CN117562310A - Temperature control method of heating appliance based on temperature prediction model - Google Patents
Temperature control method of heating appliance based on temperature prediction model Download PDFInfo
- Publication number
- CN117562310A CN117562310A CN202410022013.2A CN202410022013A CN117562310A CN 117562310 A CN117562310 A CN 117562310A CN 202410022013 A CN202410022013 A CN 202410022013A CN 117562310 A CN117562310 A CN 117562310A
- Authority
- CN
- China
- Prior art keywords
- temperature
- prediction model
- heating element
- heating appliance
- heating
- 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.)
- Pending
Links
- 238000010438 heat treatment Methods 0.000 title claims abstract description 153
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000005086 pumping Methods 0.000 claims abstract description 13
- 238000012549 training Methods 0.000 claims abstract description 12
- 238000004364 calculation method Methods 0.000 claims abstract description 11
- 235000019504 cigarettes Nutrition 0.000 abstract description 13
- 230000036632 reaction speed Effects 0.000 abstract description 6
- 238000009529 body temperature measurement Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000391 smoking effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A24—TOBACCO; CIGARS; CIGARETTES; SIMULATED SMOKING DEVICES; SMOKERS' REQUISITES
- A24F—SMOKERS' REQUISITES; MATCH BOXES; SIMULATED SMOKING DEVICES
- A24F40/00—Electrically operated smoking devices; Component parts thereof; Manufacture thereof; Maintenance or testing thereof; Charging means specially adapted therefor
- A24F40/50—Control or monitoring
- A24F40/57—Temperature control
-
- A—HUMAN NECESSITIES
- A24—TOBACCO; CIGARS; CIGARETTES; SIMULATED SMOKING DEVICES; SMOKERS' REQUISITES
- A24F—SMOKERS' REQUISITES; MATCH BOXES; SIMULATED SMOKING DEVICES
- A24F40/00—Electrically operated smoking devices; Component parts thereof; Manufacture thereof; Maintenance or testing thereof; Charging means specially adapted therefor
- A24F40/40—Constructional details, e.g. connection of cartridges and battery parts
- A24F40/46—Shape or structure of electric heating means
-
- A—HUMAN NECESSITIES
- A24—TOBACCO; CIGARS; CIGARETTES; SIMULATED SMOKING DEVICES; SMOKERS' REQUISITES
- A24F—SMOKERS' REQUISITES; MATCH BOXES; SIMULATED SMOKING DEVICES
- A24F40/00—Electrically operated smoking devices; Component parts thereof; Manufacture thereof; Maintenance or testing thereof; Charging means specially adapted therefor
- A24F40/50—Control or monitoring
- A24F40/51—Arrangement of sensors
-
- A—HUMAN NECESSITIES
- A24—TOBACCO; CIGARS; CIGARETTES; SIMULATED SMOKING DEVICES; SMOKERS' REQUISITES
- A24F—SMOKERS' REQUISITES; MATCH BOXES; SIMULATED SMOKING DEVICES
- A24F40/00—Electrically operated smoking devices; Component parts thereof; Manufacture thereof; Maintenance or testing thereof; Charging means specially adapted therefor
- A24F40/50—Control or monitoring
- A24F40/53—Monitoring, e.g. fault detection
Landscapes
- Feedback Control In General (AREA)
- Control Of Temperature (AREA)
Abstract
The invention provides a temperature control method of a heating appliance based on a temperature prediction model, which comprises the following steps: and constructing a temperature prediction model of the heating appliance, acquiring a historical temperature data set of the heating appliance in a suction stage, and taking the historical temperature data set as training data of the temperature prediction model to perform temperature prediction self-learning training. When the heating appliance performs pumping operation, the temperature prediction model predicts the predicted temperature of the heating element at the next moment according to the historical data before the current moment in the pumping operation. The method comprises the steps of obtaining the actual temperature corresponding to a heating element of a heating appliance and the preset target temperature, and further obtaining the comprehensive error through calculation. And optimizing parameters of the temperature prediction model in real time according to the comprehensive errors obtained by each calculation, and adjusting the voltage of a heating element of the heating appliance so as to enable the temperature of the heating element to be consistent with the target temperature. The invention can improve the temperature control precision and the reaction speed of the cigarette heating appliance.
Description
Technical Field
The invention relates to the technical field of temperature control of heating appliances, in particular to a temperature control method of a heating appliance based on a temperature prediction model.
