CN114527670B - Automatic control method for multiple devices matched with keyboard - Google Patents
Automatic control method for multiple devices matched with keyboard Download PDFInfo
- Publication number
- CN114527670B CN114527670B CN202210066050.4A CN202210066050A CN114527670B CN 114527670 B CN114527670 B CN 114527670B CN 202210066050 A CN202210066050 A CN 202210066050A CN 114527670 B CN114527670 B CN 114527670B
- Authority
- CN
- China
- Prior art keywords
- mode
- value
- keyboard
- input information
- reinforcement learning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B15/00—Systems controlled by a computer
- G05B15/02—Systems controlled by a computer electric
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/26—Pc applications
- G05B2219/2642—Domotique, domestic, home control, automation, smart house
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Automation & Control Theory (AREA)
- Quality & Reliability (AREA)
- Manufacturing & Machinery (AREA)
- User Interface Of Digital Computer (AREA)
- Feedback Control In General (AREA)
Abstract
The invention relates to the technical field of computers, in particular to an automatic control method for multiple devices matched with a keyboard, which comprises the following steps of receiving identification numbers of multiple devices, device data information, sensor data and modes selected by a user by the keyboard to form input information, defining corresponding reward functions by the keyboard according to the received input information and the modes selected by the user, training a reinforcement learning algorithm to obtain weight parameters trained by the corresponding modes, storing the weight parameters, calling the trained models of the corresponding modes by the keyboard according to the received input information and inputting the input information into the reinforcement learning algorithm, and outputting multiple control instruction information of the corresponding modes by the reinforcement learning algorithm according to the selected modes of the user, the corresponding sensor data, the devices and the like. The invention can automatically control networking equipment, save manpower and material resources and improve the working efficiency.
Description
Technical Field
The invention relates to the technical field of computers, in particular to an automatic control method for multiple devices matched with a keyboard.
Background
With the development of technology, the number of networked devices is increasing, and further, management and control becomes more complex and variable. Because of limited effort, a set of automated and intelligent control methods is needed for so many networking devices, but the control methods used more recently are more traditional, only the adjustment of some thresholds, and no artificial intelligence related methods are used for adjustment and control, and the artificial intelligence methods can obtain a control model of a corresponding mode through training. In view of the foregoing, it is necessary to provide an automatic control method for multiple devices matched with a keyboard, so as to solve the above-mentioned problems, thereby saving labor cost and time cost for users and improving working efficiency.
Disclosure of Invention
The invention provides an automatic control method for multiple devices matched with a keyboard aiming at the problems in the prior art, which has ingenious design, and a user can switch different modes according to the needs.
In order to solve the technical problems, the invention adopts the following technical scheme:
the invention provides an automatic control method for multiple devices matched with a keyboard, which comprises the following steps:
S1, a keyboard receives identification numbers of a plurality of devices, device data information, sensor data and a mode selected by a user to form input information;
S2, defining a corresponding reward function by the keyboard according to the received input information and a mode selected by a user, training a reinforcement learning algorithm, obtaining weight parameters trained by the corresponding mode, and storing the model;
S3, the keyboard calls a trained model of a corresponding mode according to the received input information and the selected mode of the user, and inputs the input information into a reinforcement learning algorithm;
S4, the reinforcement learning algorithm outputs multi-control instruction information of corresponding modes according to the selection modes of the user and the information of corresponding sensor data, equipment and the like.
Wherein the user-selected modes include a safe mode, an energy-saving mode, a silent mode, an entertainment mode, and a purified air mode.
The keyboard is provided with a mode switching knob, and a user can switch different modes through the mode switching knob.
The reinforcement learning algorithm defines a reward function of a corresponding mode according to the received input information, namely a model of a required mode can be trained, and in deep reinforcement learning, the reinforcement learning consists of a deep neural network and maps a plurality of inputs to a plurality of outputs.
Wherein the sensor data includes a temperature value, a humidity value, a PM2.5 value, an illumination value, and an acoustic volume value.
The device data information comprises current time and current opened device quantity information.
