JP6893750B2 - Injection molding machine, injection molding machine status notification system, injection molding machine status notification method - Google Patents

Description

The present invention relates to an injection molding machine that notifies a maintenance status, a state notification system of an injection molding machine that notifies a maintenance status, and a state notification method of an injection molding machine that notifies a maintenance status.

Conventionally, as an information management device for an injection molding machine that can accurately detect an abnormality of a part used for injection molding, the one described in Patent Document 1 is known. In Patent Document 1, in a cycle operation in which a molded product is repeatedly manufactured under the same setting conditions, the n (n is a natural number of 2 or more) second shot and m (m is n minus a predetermined positive natural number) of 1 or more. An abnormality of a part is detected by calculating the difference between the actual value of the physical quantity representing the load applied to the part and the second shot (natural number). More specifically, as described in (0058) to (0064) of the specification, an abnormality is detected by a physical quantity representing a load. Then, when a minor abnormality occurs as described in (0074) to (0077), the cycle operation may be continued, and when a serious abnormality occurs, the cycle operation is interrupted.

In addition, by diagnosing the information of the injection molding machine, it is possible to estimate and prevent the occurrence of abnormalities, prevent erroneous diagnosis of abnormalities, and prevent unexpected production suspension as an injection molding system. Is known as described in Patent Document 2. In Patent Document 2, an injection molding machine and a diagnostic server are connected by a communication line, the measured value of the calorific value of the motor is compared with the estimated value, and the difference between the measured values is out of the permissible range or exceeds the permissible range. It is described that the diagnosis request data is transmitted to the diagnosis server when the number of times is determined to be abnormal in the allowable number of times (0038). As a result, it is possible to prevent abnormal development due to a delay in maintenance management (0045).

What is common to the above two patent documents 1 and 2 is not to detect an abnormal state and immediately stop the injection molding machine, but to notify while continuing the operation when a slight abnormality is detected. This means that countermeasures will be taken before a serious abnormality occurs.

JP-A-2017-87588 (Claim 1, (0058) to (0064), (0074) to (0077), FIG. 1) JP-A-2014-184461 (Claim 1, (0038), (0045), (Fig. 1), (Fig. 3))

However, it is very difficult to accurately capture the occurrence of a slight abnormality that can continue the operation as described in Patent Document 1 and Patent Document 2. That is, there is a problem that it is difficult to accurately capture a slight abnormality under any condition in response to a change in the material to be molded, a change in molding conditions accompanying the change, and a change in disturbance factors such as weather conditions such as temperature and humidity. was there. Further, Patent Document 1 and Patent Document 2 do not describe at all when the abnormality detected in the injection molding machine is transmitted or not transmitted.

Therefore, an object of the present invention is to provide an injection molding machine, a state notification system for an injection molding machine, and a state notification method for the injection molding machine, which can appropriately notify the maintenance status.

The injection molding machine according to claim 1 of the present invention detects that the operating state of the injection molding machine is a non-steady value deviating from the steady value as a value including a metered value in the injection molding machine that notifies the maintenance state. It is calculated from both the detection means for counting, the counting means for counting the integrated value consisting of at least one of the number of conversion hours or the number of conversions, and the non-stationary value and the integrated value in which the non-stationary value including the metered value is accumulated. It is characterized in that a notification means for notifying the maintenance status of the injection molding machine is provided when the value reaches or exceeds a predetermined threshold value.

Injection molding machine according to claim 2 of the present invention, in claim 1, and the value calculated from both of the accumulated non-steady-state value and said integrated value is set in three stages to four stages threshold When the threshold value is exceeded, a notification means for notifying different maintenance states of the injection molding machine corresponding to each threshold value is provided.

Injection molding machine according to claim 3 of the present invention, in claim 1 or claim 2, the value which is calculated from both of said integrated value and said accumulated non-stationary values, machine learning using a neural network It is characterized in that it is weighted by the device.

The state notification system for an injection molding machine according to claim 4 of the present invention is a state notification system for an injection molding machine that notifies a maintenance state, and is a central control device inside a company in which the injection molding machine is arranged or the injection molding. It is characterized in that it is connected to a control device outside the company where the machine is arranged and the maintenance status of the injection molding machine can be transmitted to the control device outside the company.

The state notification system for an injection molding machine according to claim 5 of the present invention, in claim 4, when the maintenance status is notified to at least the screen of the injection molding machine and the operator permits transmission from the screen or another device. The maintenance status of the injection molding machine is transmitted to the control device outside the company.

The state notification system for an injection molding machine according to claim 6 of the present invention is the control device inside the central control device inside the company or outside the company where the injection molding machine is arranged according to claim 4 or 5. The machine learning device is provided inside the company, or is directly connected to the central control device inside the company or directly connected to the control device outside the company where the injection molding machine is arranged. To do.

The state notification method for an injection molding machine according to claim 7 of the present invention is a non-steady value in which the operating state of the injection molding machine deviates from the steady value in the state notification method for the injection molding machine that notifies the maintenance state. Is detected by the detecting means as a value including the metered value, and the integrated value measured from at least one of the number of conversion hours or the number of conversions is counted by the counting means, and the non-stationary value including the metered value is accumulated. When the value calculated from both the integrated value and the integrated value reaches a predetermined threshold value or exceeds the threshold value, the maintenance state is notified by the notification means.

The method for notifying the state of an injection molding machine according to claim 8 of the present invention is characterized in that, in claim 7, different maintenance states are notified corresponding to a threshold value of 3 to 4 steps.

The state notification method for an injection molding machine according to claim 9 of the present invention is characterized in that, in claim 8 , the notification of the different maintenance state uses a machine learning device that performs supervised learning.

The injection molding machine of the present invention is converted into a detection means for detecting that the operating state of the injection molding machine is a non-steady value deviating from the steady value as a value including a metered value in the injection molding machine that notifies the maintenance state. A counting means that counts an integrated value consisting of at least one of the number of hours or the number of conversions, and a value calculated from both the non-stationary value in which the non-stationary value including the metered value is accumulated and the integrated value is a predetermined threshold value. Since the notification means for notifying the maintenance status of the injection molding machine is provided when the maintenance status is exceeded or the threshold value is exceeded, the maintenance status can be appropriately notified.

It is the schematic of the injection molding machine of this embodiment and the state notification system of the injection molding machine. It is explanatory drawing which shows the calculation method of the maintenance state of the injection molding machine of this embodiment, the state notification system of an injection molding machine, and the state notification method of an injection molding machine. It is a flowchart of the injection molding machine of this embodiment, the state notification system of an injection molding machine, and the state notification method of an injection molding machine. It is the schematic of the injection molding machine of 2nd Embodiment and the state notification system of the injection molding machine. It is a block diagram of the control device of the injection molding machine and the state notification system of the injection molding machine of the third embodiment. It is explanatory drawing which shows the neural network of the machine learning device of the control device of the injection molding machine and the state notification system of the injection molding machine of the third embodiment.

The injection molding machine 11 and the state notification system 12 of the injection molding machine of the present invention will be described with reference to FIG. The injection molding machine 11 is an injection molding machine capable of notifying the maintenance status, and is connected to a central control device 14 in the factory 13 or an external control device 16 such as, for example, an injection molding machine manufacturer 15.