Background
The quality of the smoking experience of the heating cigarette is mainly determined by the heating cigarette itself and the performance of the heating appliance, wherein the temperature control system plays a very important role in the smoking experience of consumers as a core component of the whole heating appliance. In practical application, the temperature control system of the heating appliance is easily influenced by factors such as the advantages and disadvantages of a temperature control algorithm, hardware level, operation environment and the like, so that the problems of poor temperature control accuracy, poor stability and the like are caused. At present, the heating appliances on the market mainly adopt PID algorithm to control the temperature, which has the defects of relatively large accumulated error and low sensitivity, and is easy to cause the phenomena of large error between actual temperature and target temperature and large temperature fluctuation of the heating appliances. Therefore, how to control the temperature of the heating appliance conveniently and accurately has important significance.
Disclosure of Invention
The invention provides a temperature control method of a heating appliance based on a temperature prediction model, which solves the problems of inaccurate temperature control and poor temperature stability of the existing cigarette appliance and can improve the temperature control precision and the reaction speed of the cigarette heating appliance.
In order to achieve the above object, the present invention provides the following technical solutions:
a temperature control method of a heating appliance based on a temperature prediction model, comprising:
constructing a temperature prediction model of the heating appliance, acquiring a historical temperature data set of the heating appliance in a suction stage, and taking the historical temperature data set as training data of the temperature prediction model to perform temperature prediction self-learning training;
when the heating appliance performs pumping operation, the temperature prediction model predicts the predicted temperature of the heating element at the next moment according to historical data before the current moment in the pumping operation;
acquiring an actual temperature and a preset target temperature corresponding to a heating element of a heating appliance, and calculating to obtain a comprehensive error according to the error between the predicted temperature and the actual temperature and the error between the actual temperature and the target temperature;
and optimizing parameters of the temperature prediction model in real time according to the comprehensive errors obtained by each calculation, and adjusting the voltage of a heating element of the heating appliance so as to enable the temperature of the heating element to be consistent with the target temperature.
Preferably, the calculating obtains a comprehensive error, including:
according to the formula: the integrated error = error of the predicted temperature and the actual temperature + error between the target temperature and the actual temperature, calculated.
Preferably, the constructing a temperature prediction model of the heating appliance includes:
the time convolution network TCN is used as a temperature prediction model of the backbone network.
Preferably, the temperature prediction model adopts a loss function as follows:
loss=Smooth L1 loss(T k ,T′ k )+Smooth L1 loss(T k ,T 0 ) Wherein loss is the integrated error of the temperature prediction model, T 0 For the target temperature of the heating element, T K T 'is the actual temperature' k To predict temperature.
Preferably, the predicting the predicted temperature of the heating element at the next time according to the historical data before the current time in the pumping operation includes:
and predicting the temperature of the heating element at the next moment according to the internal fluctuation rule of the temperature of the heating element at all the previous moments.
Preferably, the acquiring the actual temperature and the preset target temperature corresponding to the heating element of the heating appliance includes:
the actual temperature of the heating element is calculated by collecting the voltage value and the current value of the heating element.
Preferably, the acquiring the actual temperature and the preset target temperature corresponding to the heating element of the heating appliance further includes:
the actual temperature of the heating element is detected in real time by a thermocouple sensor, a resistance temperature detector, a thermistor sensor or a temperature sensor.
Preferably, adjusting the voltage of the heating element of the heating appliance according to the integrated error includes:
and taking the integrated error as feedback of a temperature control PID algorithm to control the temperature PID of the heating element of the heating appliance.
Preferably, the voltage of the heating element of the heating appliance is adjusted according to the integrated error, and the method further comprises:
and obtaining a temperature regulation control quantity according to the comprehensive error, and controlling the voltage of the heating element through a corresponding PWM wave so as to regulate the temperature of the heating element.
Preferably, optimizing parameters of the temperature prediction model in real time according to the comprehensive error obtained by each calculation includes:
and optimizing the loss function according to the comprehensive error so as to optimize the network parameters of the temperature prediction model.
The invention provides a temperature control method of a heating appliance based on a temperature prediction model, which predicts the predicted temperature of a heating element at the next moment through the temperature prediction model, calculates and obtains a comprehensive error according to the error between the predicted temperature and the actual temperature and the error between the actual temperature and the target temperature, and adjusts the voltage of the heating element of the heating appliance through the comprehensive error so as to control the temperature of the heating element. Solves the problems of inaccurate temperature control and poor temperature stability of the existing cigarette appliance, and can improve the temperature control precision and the reaction speed of the cigarette heating appliance.
Drawings
In order to more clearly illustrate the specific embodiments of the present invention, the drawings that are required to be used in the embodiments will be briefly described.
Fig. 1 is a schematic diagram of a temperature control method of a heating appliance based on a temperature prediction model according to the present invention.
FIG. 2 is a logic flow diagram of a method for controlling the temperature of a heating appliance based on a temperature prediction model according to an embodiment of the present invention.
Detailed Description
In order to make the solution of the embodiment of the present invention better understood by those skilled in the art, the embodiment of the present invention is further described in detail below with reference to the accompanying drawings and embodiments.
Aiming at the problems of temperature control of the current cigarette heating appliance, the invention provides a temperature control method of the heating appliance based on a temperature prediction model, solves the problems of inaccuracy and poor temperature stability of the current cigarette heating appliance in temperature control, and can improve the temperature control precision and the reaction speed of the cigarette heating appliance.
As shown in fig. 1 and 2, a temperature control method of a heating appliance based on a temperature prediction model includes:
s1: and constructing a temperature prediction model of the heating appliance, acquiring a historical temperature data set of the heating appliance in a suction stage, and taking the historical temperature data set as training data of the temperature prediction model to perform temperature prediction self-learning training.
S2: when the heating appliance performs pumping operation, the temperature prediction model predicts the predicted temperature of the heating element at the next moment according to the historical data before the current moment in the pumping operation.
S3: and acquiring the actual temperature corresponding to the heating element of the heating appliance and a preset target temperature, and calculating to obtain a comprehensive error according to the error between the predicted temperature and the actual temperature and the error between the actual temperature and the target temperature.
S4: and optimizing parameters of the temperature prediction model in real time according to the comprehensive errors obtained by each calculation, and adjusting the voltage of a heating element of the heating appliance so as to enable the temperature of the heating element to be consistent with the target temperature.
Further, the calculating obtains a comprehensive error, including: according to the formula: the integrated error = error of the predicted temperature and the actual temperature + error between the target temperature and the actual temperature, calculated.
Specifically, historical temperature data of a heating appliance in a pumping stage is input into a temperature prediction module, and the temperature prediction model in the temperature prediction module carries out self-learning training on the historical temperature data so as to predict the temperature of a heating element at the next moment; and calculating the error between the predicted temperature and the actual temperature and the error between the actual temperature and the target temperature. And then calculating the integrated error, and further outputting a corresponding PWM command to adjust the voltage of the heating element according to the integrated error. The method can improve the temperature control precision and the reaction speed of the cigarette heating device.
Further, the constructing a temperature prediction model of the heating appliance includes: the time convolution network TCN is used as a temperature prediction model of the backbone network.
Further, the temperature prediction model adopts a loss function as follows:
loss=smooth L1 loss(T k ,T′ k )+Smooth L1 loss(T k ,T 0 ) Wherein loss is the ensemble of the temperature prediction modelError of combination, T 0 For the target temperature of the heating element, T K T 'is the actual temperature' k To predict temperature.
In practical application, a temperature prediction model using a time convolutional network TCN as a main network is adopted, and compared with a traditional convolutional neural network, historical temperature data [ T ] is introduced 1 ,T 2 ,…,T k-1 ]The time factor of (2) simulates the advantages of a PID algorithm and solves the problem of actual temperature T 1 ,T 2 ,…,T k ]And target temperature T 0 History deviation and recent deviation problem, and simultaneously, predicted temperature T' k More accurate. The main idea of this temperature prediction model is to rely on the temperature at all times before [ T ] 1 ,T 2 ,…,T k-1 ]Internal fluctuation law predicts the predicted temperature T 'of the heating element at the next moment' k And by narrowing the actual temperature T k And a predicted temperature T' k Error of (c) and actual temperature T k And a target temperature T 0 Improves the accuracy of the temperature control of the system and ensures the actual temperature T k Steady approach to target temperature T 0 . The loss function adopted by the temperature prediction model is as follows: loss=smoothl 1 loss (T k ,T′ k )+Smooth L1 loss(T k ,T 0 ) Loss is the integrated error of the temperature prediction model and is used for feeding back and optimizing network parameters.
The time convolution network TCN is pre-trained by pumping a temperature data set through a self-built heating appliance or an over-open data set of the same type, after training, the temperature data set is migrated to a real temperature data set of the heating appliance for training, and finally, a temperature calculation module and an intelligent prediction module after training are integrated to a heating appliance chip.
Further, the predicting, according to the historical data before the current moment in the pumping operation, the predicted temperature of the heating element at the next moment includes: and predicting the temperature of the heating element at the next moment according to the internal fluctuation rule of the temperature of the heating element at all the previous moments.
Further, acquiring the actual temperature corresponding to the heating element of the heating appliance and the preset target temperature comprises the step of calculating the actual temperature of the heating element by acquiring the voltage value and the current value of the heating element.
Further, the method for acquiring the actual temperature and the preset target temperature corresponding to the heating element of the heating appliance further comprises the step of detecting the actual temperature of the heating element in real time through a thermocouple sensor, a resistance temperature detector, a thermistor sensor or a temperature sensor.
Specifically, a voltage acquisition module is adopted to acquire voltage of the heating element, a current acquisition module is adopted to acquire current of the heating element, and the acquired voltage and current are input into a temperature calculation investigation block to determine the temperature of the heating element. The voltage acquisition module, the current acquisition module and the temperature calculation module can be integrated into one module, and can be respectively split. The temperature measurement can be realized by adopting a thermocouple temperature measurement principle to calculate the real-time temperature of the heating element, and can be replaced by a thermistor method, a Resistance Temperature Detector (RTD), an IC temperature sensor and other temperature measurement methods.
The temperature prediction module can adopt algorithms such as a regression prediction model, an XGBoots model, a gray prediction model and the like to replace the temperature prediction model. In addition, TCN may be replaced with a network such as RNN, CNN, LSTM by taking TCN as a temperature prediction model of the backbone network.
Further, the adjusting the voltage of the heating element of the heating appliance according to the integrated error includes: and taking the integrated error as feedback of a temperature control PID algorithm to control the temperature PID of the heating element of the heating appliance.
Further, the adjusting the voltage of the heating element of the heating appliance according to the integrated error further comprises: and obtaining a temperature regulation control quantity according to the comprehensive error, and controlling the voltage of the heating element through a corresponding PWM wave so as to regulate the temperature of the heating element.
Further, optimizing parameters of the temperature prediction model in real time according to the comprehensive errors obtained by each calculation includes:
and optimizing the loss function according to the comprehensive error so as to optimize the network parameters of the temperature prediction model.
The invention provides a temperature control method of a heating appliance based on a temperature prediction model, which predicts the temperature of a heating element at the next moment according to the temperature of the heating element at the current moment through the temperature prediction model, further calculates the integrated error according to the error between the predicted temperature and the actual temperature and the error between the actual temperature and the target temperature, and adjusts the voltage of the heating element of the heating appliance according to the integrated error so as to control the temperature of the heating element. Solves the problems of inaccurate temperature control and poor temperature stability of the existing cigarette appliance, and can improve the temperature control precision and the reaction speed of the cigarette heating appliance.
While the construction, features and effects of the present invention have been described in detail with reference to the embodiments shown in the drawings, the above description is only a preferred embodiment of the present invention, but the present invention is not limited to the embodiments shown in the drawings, and all changes made according to the concepts of the present invention or modifications as equivalent embodiments are within the scope of the present invention without departing from the spirit covered by the specification and drawings.
Claims (10)
1. A temperature control method of a heating appliance based on a temperature prediction model, comprising:
constructing a temperature prediction model of the heating appliance, acquiring a historical temperature data set of the heating appliance in a suction stage, and taking the historical temperature data set as training data of the temperature prediction model to perform temperature prediction self-learning training;
when the heating appliance performs pumping operation, the temperature prediction model predicts the predicted temperature of the heating element at the next moment according to historical data before the current moment in the pumping operation;
acquiring an actual temperature and a preset target temperature corresponding to a heating element of a heating appliance, and calculating to obtain a comprehensive error according to the error between the predicted temperature and the actual temperature and the error between the actual temperature and the target temperature;
and optimizing parameters of the temperature prediction model in real time according to the comprehensive errors obtained by each calculation, and adjusting the voltage of a heating element of the heating appliance so as to enable the temperature of the heating element to be consistent with the target temperature.
2. The method for controlling the temperature of a heating appliance based on a temperature prediction model according to claim 1, wherein the calculating results in a comprehensive error, comprising:
according to the formula: the integrated error = error of the predicted temperature and the actual temperature + error between the target temperature and the actual temperature, calculated.
3. The method for controlling the temperature of a heating appliance based on a temperature prediction model according to claim 2, wherein the constructing the temperature prediction model of the heating appliance comprises:
the time convolution network TCN is used as a temperature prediction model of the backbone network.
4. A temperature control method of a heating appliance based on a temperature prediction model according to claim 3, wherein the temperature prediction model adopts a loss function of: loss=smoothl1loss (T k ,T′ k )+Smooth L1 loss(T k ,T 0 ) Wherein loss is the integrated error of the temperature prediction model, T 0 For the target temperature of the heating element, T K T 'is the actual temperature' k To predict temperature.
5. The method according to claim 4, wherein predicting the predicted temperature of the heating element at the next time based on the history data before the current time in the pumping operation comprises:
and predicting the temperature of the heating element at the next moment according to the internal fluctuation rule of the temperature of the heating element at all the previous moments.
6. The method for controlling the temperature of a heating appliance based on a temperature prediction model according to claim 5, wherein the acquiring the actual temperature and the preset target temperature corresponding to the heating element of the heating appliance comprises:
the actual temperature of the heating element is calculated by collecting the voltage value and the current value of the heating element.
7. The method for controlling the temperature of a heating appliance based on a temperature prediction model according to claim 6, wherein the acquiring the actual temperature and the preset target temperature corresponding to the heating element of the heating appliance further comprises:
the actual temperature of the heating element is detected in real time by a thermocouple sensor, a resistance temperature detector, a thermistor sensor or a temperature sensor.
8. The method for controlling the temperature of a heating appliance based on a temperature prediction model according to claim 7, wherein adjusting the heating element voltage of the heating appliance according to the integrated error comprises:
and taking the integrated error as feedback of a temperature control PHD algorithm to control the temperature PHD of the heating element of the heating appliance.
9. The method for controlling the temperature of a heating appliance based on a temperature prediction model according to claim 8, wherein adjusting the heating element voltage of the heating appliance according to the integrated error further comprises:
and obtaining a temperature regulation control quantity according to the comprehensive error, and controlling the voltage of the heating element through a corresponding PWM wave so as to regulate the temperature of the heating element.
10. The method according to claim 9, wherein optimizing parameters of the temperature prediction model in real time based on the integrated error obtained by each calculation comprises:
and optimizing the loss function according to the comprehensive error so as to optimize the network parameters of the temperature prediction model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410022013.2A CN117562310A (en) | 2024-01-05 | 2024-01-05 | Temperature control method of heating appliance based on temperature prediction model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410022013.2A CN117562310A (en) | 2024-01-05 | 2024-01-05 | Temperature control method of heating appliance based on temperature prediction model |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117562310A true CN117562310A (en) | 2024-02-20 |
Family
ID=89891986
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410022013.2A Pending CN117562310A (en) | 2024-01-05 | 2024-01-05 | Temperature control method of heating appliance based on temperature prediction model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117562310A (en) |
-
2024
- 2024-01-05 CN CN202410022013.2A patent/CN117562310A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8131400B2 (en) | Adaptive on-tool mass flow controller tuning | |
CN104392274B (en) | The short-term electro-load forecast method in city based on power load and temperature trend | |
WO2017113875A1 (en) | Temperature prediction method and system thereof | |
CN112000008B (en) | Pipeline monitoring system based on neural network | |
CN111998919B (en) | Gas meter calibration method and device | |
WO2017211071A1 (en) | Temperature prediction method and apparatus thereof | |
CN201476905U (en) | Neural network PID temperature controlled thermocouple automatic verification system | |
JP7266907B2 (en) | BATTERY PERFORMANCE EVALUATION DEVICE AND BATTERY PERFORMANCE EVALUATION METHOD | |
JPH0995917A (en) | River water level predicting device | |
CN117562310A (en) | Temperature control method of heating appliance based on temperature prediction model | |
CN104281178B (en) | Regulator and data collecting method | |
CN117235462A (en) | Intelligent fault prediction method for bag type packaging machine based on time sequence data analysis | |
CN108399415A (en) | A kind of self-adapting data acquisition method based on life cycle phase residing for equipment | |
CN113959511B (en) | Flow metering method, equipment, medium and product based on jet flow water meter | |
CN116179840A (en) | Laser surface heat treatment temperature monitoring control system and control method | |
JP6269678B2 (en) | Fuzzy control device and fuzzy control method | |
JP2002054460A (en) | Combustion vibration predicting device | |
CN110398063A (en) | Water heater and its control method and computer readable storage medium | |
CN111340647A (en) | Power distribution network data adjustment method and system | |
CN117129904B (en) | Industrial power supply rapid switching monitoring method based on data analysis | |
CN117572823B (en) | Dynamic compensation method and system for thermal expansion of main shaft | |
KR101721111B1 (en) | Automatic tuning PID control method for industrial heater system using uDEAS | |
CN117452989B (en) | BP neural network-based temperature regulation and control valve performance regulation and test method | |
CN117225659B (en) | Automatic chip process deviation recognition and correction method and system | |
CN118154001B (en) | Intelligent management method for bridge construction data |
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 |