Wherein the multi-control instruction information comprises a switch instruction O K1 and a temperature regulation instruction of the air conditionerCurtain motor rotation command O R, sound volume adjustment command O Y, air cleaner switch command O K2, and air cleaner adjustment command
Wherein the reinforcement learning algorithm adopts a DQN algorithm, and is characterized in that the reinforcement learning algorithm adopts a switch I K1 of an air conditioner, an air conditioner temperature adjustment I T, a temperature sensor value I v1, an air conditioner electric quantity I q1 and an acoustic switchVolume I Y, sound sensor value I v2, acoustic powerAir purifier switch I K3, air purifier purifying intensity I A, PM2.5 gas detection sensor value I v3, air purifier electric quantityRGB lamp light adjustment I rgb, RGB lamp electric quantityThe input information of the smoke sensor I smoke and the algorithm model is as follows:
And through the switch O K1 of the air conditioner, the temperature of the air conditioner is regulated to O T, and the sound switch Volume O Y, air purifier switch O K3, air purifier purifying intensity O A, RGB lamp value O rgb, fire extinguishing gas and dry powder output value O powder, exhaust fan wind speed regulation O fan, and algorithm model output information ofThe neural network parameter is updated to be p=p+a (O-O y), wherein O y is an actual output value of the corresponding O medium device, and α is a learning rate, which is set to 0.1.
The invention has the beneficial effects that:
The invention has ingenious design, the user can switch different modes according to the requirement, and the invention defines the rewarding function of the corresponding mode according to the received input information, thus the model of the required mode can be trained, thereby automatically controlling the networking equipment, saving manpower and material resources and improving the working efficiency.
Drawings
FIG. 1 is a flow chart of an automatic control method of a keyboard matching multi-device according to the present invention.
Detailed Description
The invention will be further described with reference to examples and drawings, to which reference is made, but which are not intended to limit the scope of the invention. The present invention will be described in detail below with reference to the accompanying drawings.
An automatic control method for a plurality of devices matched with a keyboard comprises the following steps:
S1, a keyboard receives identification numbers of a plurality of devices, device data information, sensor data and a mode selected by a user to form input information;
S2, defining a corresponding reward function by the keyboard according to the received input information and a mode selected by a user, training a reinforcement learning algorithm, obtaining weight parameters trained by the corresponding mode, and storing the model;
S3, the keyboard calls a trained model of a corresponding mode according to the received input information and the selected mode of the user, and inputs the input information into a reinforcement learning algorithm;
S4, the reinforcement learning algorithm outputs multi-control instruction information of corresponding modes according to the selection modes of the user and the information of corresponding sensor data, equipment and the like.
Specifically, the invention has ingenious design, the user can switch different modes according to the requirement, and the invention defines the rewarding function of the corresponding mode according to the received input information, so that the model of the required mode can be trained, thereby automatically controlling the networking equipment, saving manpower and material resources and improving the working efficiency.
Wherein the user-selected modes include a safe mode, an energy-saving mode, a silent mode, an entertainment mode, and a purified air mode.
The keyboard is provided with a mode switching knob, and a user can switch different modes through the mode switching knob.
The reinforcement learning algorithm defines a reward function of a corresponding mode according to the received input information, namely a model of a required mode can be trained, and in deep reinforcement learning, the reinforcement learning consists of a deep neural network and maps a plurality of inputs to a plurality of outputs.
Wherein the sensor data includes a temperature value, a humidity value, a PM2.5 value, an illumination value, and an acoustic volume value.
The device data information comprises current time and current opened device quantity information.
Wherein the multi-control instruction information comprises a switch instruction O K1 and a temperature regulation instruction of the air conditionerCurtain motor rotation command O R, sound volume adjustment command O Y, air cleaner switch command O K2, and air cleaner adjustment command
Wherein the reinforcement learning algorithm adopts a DQN algorithm, and is characterized in that the reinforcement learning algorithm adopts a switch I K1 of an air conditioner, an air conditioner temperature adjustment I T, a temperature sensor value I v1, an air conditioner electric quantity I q1 and an acoustic switchVolume I Y, sound sensor value I v2, acoustic powerAir purifier switch I K3, air purifier purifying intensity I A, PM2.5 gas detection sensor value I v3, air purifier electric quantityRGB lamp light adjustment I rgb, RGB lamp electric quantityThe input information of the smoke sensor I smoke and the algorithm model is as follows:
And through the switch O K1 of the air conditioner, the temperature of the air conditioner is regulated to O T, and the sound switch Volume O Y, air purifier switch O K3, air purifier purifying intensity O A, RGB lamp value O rgb, fire extinguishing gas and dry powder output value O powder, exhaust fan wind speed regulation O fan, and algorithm model output information ofThe neural network parameter is updated to be p=p+a (O-O y), wherein O y is an actual output value of the corresponding O medium device, and α is a learning rate, which is set to 0.1.