The injection molding machine 11 is provided with an injection device 17 for injecting molten resin and a mold clamping device 19 for molding the molding die 18. The injection device 17 has a screw 22 having a check valve 21 built in the heating cylinder 20, and the screw 22 is rotated by a weighing servomotor 23, and forward / backward movement and back pressure control are performed by the injection servomotor 24. Is done. The mold clamping device 19 is provided with a mold clamping mechanism 25 and a mold opening / closing mechanism 26, and a fixed mold 18a is attached to the fixed plate 27, and a movable mold 18b is attached to the movable plate 28. However, the injection molding machine 11 may be operated by another mechanism, and the type thereof is not limited.

Further, the injection molding machine 11 is provided with a control device 29, and a display device 30 that also serves as an operation screen is connected to the control device 29. The display device 30 includes a touch panel of a liquid crystal panel, and in addition to displaying various information about the injection molding machine, the operator touches the touch panel to input molding conditions and the like. In addition to the display device 30 composed of the touch panel, button keys such as a numeric keypad and various function keys may be provided. The notification means for notifying the maintenance status of the injection molding machine 11 includes a control device 29, a display device 30, and the like.

Further, the control device 29 is attached to the injection molding machine 11 and is connected to various sensors (not shown) which are detection means for detecting the state of the injection molding machine 11. Since the sensors attached to the injection molding machine 11 are known, not all of them will be described, but typical examples of the sensors of each servomotor such as the weighing servomotor 23, the injection servomotor 24, and the servomotor of the mold opening / closing mechanism 25. Position sensors such as rotary encoders that detect the rotation angle and the position of moving parts moved by each servomotor, linear scales that detect the position of moving parts, current sensors and voltage sensors that detect loads and torques of servomotors, etc. Temperature sensors such as thermocouples that detect the heating of parts heated by heaters and switchboards, force sensors such as load cells that detect the force applied to moving parts, and hydraulic pressure of each part of the hydraulic mechanism such as mold clamping cylinders There is a hydraulic sensor, etc. Alternatively, a sensor such as a vibration sensor or a sound level meter may be separately attached to detect the unsteady state of the injection molding machine 11.

These sensors detect signals during sequence control during molding of the injection molding machine 11, but in the present invention, they also serve as a detecting means for detecting that the operating state of the injection molding machine 11 is unsteady. .. Further, the detecting means for detecting the state of the injection molding machine 11 may be a peripheral device included in the injection molding machine in a broad sense or one installed in the vicinity of the injection molding machine. In the present embodiment, the take-out machine 34 is attached to the upper part of the fixing plate 27, and the take-out machine 34 is provided with a sensor 35 including a load cell for detecting the weight of the molded product. The weight measuring device for the molded product, which is the detection means, may be arranged in the vicinity of the injection molding machine 11.

The control device 29 includes a storage unit, a calculation unit, an input / output unit, and the like. In addition to storing a program for sequence control when performing injection molding, the storage unit also stores data and a program for detecting the state of the present embodiment. Further, in the calculation unit 29a, in addition to various data processing at the time of injection molding, the state determination of the injection molding machine 11 of the present embodiment is performed. Further, the input / output unit is connected to the actuator and the sensor. Then, the transmission of the output signal from the arithmetic unit to the actuator and the transmission of the input signal from the sensor or the like to the arithmetic unit 29a are performed via the input / output unit. Further, in the present embodiment, the timer is attached to the calculation unit 29a or the calculation unit 29a, and detects the operating time of each of the above units. In the present invention, the calculation unit 29a including the timer corresponds to a counting means that counts the operating time and processes it as an integrated value N.

Further, the control device 29 of the injection molding machine 11 is connected to the central control device 14 in the factory 13 where the injection molding machine 11 is arranged or in the company via an input / output unit via a line 31. In the company, the line 31 between the personal computer 14a including the server of the central control device 14 and the injection molding machines 11, 11, 11 may be a dedicated communication line, or an intranet constructed inside the company. It may be an Ethernet (registered trademark) line or an Ethernet (registered trademark) line. Further, the line connection between the injection molding machine 11 and the central control device 14 may be connected by a wireless LAN or WiFi, and the communication method is not limited.

The function of calculating the maintenance index value M of the present invention, which will be described in detail later, may be possessed by the control device 29 of the injection molding machine 11 or possessed by the central control device 14, and the functions are shared by both. You may. Generally, when the calculation of the maintenance index value M is limited to a light calculation process, it is possible on the control device 29 side of the injection molding machine 11, but when performing advanced calculation processing, the calculation is performed on the central control device 14 side. It is preferable that the treatment is performed. These are also closely related to the system construction status of the company that owns and operates the injection molding machine 11.

The central control device 14 in the company in which the injection molding machine 11 is operating and the control device 16 of the injection molding machine manufacturer 15 outside the company are connected by a line 32 such as the Internet. The default gateway 16b of the personal computer 16a of the control device 16 outside the company is connected via the default gateway 14b of the personal computer 14a which is the central control device 14 for transmitting data in the company where the injection molding machine 11 is arranged. Invasion of virus software from the outside is prevented from each.

In the present embodiment, the control device 16 outside the company refers to the control device 16 of the injection molding machine manufacturer 15, but may be a control device of a company that specializes in maintenance. Further, the place where the control device 16 on the injection molding machine manufacturer 15 side is placed may be a base such as a head office having a function of controlling the entire service operation, but each service base in the area of the company that owns the injection molding machine 11. It may be. The control device 16 can also be interlocked with the mobile phone of each service person. Furthermore, the communication between the central control device 14 inside the company where the injection molding machine 11 is located and the control device 16 outside the company is not limited to the Internet, but is limited to telephone lines other than the Internet (including facsimiles) and between two companies. The communication method may be not limited.

Next, a method of notifying the state of the injection molding machine 11 using the state notification system 12 of the injection molding machine will be described with reference to FIG. The first feature of the present invention is to combine the operating state of the injection molding machine 11 with both a non-stationary value V detected by a detection means such as a sensor and an integrated value N such as a molding time counted by a timer or the like. It is a point to judge. These determinations are made for each part or each part of the injection molding machine 11. More specifically, the detection and notification of the operating state of the injection molding machine 11 can be performed by moving various motors, power distribution boards such as motor control devices, speed reducers, ball screw mechanisms, mold clamping cylinders, hydraulic mechanisms, hydraulic pumps, movable boards 28, etc. The unit, the screw 22 of the injection device 17, the check valve 21, the heater, the load cell for injection and mold clamping, and the like are performed separately. Further, in the above, each part means that judgment and notification of two or more parts are collectively performed.

First, the detection and utilization of the non-stationary value V during operation of the injection molding machine 11 will be described. The type of sensor used to detect the unsteady value V of each part or each part is not limited as described above, and it is desirable that the sensor used for controlling the injection molding machine 11 is also used, but the unsteady value V It may be provided exclusively for the detection of. Further, the portion where the sensor 35 is provided is not limited.

Whether or not a non-steady value V is detected in the injection molding machine 11 in the operating state is determined by comparison with the steady value. A general method for setting a steady value indicates the state of a molding machine such as vibration, noise, molding time, and current value when the injection molding machine 11 is newly built or when the parts are replaced, or when the injection molding machine 11 is operated within a certain period of time from the new construction or replacement. The value is within the setting, and the average value of the values detected in the state where a good molded product is molded is stored in the storage unit or the like. The storage of the steady-state value is performed automatically or by the worker storing it in the storage unit. Further, the steady-state value may be set by using a calculated value or a value specified by the component manufacturer. Further, when the steady-state value is different depending on the molding, the steady-state value may be calculated by using the average value, the differential value, or the like of the measured values during the molding cycle for a certain period of stable molding. As an example, the temperature of the switchboard and motor measured by the temperature sensor, the resistance value of the heater measured by the current sensor, the vibration of moving parts and pumps measured by the vibration sensor, and the mold clamping cylinder measured by the oil pressure sensor. As the state of the seal member or the like, a fixed value set in advance may be used. In addition, moving parts such as a movable plate including a ball screw mechanism, a screw 22 including a check valve 21, a speed reducer, and the like that measure the current value (torque) of a motor vary depending on the molding material, mold weight, cycle time, and the like. Therefore, the steady value may be obtained by calculation from the average value or the like of the measured values of a plurality of times during the molding cycle.

