of the refrigerant that remains in the refrigerant circuit by using the detection value of the first feature value.

16. The refrigerant amount estimation method for the air

conditioning system according to claim 15, wherein, in a

case where, from among the state quantities, state

quantities that include at least one state quantity that is

included in the first feature value and at least one state

quantity that is not included in the first feature value

are indicated by the second feature value, the determining

includes determining, performed by the determination unit,

by using a detection value of the second feature value,

whether or not the detection value of the first feature

value is the detection value that is to be used to estimate

the remaining refrigerant amount.

17. The refrigerant amount estimation method for the air

conditioning system according to claim 16, further

comprising:

inputting, performed by the determination unit, the

detection value of the second feature value to a

determination model that has been generated by using the

second feature value;

calculating, performed by the determination unit, by

adopting the second feature value that is used to generate

the determination model as a normal sample value, an

outlier that indicates a degree of deviation from the

normal sample value related to the detection value of the

second feature value from among the detection values

acquired by the acquisition unit; and

determining, performed by the determination unit, when an absolute value of the outlier is larger than a predetermined threshold, that the detection value of the first feature value that is acquired at the same time as the detection value of the second feature value is not to be used to estimate the remaining refrigerant amount.

18. The refrigerant amount estimation method for the air conditioning system according to claim 17, wherein the second feature value that is used to generate the determination model is a value that is obtained from a result of a simulation of an operation of the refrigerant circuit when the operation of the refrigerant circuit is normal and only the remaining refrigerant amount has been changed.

19. The refrigerant amount estimation method for the air conditioning system according to claim 17, further comprising determining, performed by the determination unit, when the absolute value of the outlier is less than the predetermined threshold, that the detection value of the first feature value that is acquired at the same time as the detection value of the second feature value is to be used to estimate the remaining refrigerant amount.

20. An air conditioner that includes a refrigerant circuit that is constituted to have a structure in which at least one indoor unit is connected to an outdoor unit by a refrigerant pipe and a predetermined amount of refrigerant is filled, the air conditioner comprising: a detection unit that detects a state quantity related to control of the air conditioner; an acquisition unit that acquires a detection value that has been detected by the detection unit; an estimation unit that estimates a remaining refrigerant amount of the refrigerant that remains in the refrigerant circuit by using a detection value of a first feature value in a case where a state quantity related to an amount of the refrigerant that is filled in the refrigerant circuit is indicated by the first feature value; and a determination unit that determines by using a second feature value whether or not the detection value of the first feature value is a detection value that is to be used to estimate the remaining refrigerant amount performed by the estimation unit, the second feature value being obtained when the refrigerant circuit is operated normally and when only the remaining refrigerant amount is changed.

21. The air conditioner according to claim 20, wherein, in a case where, from among the state quantities, state quantities that include at least one state quantity that is included in the first feature value and at least one state quantity that is not included in the first feature value are indicated by the second feature value, the determination unit determines, by using a detection value of the second feature value, whether or not the detection value of the first feature value is the detection value that is to be used to estimate the remaining refrigerant amount.

22. The air conditioner according to claim 21, wherein the number of state quantities included in the second feature value is larger than the number of state quantities included in the first feature value.

23. The air conditioner according to claim 21 or 22, wherein the estimation unit includes an estimation model that is generated by using the first feature value, and estimates the remaining refrigerant amount by applying detection value of the first feature value to the estimation model, and the determination unit includes a determination model that is generated by using the second feature value, and determines, by applying the detection value of the second feature value to the determination model, whether or not the detection value of the first feature value is to be used to estimate the remaining refrigerant amount performed by the estimation unit.

24. The air conditioner according to claim 23, wherein

the determination model calculates, by adopting the

second feature value that is used to generate the

determination model as a normal sample value, an outlier

that indicates a degree of deviation from the normal sample

value related to the detection value of the second feature

value from among the detection values acquired by the

acquisition unit, and,

when an absolute value of the calculated outlier is

larger than a predetermined threshold, the determination

unit does not estimate the remaining refrigerant

amount performed by the estimation unit by using the

detection value of the first feature value that is acquired

at the same time as the detection value of the second

feature value, and,

when the absolute value of the calculated outlier is

less than the predetermined threshold, the determination unit estimates the remaining refrigerant amount performed by the estimation unit by using the detection value of the first feature value that is acquired at the same time as the detection value of the second feature value.

25. The air conditioner according to claim 20, 21, 22, or 24, wherein, before the remaining refrigerant amount is estimated by the estimation unit, the determination unit determines whether or not the detection value of the first feature value is to be used.

26. The air conditioner according to claim 23, wherein, before the remaining refrigerant amount is estimated by the estimation unit, the determination unit determines whether or not the detection value of the first feature value is to be used.

27. The air conditioner according to claim 23, wherein the second feature value that is used to generate the determination model is a value that is obtained from a result of a simulation of an operation of the refrigerant circuit when the operation of the refrigerant circuit is normal and only the remaining refrigerant amount has been changed.

28. The air conditioner according to claim 23, wherein the outdoor unit includes a compressor, the detection unit includes a suction temperature sensor that detects a suction temperature that is a temperature of the refrigerant that is sucked into the compressor, and the second feature value includes a rotation speed of the compressor and the suction temperature.

29. The air conditioner according to claim 28, wherein the determination model includes a heating time determination model that is used when the air conditioner performs a heating operation, and a cooling time determination model that is used when the air conditioner performs a cooling operation, and the second feature value that is used by the heating time determination model is different from the second feature value that is used by the cooling time determination model except for the rotation speed of the compressor and the suction temperature.

30. The air conditioner according to claim 29, wherein the outdoor unit further includes an outdoor heat exchanger, and an outdoor unit expansion valve, the detection unit further includes a discharge temperature sensor that detects a discharge temperature that is a temperature of the refrigerant that is discharged from the compressor, a discharge pressure sensor that detects a discharge pressure that is a pressure of the refrigerant that is discharged from the compressor, and a suction pressure sensor that detects a suction pressure that is a pressure of the refrigerant that is sucked into the compressor, the discharge temperature, the suction pressure, a low pressure saturation temperature that is calculated by using the suction pressure, and a degree of opening of the outdoor unit expansion valve are included as the second feature value that is used for the heating time determination model, and the heat exchange outlet temperature of the outdoor heat exchanger, a high pressure saturation temperature that is calculated by using the discharge pressure, and the discharge pressure are included as the second feature value that is used for the cooling time determination model.

31. The air conditioner according to claim 23, wherein the indoor unit includes an indoor heat exchanger, and an indoor unit expansion valve, the detection unit includes a refrigerant temperature sensor that detects an indoor unit side heat exchange inlet temperature that is a temperature of the refrigerant flowing into the indoor heat exchanger at the time of a heating operation, and an indoor unit side heat exchange outlet temperature that is a temperature of the refrigerant flowing out from the indoor heat exchanger at the time of the heating operation, and the second feature value includes the indoor unit side heat exchange inlet temperature, the indoor unit side heat exchange outlet temperature, and a degree of opening of the indoor unit expansion valve.

32. The air conditioner according to claim 23, wherein the estimation model is generated by using linear analysis, and the determination model is generated by using non linear analysis.

33. The air conditioner according to claim 24, 27, 28, 29, 30, or 31, wherein the estimation model is generated by using linear analysis, and the determination model is generated by using non linear analysis.

34. A refrigerant amount estimation method for estimating a remaining refrigerant amount in an air conditioner that includes a refrigerant circuit that is constituted to have a structure in which at least one indoor unit is connected to an outdoor unit by a refrigerant pipe and a predetermined amount of refrigerant is filled or estimating a remaining refrigerant amount in an air conditioning system that includes the air conditioner, the refrigerant amount estimation method for the air conditioner comprising: detecting a state quantity related to control of the air conditioner; acquiring a detection value of the detected state quantity; determining by using a second feature value whether or not a detection value of a first feature value is a detection value that is to be used to estimate the remaining refrigerant amount in a case where a state quantity related to an amount of the refrigerant that is filled in the refrigerant circuit is indicated by the first feature value, the second feature value being obtained when the refrigerant circuit is operated normally and when only the remaining refrigerant amount is changed; and estimating the remaining refrigerant amount of the refrigerant that remains in the refrigerant circuit by using the detection value of the first feature value.

35. The refrigerant amount estimation method for the air

conditioner according to claim 34, wherein, in a case

where, from among the state quantities, state quantities

that include at least one state quantity that is included

in the first feature value and at least one state quantity

that is not included in the first feature value are

indicated by the second feature value, the determining

includes determining, by using a detection value of the

second feature value, whether or not the detection value of

the first feature value is the detection value that is to

be used to estimate the remaining refrigerant amount.

36. The refrigerant amount estimation method for the air

conditioner according to claim 35, wherein the determining

further includes

calculating, by adopting the second feature value as a

normal sample value, an outlier that indicates a degree of

deviation from the normal sample value related to the

detection value of the second feature value from among the

acquired detection values, and

determining, when an absolute value of the outlier is

larger than a predetermined threshold, that the detection

value of the first feature value that is acquired at the

same time as the detection value of the second feature

value is not to be used to estimate the remaining

refrigerant amount.

37. The refrigerant amount estimation method for the air

conditioner according to claim 35 or 36, wherein the second

feature value that is used at the determining is a value

that is obtained from a result of a simulation of an operation of the refrigerant circuit when the operation of the refrigerant circuit is normal and only the remaining refrigerant amount has been changed.

38. The refrigerant amount estimation method for the air conditioner according to claim 36, further comprising determining, when the absolute value of the outlier is less than the predetermined threshold, that the detection value of the first feature value that is acquired at the same time as the detection value of the second feature value is to be used to estimate the remaining refrigerant amount.