In the safe mode combined with the energy-saving mode, the input information through the algorithm model isDefining a reward function with as small an amount of electricity as possible:
Wherein W smoke is set to 10, because the safety problem is considered and the smoke gas value is more sensitive, the aim is to make the prize value r bigger and better, when the prize value r is stable, the model parameters are converged, and corresponding instructions are output The unnecessary equipment is closed as much as possible, the power consumption of the corresponding equipment is reduced, the corresponding equipment enters an energy-saving mode, and when the smoke value reaches the concentration measured by the model, a fan is started to send dry powder to a target area;
In the clean air mode in combination with the safe mode in combination with the energy saving mode, a bonus function is defined in which the amount of electricity is as small as possible and the PM2.5 value is as small as possible:
Wherein W smoke is set to 10 and W v3 is set to 5, because in this mode the value of PM2.5 gas is more sensitive;
In silent mode in combination with safe mode in combination with energy saving mode, a bonus function is defined that has as little power as possible and as little sound value as possible:
Wherein W smoke is set to 10 and W v2 is set to 5, because the value of sound is more sensitive in this mode;
in the entertainment mode in combination with the safety mode in combination with the energy saving mode, a bonus function is defined in which the amount of power is as small as possible and the sound value is as small as possible:
Where W smoke is set to 10 and W rgb is set to 5, because the values of RGB light are more sensitive in this mode.
While the invention has been described with reference to the preferred embodiments, it will be understood by those skilled in the art that the present invention is not limited thereto, and that the invention is not limited thereto, but is intended to be limited thereto, when the technical content disclosed above is utilized to make a little change or modification into equivalent embodiments of equivalent changes, but the technical content of the invention is not deviated from, any simple modification, equivalent changes and modification of the above embodiments are all within the scope of the technical solution of the invention.
Claims (3)
1. An automatic control method for a plurality of devices matched with a keyboard is characterized by comprising the following steps:
S1, a keyboard receives identification numbers of a plurality of devices, device data information, sensor data and a mode selected by a user to form input information;
S2, defining a corresponding reward function by the keyboard according to the received input information and a mode selected by a user, training a reinforcement learning algorithm, obtaining weight parameters trained by the corresponding mode, and storing the model;
S3, the keyboard calls a trained model of a corresponding mode according to the received input information and the selected mode of the user, and inputs the input information into a reinforcement learning algorithm;
s4, outputting multi-control instruction information of a corresponding mode by the reinforcement learning algorithm according to the selection mode of the user, corresponding sensor data and equipment information;
the multi-control instruction information comprises a switch instruction of the air conditioner And temperature regulation commandCurtain motor rotation instructionVolume adjusting instruction for sound equipmentSwitch instruction of air purifierWith air purifier adjustment instructions;
The reinforcement learning algorithm adopts a DQN algorithm, and is switched on and off by an air conditionerAir conditioner temperature regulationTemperature sensor valueAir conditioner electric quantitySound switchVolume sizeSound sensor valueSound electric quantityAir purifier switchPurifying strength of air purifierPM2.5 gas detection sensor valueElectric quantity of air purifierRGB light adjustmentRGB lamp powerSmoke sensorThe input information of the algorithm model is as follows:
through the switch of the air conditioner Air conditioner temperature regulationSound switchVolume sizeAir purifier switchPurifying strength of air purifierRGB lamp valuesOutput value of fire extinguishing gas and dry powderExhaust fan wind speed adjustmentThe output information of the algorithm model isUpdating neural network parameters toWherein, the method comprises the steps of, wherein,To correspond toThe actual output value of the device in question,The learning rate is set to be 0.1;
The user-selected modes include a safe mode, an energy-saving mode, a silent mode, an entertainment mode, and a purified air mode;
the keyboard is provided with a mode switching knob, and a user can switch different modes through the mode switching knob;
The reinforcement learning algorithm defines a reward function of a corresponding mode according to the received input information, namely a model of a required mode can be trained, and in the deep reinforcement learning, the reinforcement learning consists of a deep neural network and maps a plurality of inputs to a plurality of outputs;
in the safe mode combined with the energy-saving mode, the input information through the algorithm model is Defining a reward function of the electrical quantity:
wherein, the method comprises the steps of, wherein, Let the prize value be 10The larger and better, when rewarding the valueAfter stabilization, the model parameters are converged, and corresponding instructions are outputAllowing the corresponding equipment to enter an energy-saving mode, and when the smoke value reaches the concentration measured by the model, starting a fan to send dry powder to a target area;
In the clean air mode in combination with the safe mode in combination with the energy saving mode, a reward function of the power and PM2.5 values is defined:
wherein, the method comprises the steps of, wherein, The number of the holes is set to be 10,Set to 5;
In silent mode in combination with safe mode in combination with energy saving mode, a bonus function of power and sound values is defined:
wherein, the method comprises the steps of, wherein, The number of the holes is set to be 10,Set to 5;
in the entertainment mode in combination with the safety mode in combination with the energy saving mode, a bonus function of the power and sound values is defined:
wherein, the method comprises the steps of, wherein, The number of the holes is set to be 10,Set to 5.