Then, a threshold value (non-steady value determination value) having a certain width with respect to the steady value is set for determining the non-steady value V, and is stored in the storage unit together with the steady value. How much the value deviates from the steady value is set as the non-steady value judgment value differs depending on each part or part. In order to capture minor abnormalities of parts and parts and their precursors, it is necessary to capture an extremely small unsteady state, and the unsteady value V needs to be set to a value slightly deviating from the steady value. If the unsteady value V is set to a small value, it may exceed the unsteady value V due to disturbance factors even though the parts and parts of the injection molding machine 11 are operating normally, which is not originally desirable. However, in the present invention, in most cases, the maintenance state is not determined by exceeding the unsteady value V only once. Therefore, it is desirable to count the unsteady value V as having the possibility of minor abnormalities in parts or parts, regardless of the cause for which the unsteady value V is detected. The determination of the non-steady state using these non-steady values V is usually used by replacing the number of times the non-steady value V is detected with a converted value and cumulatively adding them. However, the value or amount of the non-stationary value V deviating from the steady value may be added to the calculation for the converted value, or a combination of both may be used.

In addition, it is often suspected that there is an abnormality in any of a plurality of parts by detecting one non-stationary value V. For example, if an unsteady value is detected in the current value of the die opening / closing servomotor that moves the movable platen 28, there is a problem with the mechanical parts such as the linear guide, tie bar bush, and ball screw mechanism (including loosening of the bolt of the mounting part). Is about to occur, or there may be a problem with the servomotor itself or its control system. In these cases, even if it is unknown which part has an abnormality, the display device 30 is first notified of the state to notify the operator of which part may have an abnormality. The operator sees the notification and decides whether to contact the injection molding machine manufacturer 15 or the like outside the company.

In addition, when it is suspected that there is an abnormality in any of the above-mentioned plurality of parts, it may be possible to estimate which part is likely to have a problem by combining with the values of other sensors. For example, in the case of the mold opening / closing movement of the movable board 28, whether a non-stationary value is generated in the entire mold opening / closing section or a non-stationary value is generated only in a specific section due to the combination with the position sensor and the timer. It may be possible to estimate which part is likely to have a problem by grasping. Further, the history of abnormality notification of the injection molding machine 11 is stored in the storage unit of the injection molding machine 11 or the storage unit of the central control device 14, and which of the data is referred to when the same abnormality occurred last time. It may be possible to predict if there is a high probability of a component malfunction.

Next, the detection and use of the integrated value N will be described. The integrated value N is a value that is gradually increased even if there is no abnormality during molding, and generally, the molding time is most often used. The integrated value N is counted by a timer which is a coefficient means of the calculation unit 29a. As the integrated value N, the operating time from the power-on of the entire device to the power-down is generally used. The counting of the timer may be started at any timing other than when the power is turned on, such as when the injection molding machine is started by any method, when the fully automatic operation is started, or when the operation of each part is started.

When the operating time is used for the integrated value N, 1 hour = 1 is usually counted as the conversion time. If the injection molding machine is used under special conditions such as overload due to high acceleration or the use of recycled materials, the load of each part will increase, so for example, multiply the molding time by a certain coefficient such as 1.5. The conversion time may be calculated. Further, the conversion time, which is the integrated value N, may be integrated based on the number of days of molding and the value added up to the unit of minutes or seconds less than the hour.

Further, the integrated value N may be the number of molding cycles or the like. When a molding cycle is used for the integrated value N, one molding cycle = 1 is usually counted as the number of conversions. However, the number of conversions at the time of molding is counted as 2 times for opening and closing the mold in one molding cycle for opening and closing movement of the mold, and the number of rotations such as the screw 22 and the servomotor 23 for weighing for the number of rotations such as the screw rotation speed. May be counted. Even when these conversion times are used for the integrated value N, a value obtained by multiplying by a certain coefficient or the like in consideration of the load according to the state at the time of use may be used as the conversion number. Further, as the integrated value N, both the conversion time and the number of conversions may be used.

The integrated value N such as the conversion time and the number of conversions is counted for each of a plurality of parts and stored in the storage unit. That is, even if the injection molding machine 11 is new, the integrated value of the conversion time is calculated for the part that calculates the conversion time with the molding time = 1 as described above and the part that calculates the conversion time by multiplying by a certain coefficient according to the load. N is different for each. Further, the integrated value N such as the conversion time and the number of conversions is reset to 0 when the parts are replaced. As a result, even if there are a plurality of parts to be counted by the integrated value N of molding time = 1 at the time of shipment of the injection molding machine 11, the integrated value N constituting the maintenance index value M becomes a different value by exchanging each part. Become. Various data such as the replacement date or time of the part, the numerical value of the sensor at the time of replacement, etc. are saved in the storage unit of the central control device 14 automatically or by the input of the operator, and the replacement history of the part can be seen at a glance by the display. It has become.

In FIG. 2, the accumulated value obtained by adding the conversion value V1 of the unsteady value V to the integrated value N gradually increasing to the right is the maintenance index value M which is a judgment value for notifying a message related to maintenance. It shows that it becomes. In FIG. 2, the non-stationary value V is detected four times, the conversion value V1 is added to the maintenance index value M based on the integrated value N each time, and finally the maintenance index is detected by the fifth detection of the non-stationary value V. An example is shown in which the converted value V1 is added to the value M, and the first message A is notified when the threshold value ma for notifying the first message A is exceeded.

Next, the relationship with the manufacturer's warranty period and legal inspections is also described. Generally, each part of the injection molding machine 11 has a warranty period set by the parts manufacturer. Each part also deteriorates due to cumulative molding time or number of moldings, or simply aging. However, even if the warranty period by the component manufacturer has expired, the actual situation is that each component can be used for a considerable period of time, although the probability that the deterioration gradually progresses and a failure occurs increases little by little. Therefore, the manufacturer's warranty period is an important factor in determining the maintenance status message notification based on the integrated value N, but is generally not used as a notification indicating the actual replacement of parts. However, if the manufacturer specifies the replacement deadline, the display device 30 is notified of the day before the replacement deadline and the replacement deadline date. Needless to say, those that use steam or compressors that require legal inspections and regular replacements are required to be maintained (inspection and parts replacement) in accordance with the laws and regulations, and they are also replaced. Notify the day before the specified number of days and the exchange deadline date.

The present invention can be realized by the injection molding machine 11 alone that notifies the maintenance status without being connected to a communication such as an in-house LAN or the Internet. That is, the maintenance information based on the maintenance index value M, which is a combination of the unsteady value V detected by the sensor and the integrated value N measured from at least one of the number of conversion hours or the number of conversions, is displayed on the screen of the injection molding machine or by voice. It may only be notified by. Upon receiving the notification, the operator can take necessary measures such as contacting the injection molding machine manufacturer 15 and securing spare parts.

Next, the state notification system of the injection molding machine 11 for notifying the maintenance state and the state notification method for the injection molding machine 11 for notifying the maintenance state will be described with reference to the flowchart of FIG. As described above, the maintenance state of the injection molding machine 11 is managed for each part or each part, but here, the detection of wear of the check valve 21 of the screw 22 will be described as an example.

First, when the power is turned on to the injection molding machine 11, the maintenance index value M accumulated up to the previous molding is read out for each part (here, the check valve 21) for which the abnormality sign notification is set in advance (s1). .. Further, when the power is turned on, the counting of the operating time (integrated value N) is started (s2). Then, the molding conditions are read out and the molding cycle starts (s3). As described above, the integration of the operating time (integrated value N) may be started from the start of the molding cycle or the like.

The weight of the continuously molded injection-molded product is detected by a load cell (sensor 35) for measuring the weight of the take-out machine 34, which is a peripheral device included in the injection-molding machine 11 in a broad sense. Then, the variation in the weight of the molded product was detected with respect to the weight of the molded product (steady value) determined in advance as a passing product, and whether the weight of the molded product exceeded the predetermined range (threshold value) and the non-stationary value V was detected. Judge (s4). When the non-stationary value V is detected, the control device 29 replaces and calculates the non-stationary value V with the converted value V1 (s5). Then, the conversion value V1 composed of the unsteady value V is further added to the maintenance index value M to obtain a new maintenance index value M (M + V1 = M) (s6). The magnitude of the converted value V1 is determined in relation to the converted value of the integrated value N. As an example, if the integrated value N has a molding time of 1 hour as 1, the converted value V1 when the unsteady value V is detected once is 100 times that value, and 100 is added. The amount of difference from the steady value at the time of measuring the weight of the molded product (value of the non-steady value judgment value) may be the same as the value judged to be defective, but the threshold value is further narrowed and the molded product is regarded as a acceptable product. It is also desirable to capture the numerical fluctuations within the range. Further, instead of counting the number of abnormalities as one time and always adding a fixed number, the conversion value may be determined according to the degree of deviation from the comparison value, and the conversion value consisting of variables may be added. Further, the above-mentioned calculation method may use a calculation method other than addition in part or in whole.

Next, it is determined whether the new maintenance index value M is a value for notifying an abnormality. Specifically, it is determined whether or not the new maintenance index value M is smaller than the threshold value ma for displaying the first message A (s7). Further, even when the non-stationary value V is not detected in the above (s4) (s4 = N), from ma, which is a threshold value for displaying the first message A by the maintenance index value M to which the converted value V1 is not added. Make a judgment as to whether it is small. This is because the threshold value ma may be reached only by accumulating the integrated values N during continuous molding.

Then, in the step (s7), when the maintenance index value M is smaller than ma (when s7 = Y), it is then determined whether the molding is completed (s8). Then, when the molding is not completed (s8 = N), the integrated value N is calculated next. As the calculation of the integrated value N, it is determined by the timer whether the molding time has been counted (s9). For example, when one hour has passed and the count is performed, 1 is added and N + 1 = N (s10). Then, the new integrated value N is also added to the maintenance index value M to obtain a new maintenance index value M (M ← M + N) (s11). Then, whether the timer counts (s9 = Y) or not (s9 = N), the process shifts to the next molding cycle, and whether the unsteady value V is detected again in the next molding cycle (s4). to decide.

Further, in the step (s7), when the maintenance index value M is equal to or greater than the threshold value ma (when s7 = N), then in the step (s12), the determination of ma ≦ M <mb is performed. In step (s12), mb is also a threshold value for determining the state of the injection molding machine 11. Then, in the case of (s12 = Y), the display device 30 of the injection molding machine 11 displays (notifies) the first message A and the maker contact button 33 (s13). The display of the first message A is displayed only when the range of ma ≦ M <mb is satisfied for the first time, and the display is continued until the operator deletes it.

The first message A notifies a sign of a slight abnormality, and as an example, the following notification is made.
"It is recommended to prepare spare parts for the check valve." Or "Inspection of the check valve is recommended."
In addition to the screen display, the notification may be a voice or a character output from a printer, or may be a combination of at least two of them. Further, the notification may be displayed not on the display device 30 on the side of the injection molding machine 11 but on the display screen of the personal computer 14a of the central control device 14 in the factory (or in the company) by communication.

It is suspected that the check valve is worn due to the weight variation of the molded product, but it is not without other causes. Although not explained in depth here for the sake of simplicity, deterioration of the screw drive mechanism, poor control of the screw drive mechanism, wear of the screw 22 other than the check valve 21, wear of the inner hole of the heating cylinder, and wear of the heating cylinder and the mold. There are improper temperature. For those defective or inappropriate states, some problems may occur in any part due to the combination with the detected values of other sensors and the passage of time (integrated value N) from the replacement of the check valve and other parts. In many cases, it is possible to estimate. If it is not possible to identify which of the plurality of parts has a sign of abnormality, the parts that may have a sign of abnormality are listed and the first message A is notified.

Further, on the display device 30 or the like of the injection molding machine 11 or the like, a manufacturer contact button 33 that is transmitted to the injection molding machine manufacturer 15 by pressing the button together with the first message A is displayed. Then, only when the operator presses the manufacturer contact button 33 of the display device 30 of the injection molding machine 11 and the ON signal is transmitted, the maintenance information of the check valve of the injection molding machine 11 is the personal computer 16a of the central control device 14. It is transferred to a personal computer 14a outside the company such as an injection molding machine manufacturer 15 via a line 32 such as the Internet via (default gateway 16b). The data sent in this embodiment includes the company name and factory name, contact information including the name of the person in charge, the model and serial number of the injection molding machine 11, the part number of the check valve, the replacement date and time, the molding time, and the weight of the molded product. Data on distribution (variation), molding history at each molding, etc.

At this time, the line 31 between the injection molding machine 11 and the central control device 14 may be connected by a cable such as a wired LAN, or may be connected by a radio such as a wireless LAN including WiFi. Further, the central control device 14 inside the company and the control device 16 outside the company may also be connected by a line means other than the Internet such as a dedicated line. In the personal computer 14a of the company in which the injection molding machine 11 is arranged, the history information can be stored in the server directly or via the personal computer 14a, and inventory can be secured including the ordering of spare parts. In addition, the injection molding machine manufacturer 15 can also receive information, manufacture spare parts, secure inventory, ship them, and arrange service personnel.

The present invention does not exclude those that automatically transmit the maintenance status from the injection molding machine 11 to the injection molding machine manufacturer 15, but in the present embodiment, the manufacturer contact button 33 is provided and displayed for the following reason. Only when the operator who sees the device 30 or the like permits the transmission of the maintenance status from the display device 30 or another device, the central control device 14, the injection molding machine manufacturer 15 is transmitted. That is, in many cases, a molding maker that operates the injection molding machine 11 to perform molding has a feeling of resistance to automatically sending all the data to the injection molding machine maker 15. Further, in a state where a sign of an initial minor abnormality is notified, it may not be necessary to contact the injection molding machine manufacturer 15 if there are spare parts. Furthermore, by limiting the number of communications, the possibility of virus infection or data leakage can be further reduced.

If the operator does not press the manufacturer contact button 33 for the first message A displayed on the display device 30 and the injection molding machine 11 does not transmit an ON signal (s14 = N), the injection molding machine No contact is made to the manufacturer 15. In this case, the data may be sent to the central control device 14 in the company, or the data may be accumulated as a history only in the injection molding machine 11. Then, it is determined whether or not the molding is completed (s8), and the process proceeds to the next molding cycle through the steps of calculating the integrated value N of (s9), (s10), and (s11) described above.

If the maintenance index value M is mb or more in step (s12) (s12 = N), then mb ≦ M <mc is determined in (s16). The transition to step (s16) is a case where the first message A has already been notified and the integrated value N is added to the maintenance index value M and a case where the unsteady value V1 is added to the maintenance index value M. As shown in FIG. 2, a metered value other than 1 is used for the non-stationary value V, and as a result of adding the maintenance index value M and the non-stationary value V2a, the calculated maintenance index value M suddenly becomes mb or more. This is the case. When the maintenance index value M is mb or more and smaller than mc (s16 = Y), the display device 30 of the injection molding machine 11 displays (notifies) the second message B (s17). The display of the second message B is displayed only when the range of mb ≦ M <mc is satisfied for the first time, and the display is continued until the operator deletes it.

The second message B informs the existence of a minor abnormality, and as an example, the following notification is made.
"It is recommended to replace the check valve.""The check valve needs to be inspected."
Further, the notification may be made by voice or characters may be output from the printer, or may be a combination of at least two of them. Further, the notification may be displayed not on the screen of the display device 30 on the side of the injection molding machine 11 but on the screen of the personal computer 14a of the central control device 14 in the factory 13 (or in the company) by communication.

Regarding the second message B, as in the case of the first message A, when the manufacturer contact button 33 is displayed on the display device 30, the manufacturer contact button is pressed by the operator's operation, and the ON signal is transmitted (s18). = Y), the maintenance information of the injection molding machine 11 is transferred to a personal computer outside the company such as the injection molding machine manufacturer 15 via a line 32 such as the Internet (s19). Further, if it is not transmitted and the operator does not stop the apparatus due to the completion of molding quantity molding or the like (s8 = N), molding is continued. That is, when the maintenance index value shows a value within the range of mb ≦ M <mc, it does not immediately lead to a complete failure of the injection molding machine 11, molding failure, danger to the operator, etc., so that it is automatic. The injection molding machine 11 may not be stopped, and molding may be continued for a preset number of production pieces.

If M is mc or more in step (s16) (s16 = N), then in (s20), a message C indicating that an abnormality has occurred in the display device 30 and a manufacturer contact button 33 are displayed (notified). .. The transition to step (s20) is a case where the second message B has already been notified and the unsteady value V1 is added to the maintenance index value M including the integrated value N, and as shown in FIG. This is a case where the calculated new maintenance index value M suddenly becomes mc or more as a result of adding the maintenance index value M and the conversion value V2b of the non-stationary value while using the metered value of the conversion value of the non-stationary value. When an abnormal value is detected, the injection molding machine 11 is immediately or until the molding cycle is completed, and then the injection molding machine 11 is stopped. When detecting an abnormality in the check valve, which is performed by detecting the weight of the molded product, the number of times the unsteady value V is detected may be added as a fixed conversion value, but the current value of the servomotor is detected. In the case of detecting an abnormality in the servomotor or the moving part, it is desirable that the converted value V of the unsteady value is a metered value, and when an abnormal value is detected, the injection molding machine 11 is stopped in an emergency.

Even when an abnormal stop is notified, the manufacturer contact button 33 is displayed on the display device 30 as in the case of the first message A and the second message B, and the manufacturer contact button is pressed by the operator's operation. When the ON signal is transmitted (s21 = Y), maintenance information including an abnormality of the injection molding machine 11 is transferred to a personal computer outside the company such as the injection molding machine manufacturer 15 via a line 32 such as the Internet (s). s22). Further, regardless of the presence or absence of the transfer, the process does not proceed to the step (s8) and the molding cycle ends as it is. In the flowchart of FIG. 3 of the present embodiment, the notification based on the maintenance index value M is a first message A recommending the preparation of parts, a second message B recommending replacement of parts, and an abnormality. There are three stages of message C to stop the device. However, the number of stages of the message for each part or each part may be different as long as different maintenance status notifications are made corresponding to the thresholds of a plurality of stages, even if the stages are different such as 2 to 4 stages. Good.

In the above, when the maintenance index value M reaches the predetermined thresholds ma, mb, bc (M = ma, M = mb, M = mc) or exceeds the threshold (M> ma, M> Whether to notify the first message A, the second message B, and the third message C to mb, M> mc) is a slight difference, and any method may be used.

In the present invention, both the converted value V1 obtained by converting the unsteady value V detected by various sensors as described above and the integrated value N such as the molding time (including the case of the converted molding time) and the number of moldings are cumulatively added or the like. When the maintenance index value M obtained by performing the above calculation reaches a predetermined threshold value (ma, mb, etc.) or exceeds the threshold value (ma, mb, etc.), the maintenance status of the injection molding machine 11 is notified. Therefore, the state of the injection molding machine 11 can be detected, determined, and notified in consideration of the secular change of the parts or parts constituting the injection molding machine 11 and the state change detected from the sensor.

Next, an example of multiplying the molding time or the number of molding cycles by a predetermined value according to various conditions and converting the integrated value is an example of the state notification system of the vertical rotary injection molding machine 41 of the second embodiment of FIG. explain. The vertical rotary injection molding machine 41 is a molding machine in which a rotary disk 43 to which a mold 42 is attached is rotatably provided by an electric motor such as a servomotor 44, as described in Japanese Patent No. 5518565. The vertical rotary injection molding machine 41 is composed of a mold clamping device 45, a first injection device 46 provided on both sides thereof, and a second injection device 47. In the mold clamping device 45, four tie bars 49 are fixed in an upright direction to a fixing plate 48 provided below, a movable plate 50 is inserted through the tie bar 49, and the movable plate 50 can move in the vertical direction. ing. A rotary table 43 (rotary table) is rotatably attached to the lower surface of the movable board 50. A fixed mold 42a is attached to the fixed plate 48, and a movable mold 42b is attached to the rotating plate 43.

The rotation of the turntable 43 is performed by the servomotor 44, and the timing belt 53 is hung over the toothed pulley 52 attached to the drive shaft 51 of the servomotor 44 and the toothed portion on the outer peripheral surface of the turntable 43. There is. A speed reducer 54 is attached to the servomotor 44. Further, the vertical rotary injection molding machine 41 includes a control device 56. The control device 56 controls the drive of the servomotor 44 and the like, and is connected to each sensor including the encoder 44a of the servomotor 44 and the current sensor for measuring the current value transmitted to the servomotor 44. Further, the control device 56 is connected to a display device 57 that displays maintenance information and the like. Further, the control device 56 is also connected to a control device outside the company (not shown) via a central control device 58 inside the factory.

The weight of the mold 42 attached to the rotary disk 43 of the vertical rotary injection molding machine 41 may differ depending on the molded product. Further, the rotation speed of the turntable 43 is controlled so that the turntable 43 is reversed or rotated at almost the fastest speed within the capacity of the servomotor 44 so that the molding time is not extended more than necessary. At this time, the speed of reversal of the turntable 43 is set so that the acceleration during acceleration and deceleration is within the allowable range of the servomotor 44 and the reduction gear 54, and the load on the servomotor 44 and the reduction gear 54 is reduced. ing. However, even so, the load on the servomotor 44 and the speed reducer 54 differs depending on the molding conditions, such as when the heaviest mold 42 is used, when the lightest mold 42 is used, or when the rotation speed (acceleration) is different. To do.

Therefore, in the second embodiment of FIG. 4, the peak torque is detected from the current value sent to the servomotor 44, and the peak torque is converted into a coefficient value. That is, the coefficient value a is increased as the peak torque increases. Then, the coefficient value a is multiplied by the molding time N to obtain the conversion time aN used for the integrated value N. Alternatively, the coefficient value a is multiplied by the number of molding cycles n to obtain the integrated value an of the number of converted moldings, which is the number of conversions. For this reason, when the load of the servomotor 44 or the speed reducer 54 is large, the integrated value N is set to be closer to the cumulative load of the actual load than the simple molding time N or the number of molding cycles n used as the integrated value N as it is. Can be done.

In the second embodiment of FIG. 4, what is used for the coefficient value is a part or all of the rotating disk 43 during rotation, in addition to the peak torque, if the numerical value is changed according to the magnitude of the load. It may be the total of the current values of the above, the weight of the mold, the temperature of the servomotor or the speed reducer, and the like. Also in the second embodiment of FIG. 4, the maintenance index value M is calculated by adding the integrated value N such as the conversion time aN calculated above and the unsteady value V detected by the sensor to calculate the state of the apparatus. Used for notification. For the unsteady value V, the peak torque of the servomotor 44, the deviation of the entire current value, the deviation of the time until the rotation is completed, etc. are measured by sensors, respectively, and when the servomotor 44 and the speed reducer 54 are new or close to each other. Compare with the detected value (steady value).

Further, regarding the speed reducer 54, from the normal value of the detection value of the encoder 44a of the servomotor 44 when the rotary disk 43 rotates and comes into contact with a stopper (not shown) or when a cam or the like is detected by a proximity switch (not shown). Detects the occurrence of divergence. Alternatively, when the stopper 55 that fixes the rotary disk 43 is advanced at the stop position and inserted into the positioning hole 43a of the rotary disk 43, the tapered stopper tip side hits the side surface of the positioning hole 43a and the rotary disk 43 rotates. It is detected by the encoder 44a of the servomotor 44. As a result, it is detected that the backlash is increasing due to wear of the gears in the speed reducer 54 and the like. As for the calculation method of the non-steady value when these non-steady value V is detected, it is desirable to use the metered value according to the deviation from the steady value as described above.

The drive systems such as the servomotor 44 for rotating the rotary disk, the speed reducer 54, and the timing belt 53 of the vertical rotary injection molding machine 41 of the second embodiment of FIG. 4 are also detected by the sensor as unsteady values. However, it may not be possible to judge that it is a sign of abnormality of one specific part. In that case, the display may be performed in the order of parts having a high possibility of occurrence of a sign of abnormality, taking into consideration the integrated time from the replacement of each part, the record when the previous abnormality occurred, and the like. The notification of the abnormality in FIG. 4 is basically the same as the flowchart in FIG. 3, and the notification with a stage in the maintenance state is performed.

Next, the control device of the injection molding machine of the third embodiment shown in FIGS. 5 and 6 and the state notification system of the injection molding machine will be described. The mechanism such as the injection device and the mold clamping device of the injection molding machine of the third embodiment may be the injection molding machine of the first embodiment or the injection molding machine of the second embodiment, and may be injected. The mechanism of the molding machine is not limited. Therefore, in the following description, the same elements or parts having the same function will be referred to with the same reference numerals as those in FIGS. 1 to 3, and duplicate description will be omitted. In the third embodiment, the technical idea of determining and notifying the maintenance status is the same, but it is characterized in that the maintenance status is determined and notified using AI (Artificial Intelligence) technology.

The block diagram shown in FIG. 5 conceptually shows an example in which the machine learning device 61 is mounted on the arithmetic unit 29a of the control device 29 of the injection molding machine 11. The control device 29 is also connected to a display device 30 having a setting / input function and each sensor of the injection molding machine 11. The control device 29 is provided with an input unit 62 for inputting signals from the display device 30 and the sensor. Further, the input unit 62 is connected to the machine learning device 61 of the arithmetic unit 29a.

The machine learning device 61 includes a data input processing unit 63, a learning unit 64, a learning result output unit 65, a storage unit 66 including a weighted storage unit 66a, and the like. Here, the storage unit 66 also serves as a storage unit for the entire control device 29. The storage unit 66 stores data on the replacement time of parts and the injection molding machine at the time of molding. The integrated value and the cumulative value of the non-stationary value for each part that notifies the maintenance information are also stored. Further, the arithmetic unit 29a of the control device 29 includes a portion for determining and notifying the maintenance state of the normal injection molding machine 11. Specifically, the arithmetic unit 29a includes a timer 67, and the timer 67 is connected to the integrated value arithmetic processing unit 68. Further, the arithmetic unit 29a includes a non-stationary value arithmetic processing unit 69 connected to the input unit 62. The integrated value calculation processing unit 68 and the non-stationary value calculation processing unit 69 are connected to the weighting correction unit 70, respectively.

Further, the weighting correction unit 70 is connected to the weighting storage unit 66a of the storage unit 66 of the machine learning device 61. Further, the weighting correction unit 70 is connected to the maintenance index value calculation unit 71, and the maintenance index value calculation unit 71 is connected to the maintenance information notification determination unit 72. The maintenance information notification determination unit 72 is connected to the data input processing unit 63 and the storage unit 66 of the machine learning device 61, and further to the output unit 73 of the control device 29. The output unit 73 of the control device 29 is connected to the display device 30 of the injection molding machine 11 and other servo amplifiers and solenoids of the drive system. Further, in some cases, the output unit 73 is connected to a central control device 14 in the factory 13 or an external control device 16 such as an injection molding machine manufacturer 15 outside the factory.

Next, the functions of the calculation unit 29a of the control device 28 and the machine learning device 61 for notifying the maintenance status will be described. The integrated value calculation processing unit 68 generates an integrated value N for maintenance state calculation from the time measured by the timer 67 and the like. The integrated value N may be multiplied by a certain coefficient in consideration of the operating state of the injection molding machine 11 and when the injection molding machine 11 is used in a high load state or in a bad environment. Further, the non-stationary value calculation processing unit 69 generates a non-stationary value V for maintenance state calculation from a data signal input from an external sensor or the like via the input unit 62.

In the weighting correction unit 70, the integrated value N and the non-stationary value V are multiplied by a coefficient value and corrected to the weighted integrated value Na and the non-stationary value Va. The weighting correction method is not limited to multiplication, and may be another calculation method. The calculation and correction of the coefficient value when weighting the integrated value N and the unsteady value V will be described in the description of the machine learning device 61 described later. Then, the weighted integrated value Na and the non-stationary value Va are sent to the next maintenance index value calculation unit 71 and added, and the maintenance index value M is generated. Then, in the next maintenance status notification determination unit 72, the first message A, which is compared with the threshold values ma, mb, mc stored in the storage unit 66, notifies a sign of a minor abnormality, and recommends inspection, is a minor abnormality. Either the second message B that notifies the existence of the message and recommends the replacement of parts, or the third message C that notifies the abnormality is output, or no message is given because it is not yet in the stage of notifying the maintenance status. Is not notified.

When any of the first message A, the second message B, and the third message C is output by the maintenance status notification determination unit 72, maintenance is performed from the maintenance status notification determination unit 72 at the same time or before or after. Data including the index value M and its calculation process is sent to the data input processing unit 63 of the machine learning device 61. It is also sent to the storage unit 66 and stored.

When any of the first message A, the second message B, and the third message C is output, the operator checks the degree of deterioration such as wear of the parts. Then, when the first message A, the second message B, and the third message C are output at the optimum time, the operator inputs the information that the output of the message was optimal from the display device 30. To do. The input information is sent to the data input processing unit 63 of the machine learning device 61 via the input unit 62. Then, the information is associated with the data sent from the maintenance status notification determination unit 72, and the maintenance index value for issuing any one of the first message A, the second message B, and the third message C ( (Including weighting of integrated value and non-stationary value) is considered to be appropriate teacher data.

Also, if the degree of deterioration of the parts is checked and one of the first message A, the second message B, and the third message C is issued too early or too late, the operator also performs the same. Information that the timing of issuing message A or message B from the display device 30 was not optimal is input. Then, the input information is sent to the data input processing unit 63 of the machine learning device 61. Then, the information is associated with the data sent from the maintenance status notification determination unit 72, and the maintenance index value (integration) for issuing any one of the first message A, the second message B, and the third message C is linked. (Including weighting of values and non-stationary values) is considered to be inappropriate teacher data.

When visually determining the degree of deterioration of a part, it is advantageous to input information using a push button or the like that advances to the next stage, which saves the operator time and effort. Specifically, in the case of the first message A, buttons such as "no problem at all", "parts are slightly deteriorated but molding can be continued", and "parts need to be replaced immediately" are additionally provided. .. And when the operator presses the "No problem with parts" button, the message is displayed too quickly, and when the operator presses the "Parts are slightly deteriorated but molding can be continued" button, the message is displayed appropriately. Yes, if you press the "Need to replace parts immediately" button, the message may be displayed too late. Information on the degree of deterioration of parts may be obtained from the evaluation of a plurality of items, or may be obtained by using label data obtained by processing the data by the operator. Further, the information on the degree of deterioration of the parts may be quantified by mechanically determining the degree of deterioration of the parts by using a camera or a sensor so that the operator does not judge the degree of wear or the like.

It should be noted that the information when the message B recommending replacement is displayed before the first message A recommending inspection is displayed, and before the first message A and the second message B are issued. The information when the third message C indicating an abnormality is automatically set to the maintenance index value M including the weighted integrated value N and the non-stationary value V without the judgment of the operator. Appropriate teacher data.

Then, the external information processed by the data input processing unit 63 of the machine learning device 61 is sent to the learning unit 64, and as shown in FIG. 6, the learning unit 64 uses a neural network that imitates the mechanism of the neural circuit of the brain. Mainly supervised learning is conducted. Specifically, the teacher data in which the maintenance index value M including the weighted integrated value N and the information of the non-stationary value V is appropriate and the teacher data in which the maintenance index value M is inappropriate are each neural network. It is input from the input layer of.

Then, in the neural network, regression analysis is performed using each of the teacher data (what kind of integrated value N and non-stationary value V were weighted when the optimum message was delivered), and a functional expression (generally a plurality) is performed. (Functional expression of) is derived. The method of supervised learning may be a method using a decision tree in addition to regression analysis. The function calculation formula may be used as it is or as an approximate expression. Note that FIG. 6 shows a neural network, in which only one intermediate layer 76 (hidden layer) is provided between the input layer 74 and the output layer 75, but between the input layer and the output layer. It is not excluded from those that have multiple intermediate layers (hidden layers) and perform deep learning. In particular, when the amount of data used for learning in abnormality detection or failure prediction is small, it is a desirable method to perform deep learning including inference performed by the machine learning device 61.

Then, in the learning unit 64, the output layer 75 is weighted with the integrated value N such as the time which is the basis of the maintenance index value and the non-stationary value N other than the normal time of each sensor or the like by using the function formula of the neural network. The numerical value is output. That is, in the present invention, the integrated value N and the unsteady value V are weighted by the machine learning device 61 using the neural network. To give a simpler example of this point, supervised learning from many learning opportunities is that the time factor (integrated value N) is deeply involved as a factor for issuing the second message B recommending the replacement of a certain part. If so, the weighting of the integrated value N is increased, and the weighting of the non-stationary value V detected from the sensor or the like is decreased. Or conversely, when supervised learning is learned that the relationship between the integrated value N such as time is small and the relationship with the detection value (nonsteady value V) of the sensor etc. is large, the weighting of the nonsteady value V such as the sensor is weighted. To increase. The weighting adjustment is performed not only in the relationship between the plurality of sensors but also in the relationship between the number of detections of the non-stationary value V and the magnitude (frequency) of the non-stationary value V. Further, the values of the threshold values ma, mb, and mc for notifying the first message A and the second message B are often changed according to the adjustment of the weighting.

Then, the learning result (weighting value of the integrated value N and the non-stationary value V) output to the output layer 75 using the neural network of the learning unit 64 is weighted in the storage unit 66 via the learning result output unit 65. It is temporarily stored in the storage unit 66a. The block diagram of FIG. 5 conceptually shows the functions of the control device 29 and the machine learning device 61, and various methods are assumed for actual control.

Next, a method of notifying the state of the injection molding machine using the machine learning device 61 that performs supervised learning by AI will be further described. The method of FIG. 2 is also used for the calculation method using the machine learning device 61, and the result of machine learning is used for weighting the integrated value N and the non-stationary value V. Further, the flowchart of FIG. 3 is also used for the flowchart of the state notification method of the injection molding machine 11. However, if the predictive ability of the AI is improved, the message may be in two stages, a second message B recommending replacement of parts and a third message C indicating an abnormality.

The integrated value N detected by the timer 67 or the like and numerically processed by the integrated value calculation processing unit 68 is based on the data machine-learned by the learning unit 64 of the machine learning device 61 and stored in the weighted storage unit 66a of the storage unit 66. Further, the weighting correction unit 70 weights and corrects the weight. At the first stage, the weighting of the integrated value is preferably 50% or more. The non-stationary value V numerically processed by the non-stationary value calculation processing unit 69 detected by the sensor of the injection molding machine 11 is further weighted and corrected by the weighting correction unit 70 based on the data stored in the weighting storage unit 66a. .. Then, the integrated value Na and the unsteady value Va after the correction process are added by the maintenance index value calculation unit 71. Then, the maintenance information notification determination unit 72 is compared with a predetermined threshold value stored in the storage unit 66, and when the threshold value is reached or the threshold values ma, mb, mc are exceeded, the maintenance status of the injection molding machine 11 is notified. As described above, the threshold values ma, mb, and mc are often changed as a result of machine learning.

It should be noted that the weighting of the integrated value N and the unsteady value V is changed, and the threshold values ma, mb, and mc are changed accordingly for each machine learning corresponding to each message display. However, the weighting and the threshold value may be changed by performing machine learning after accumulating a certain amount of data. Further, when the number of data is small, the AI may change the weighting of the integrated value N and the non-stationary value V and change the threshold value accordingly by adding inference by deep learning or the like.

Further, in the above description, the machine learning device 61 is mainly described for learning with supervised learning using a neural network, but does not exclude those for learning without supervised learning such as the k-means method. Unsupervised learning is also possible if the state of parts for which replacement is recommended can be objectively grasped by sensors or the like. That is, from the values of the integrated value N and the unsteady value V, what kind of combination causes a problem with the part and should be recommended for replacement, or what kind of combination causes a problem with the part. Create a classification that does not require replacement. Then, the accuracy of machine learning can be improved by further verifying whether the classification is correct by using the machine learning device 61. Furthermore, reinforcement learning is performed by giving a negative reward to the data when the third message C indicating an abnormality is issued from the injection molding machine 11, and the accuracy of failure prediction is achieved by accumulating the data by reinforcement learning. You may try to improve.

Further, in the above description, an example in which the machine learning device 61 is provided in the injection molding machine 11 is described. However, with the injection molding machine 11 alone, the frequency with which failure prediction of parts is required is not so high. Therefore machine learning unit 61, or provided within the corporate external control device inside, or disposed of an injection molding machine of the central control device in the company, the arrangement of direct connection or an injection molding machine to the central control unit of an internal corporate It is also preferable to directly connect to a control device outside the company. When the machine learning device 61 is provided in the central control device 14 or the external control device 16 in this way, the learning opportunities for data other than the steady state of each injection molding machine 11 increase, and the opportunities for supervised learning increase and the accuracy becomes higher. It can be improved. Further, even when the machine learning device 61 is provided in the control device 29 of the injection molding machine 11, the injection molding machine 11 having the same model or a mechanism similar to the same model and having a common degree of deterioration of parts. It is also possible to input the data into another injection molding machine 11 and use it.

And especially in the current injection molding machine, the number of occurrences of the problem that the device (parts) actually occurs and the device stops is small, so even if AI is used, there are few opportunities for machine learning at the time of abnormality and failure prediction. It is said that it is difficult to improve the accuracy of. However, in the present invention, not only the occurrence of an abnormality in the device is detected, but the information in the first message A for notifying the sign of a minor abnormality and the information in the second message B for recommending the replacement of parts are used, so that the amount of data is used. There are many opportunities for machine learning. Furthermore, as described above, since the central control device 14 and the external control device 16 can collect data of a large number of injection molding machines 11, there are more opportunities for machine learning, and the accuracy of notification of the maintenance status is improved. To do.

In the failure prediction of a part of an injection molding machine, there is a case where an abnormality (including the necessity of inspection or replacement) of a plurality of parts is suspected from one abnormal value. However, in the third embodiment using AI, it is recommended to replace or inspect any one of a plurality of parts or parts from a single or a plurality of command values and a value detected by the single or a plurality of sensors (unsteady value V). In this case as well, learn the combination of the command value and the sensor value, or which of the values between the sensors, when the non-stationary value V occurs, which part often has a problem. It is possible to identify. Alternatively, in identifying the component, each integrated value N from the replacement time of each component is also taken into consideration. When it is determined that a plurality of parts among some parts are suspected to be abnormal, the list may be displayed in descending order of the possibility of the component abnormality. Then, as a result of the inspection, when a actually problematic part is found, the accuracy of the list in the order of high possibility of part abnormality can be improved by further machine learning (supervised learning).

In addition, the recommendation of parts replacement not only catches and notifies only the optimum recommended timing for each part, but also notifies the inspection recommendation and replacement recommendation for each part or multiple parts in relation to other elements. You may do so. Specifically, when it is determined that replacement of part A should be recommended and notification is given, parts B and C have no non-stationary value V or a small amount of non-stationary value V, and are slightly before the time when replacement is recommended. Even if it is, replacement is recommended at the same time. In this case, the following points are taken into consideration. Cost reduction by reducing costs such as the number of parts replacement work and time (may include travel expenses of workers), as opposed to cost increase by replacing parts before the recommended replacement time If it is larger, it makes sense to replace multiple parts at the same time. Alternatively, if it takes time to obtain replacement parts, take into consideration the number of parts in stock and the number of days required to procure parts at the injection molding machine manufacturer or the factory that owns the injection molding machine. It can be said that the one that performs the above is also preferable. Furthermore, even if it is known that the operation of the injection molding machine cannot be stopped at all, it is possible to take measures such as accelerating the timing of recommending parts replacement.

When AI is used in these cases, it is desirable to optimize it by using the mathematical programming method in machine learning. More specifically, we will create a mathematical model such as an objective function and optimize under what conditions the cost related to parts replacement will be minimized. The algorithm for optimization is not limited to a specific algorithm, and a linear programming method such as a branch-and-bound method, a trust region method, or the like may be used.

Although the present invention is not listed one by one, it is not limited to the above-described embodiment of the present invention, and those skilled in the art have been modified based on the gist of the present invention or the description of the present embodiment is multiplied. Needless to say, it also applies to.

Further, although the injection molding machine has been described in the present invention, the maintenance status of a press device, a vacuum laminating device using a diaphragm, and the like can also be applied to notification.

11. Injection molding machine 12 Injection molding machine status notification system 13 Factory (company where injection molding machine is installed)
14 Central control device 15 Injection molding machine manufacturer (outside the company where the injection molding machine is located)
16, 29 Control device 29a Calculation unit (timekeeping means)
30 Display device 35 Sensor (detection means)
N Integrated value V Unsteady value M Maintenance index value ma, mb, mc Threshold

Claims (9)

In an injection molding machine that notifies the maintenance status
A detection means for detecting that the operating state of the injection molding machine is a non-steady value deviating from the steady value as a value including a metered value, and
A counting means that counts an integrated value consisting of at least one of the number of conversion hours or the number of conversions ,
Notification means for notifying the maintenance status of the injection molding machine when the value calculated from both the non-stationary value in which the non-stationary value including the metered value is accumulated and the integrated value reaches a predetermined threshold value or exceeds the threshold value. An injection molding machine characterized by being equipped with. When exceeding the accumulated unsteady value as the value calculated from both of the integrated value of 3 steps to set in four stages threshold or threshold value, an injection molding machine corresponding to each of the threshold The injection molding machine according to claim 1, further comprising a notification means for notifying different maintenance states. The value calculated from both of the accumulated non-stationary value and the integrated value, according to claim 1 or claim 2, characterized in that weighted by machine learning system using a neural network Injection molding machine. In the injection molding machine status notification system that notifies the maintenance status,
The injection molding machine according to claim 1 is connected to a central control device inside the company where the injection molding machine is arranged or a control device outside the company where the injection molding machine is arranged, and is connected to the control device outside the company. An injection molding machine status notification system characterized in that the maintenance status of the injection molding machine can be transmitted. The maintenance status is notified at least on the screen of the injection molding machine.
The state notification of the injection molding machine according to claim 4, wherein the maintenance state of the injection molding machine is transmitted to the control device outside the company when the operator permits the transmission from the screen or another device. system. A machine learning device is provided inside the central control device inside the company or inside the control device outside the company where the injection molding machine is arranged, or is directly connected to the central control device inside the company or the injection molding machine. The state notification system for an injection molding machine according to claim 4 or 5, wherein the machine learning device is provided by directly connecting to a control device outside the company. In the state notification method of the injection molding machine that notifies the maintenance status,
The detection means detects that the operating state of the injection molding machine is a non-steady value deviating from the steady value as a value including a metered value.
The integrated value measured from at least one of the number of conversion hours or the number of conversions is counted by the counting means, and
The feature is that the maintenance status is notified by the notification means when the value calculated from both the non-stationary value in which the non-stationary value including the metered value is accumulated and the integrated value reaches a predetermined threshold value or exceeds the threshold value. The method of notifying the state of the injection molding machine. The state notification method for an injection molding machine according to claim 7, wherein different maintenance states are notified corresponding to a threshold value of 3 to 4 stages. The state notification method for an injection molding machine according to claim 8 , wherein the notification of different maintenance states uses a machine learning device that performs supervised learning.

Images