2. The method for automatically controlling a plurality of devices for keyboard matching according to claim 1, wherein the sensor data comprises a temperature value, a humidity value, a PM2.5 value, an illumination value, and a sound volume value.
3. The method for automatically controlling a plurality of devices according to claim 1, wherein the device data information includes a current time and a current number of devices turned on.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210066050.4A CN114527670B (en) | 2022-01-20 | 2022-01-20 | Automatic control method for multiple devices matched with keyboard |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210066050.4A CN114527670B (en) | 2022-01-20 | 2022-01-20 | Automatic control method for multiple devices matched with keyboard |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114527670A CN114527670A (en) | 2022-05-24 |
| CN114527670B true CN114527670B (en) | 2024-12-17 |
Family
ID=81620832
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210066050.4A Active CN114527670B (en) | 2022-01-20 | 2022-01-20 | Automatic control method for multiple devices matched with keyboard |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114527670B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109799727A (en) * | 2019-03-20 | 2019-05-24 | 北京理工大学 | A kind of smart home system of long-range control curtain and window |
| WO2019129299A1 (en) * | 2017-12-29 | 2019-07-04 | 深圳市欧瑞博科技有限公司 | Intelligent control panel, and control method and control apparatus thereof |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104133427A (en) * | 2013-05-03 | 2014-11-05 | 于庆广 | Intelligent household control method and system |
| CN105182763A (en) * | 2015-08-11 | 2015-12-23 | 中山大学 | Intelligent remote controller based on voice recognition and realization method thereof |
| CN105911873A (en) * | 2016-06-27 | 2016-08-31 | 谢骞 | Self-learning intelligent household platform with sleep mode control |
| CN106647301B (en) * | 2016-12-20 | 2019-09-17 | 王尚谦 | A kind of smart home method for safe operation and system |
| CN110647049A (en) * | 2019-10-28 | 2020-01-03 | 苏州朗捷通智能科技有限公司 | Intelligent hotel management system |
-
2022
- 2022-01-20 CN CN202210066050.4A patent/CN114527670B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019129299A1 (en) * | 2017-12-29 | 2019-07-04 | 深圳市欧瑞博科技有限公司 | Intelligent control panel, and control method and control apparatus thereof |
| CN109799727A (en) * | 2019-03-20 | 2019-05-24 | 北京理工大学 | A kind of smart home system of long-range control curtain and window |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114527670A (en) | 2022-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109631241B (en) | Building indoor comfortable environment regulating system | |
| CN113551340A (en) | Intelligent fresh air monitoring system and fresh air control method thereof | |
| CN110836509A (en) | Household equipment control method and device, control equipment and readable storage medium | |
| WO2022237193A1 (en) | Air supply control method and apparatus for air conditioner, and air conditioner | |
| CN111457485A (en) | Intelligent temperature and humidity environment control device and system | |
| CN110940030A (en) | Operation control method and system of air conditioner and air conditioner | |
| CN114527670B (en) | Automatic control method for multiple devices matched with keyboard | |
| CN104407588A (en) | Automatic control system of livestock and poultry | |
| CN106482185B (en) | Fuzzy intelligent switch device and fuzzy intelligent variable speed control method for range hood | |
| KR20010095960A (en) | Neuro-controller for the Implementation of Artificial Intelligence Apartment Building | |
| CN112117665A (en) | Dehumidification control method and system for matching switchgear group | |
| CN115493227A (en) | Purification equipment control method and device, purification equipment | |
| CN107347507A (en) | A kind of smart greenhouse | |
| CN114740740A (en) | Control method, control device and smart home system of smart home system | |
| KR20220067394A (en) | Cubicle type artificial intelligence insect breeding device | |
| CN112128934A (en) | Intelligent control method and intelligent control device of air conditioner | |
| CN115167585A (en) | Environmental control system for animal husbandry farms | |
| CN114489200A (en) | Warmhouse booth environmental control system | |
| CN103293994B (en) | A kind of domestic environment energy-saving control method based on fuzzy intelligence Behavior modeling | |
| CN109237571A (en) | Oil fume extraction system and control method thereof | |
| CN215965412U (en) | Intelligent fume hood ventilating system and fume hood | |
| CN116774599A (en) | Intelligent equipment control method based on knowledge graph, computer device and computer readable storage medium | |
| CN209430459U (en) | A kind of intelligent fan | |
| CN114738981A (en) | Air conditioning and environmental parameter control methods | |
| CN206683117U (en) | A kind of intelligent fresh air system based on internet cloud platform |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |