Automatic temperature control method of oven
By obtaining the characteristic position and environmental prediction data of the oven, and adjusting the gain parameters of the PID controller using the artificial intelligence model, the problem of inaccurate oven temperature control under the influence of external environment in the existing technology is solved, and the problem of inaccurate oven temperature control in the outdoor environment is realized. Highly efficient and stable temperature control.
Patent Information
- Application Number
- CN202410948272.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-16
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-07-16
AI Technical Summary
The existing oven temperature control system is difficult to ensure the accuracy and stability of temperature control under the influence of the external environment. Especially when used outdoors, the gain parameters of traditional PID controllers are difficult to adapt to environmental changes, resulting in insufficient temperature control.
By obtaining the characteristic location of the oven, obtaining environmental prediction data and performing segmentation processing, using artificial intelligence models to build a gain prediction model, dynamically adjusting the gain parameters of the PID controller to ensure that the gain parameters match the current environment, thereby achieving accurate temperature adjustment .
It improves the accuracy and stability of oven temperature control, can effectively adapt to environmental changes in the outdoor environment, and ensures the efficiency and accuracy of temperature control.
Smart Images

Figure CN118484044B_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of oven temperature control, and relates to an automatic temperature control technology for an oven, and specifically to an automatic temperature control method for an oven. Background Art
[0002] In the oven control system, the accuracy and stability of temperature control have always been the top priority. In the traditional oven temperature control system, the temperature control effect is not ideal due to the large inertia, large hysteresis, nonlinearity and difficulty in establishing an exact mathematical model of the oven itself.
[0003] The prior art (patent application with publication number CN117663814A) discloses a hot air circulation electric oven and a control method thereof. The method adjusts the parameters of the PID controller through a preset specific algorithm, realizes real-time self-tuning of the parameters, and automatically matches the optimal temperature control parameters for the new oven, so as to achieve the purpose of improving control accuracy and stability, and realize intelligent control of steaming and baking temperature.
[0004] In the prior art, various gains in the PID controller are calculated by combining the target temperature, actual temperature, temperature deviation and temperature deviation change rate through a preset specific algorithm, and then the PID controller is adjusted in real time based on various gains. However, the prior art mainly considers the influence of the oven's own parameters and set values when calculating the gain. Once the external environment affects the oven's temperature control process, it is difficult to ensure the accuracy and stability of the temperature control, which will seriously affect the oven's usage scenario.
[0005] The present application provides an automatic temperature control method for an oven to solve the above technical problems. Summary of the invention
[0006] The present application aims to solve at least one of the technical problems existing in the prior art; to this end, the present application proposes an automatic temperature control method for an oven, which is used to solve the technical problem that the prior art is difficult to eliminate the influence of the external environment on the temperature control of the oven, resulting in difficulty in ensuring the accuracy and stability of temperature control when the oven is used outdoors.
[0007] To achieve the above-mentioned purpose, the first aspect of the present application provides an automatic temperature control method for an oven, comprising:
[0008] Acquire the characteristic position of the target oven, and continuously extract the environmental prediction data corresponding to the target oven based on the characteristic position; segment the environmental prediction data according to the fluctuation state to obtain a number of environmental data segments;
[0009] After preprocessing several environmental data segments, input them into the gain prediction model to obtain several gain data groups; splicing each gain data group according to the time sequence of the corresponding environmental data segments to obtain a gain data sequence; wherein the gain prediction model is constructed based on the artificial intelligence model;
[0010] The gain parameters of the PID controller in the target oven are adjusted according to the gain data sequence to achieve dynamic adjustment of the gain parameters; wherein the gain parameters include proportional gain, integral gain and differential gain.
[0011] With the improvement of the quality of life, more and more residents yearn for outdoor life. The oven is an important cooking utensil for making delicious food outdoors, and it is used more and more frequently outdoors. The temperature control of the oven is generally controlled by a PID controller. The proportional gain, integral gain and differential gain in the PID control function are generally calibrated through experiments or other methods. The above gain parameters are generally not adjusted during subsequent use. However, when the oven is used outdoors, it is easily affected by various environmental factors, which makes it difficult to efficiently and accurately control the oven temperature according to the original gain parameters.
[0012] The present application determines the corresponding use environment according to the characteristic position of the oven (target oven), and obtains the environmental prediction data corresponding to the use environment. The environmental prediction data is then segmented according to its fluctuations, and the segmented environmental data segments are integrated and input into the gain prediction model to obtain the gain data group corresponding to the environmental data segment. The gain parameters in the gain data group are sent to the PID controller to achieve precise temperature regulation. The present application predicts the corresponding gain parameters in advance through the environmental prediction data of the location of the oven. During subsequent adjustments, it is only necessary to update the gain parameters used by the PID controller at the corresponding time, which can ensure the real-time performance of the gain parameters and improve the accuracy of temperature control.
[0013] Preferably, the step of continuously extracting environmental prediction data corresponding to the target oven based on the characteristic position includes:
[0014] Extracting a characteristic position; wherein the characteristic position is obtained by a sensor disposed in the target oven, or by an intelligent terminal, and the characteristic position includes latitude, longitude and altitude;
[0015] A target area is constructed with the characteristic position as the center and the set parameters as the radius; environmental prediction data at the characteristic position in the target area is obtained through the meteorological platform; wherein the environmental prediction data includes ambient temperature, ambient humidity and wind strength.
[0016] In order to adjust the target oven in real time, it is necessary to obtain the characteristic position of the target oven, that is, where the target oven is used. Then, the environmental prediction data at the characteristic position is obtained through the authorized meteorological platform, and the optimal gain parameter can be predicted through the environmental prediction data.
[0017] However, considering that the environmental data of a certain point is difficult to obtain accurately, the present application constructs a target area with the characteristic position as the center and the set parameters as the radius to obtain the environmental prediction data within the target area. The mean of each environmental element in the target area can be used as the environmental prediction data of the characteristic position.
[0018] Preferably, the segmented processing of the environmental prediction data according to the fluctuation state includes:
[0019] Construct an environmental prediction curve based on the environmental prediction data; mark the corresponding functions of the temperature change curve, humidity change curve, and wind strength curve in the environmental prediction curve as WBQ, SBQ, and FBQ, respectively;
[0020] The volatility assessment coefficient BPX is calculated by the formula BPX=∫[α1×d(WBQ)+α2×d(SBQ)+α3×d(FBQ)]; where α1, α2 and α3 are weight coefficients, For function The differential of For function The integral of
[0021] Whenever the fluctuation assessment coefficient BPX is greater than or equal to the fluctuation assessment threshold, the environmental prediction data corresponding to the integral time period is used as an environmental data segment; wherein the fluctuation assessment threshold is set according to the degree of influence of environmental changes on the gain parameters.
[0022] When using the oven outdoors, the environment may change rapidly during use. Once the environment changes dramatically, it is possible that the established gain parameters cannot meet the requirements of the changed environment, resulting in inefficient and inaccurate temperature control of the oven. Therefore, it is necessary to monitor environmental changes in the use scenario at all times and adjust the gain parameters of the PID controller at any time.
[0023] Therefore, this application needs to process the environmental prediction data in segments to ensure that the total gain parameters of the PID controller can be updated in time. In the segmented processing process, the main factor to be considered is the volatility of the environmental prediction data. Therefore, the function corresponding to the environmental prediction curve is first differentiated to obtain the incremental change at each moment, eliminating the influence of the constant term on the volatility assessment; then the incremental change over a period of time is summed up through integral processing to obtain the fluctuation assessment coefficient. The fluctuation assessment coefficient is compared with the assessment coefficient threshold. Once the fluctuation assessment coefficient is greater than or equal to the assessment coefficient threshold, the corresponding integral time range in the calculation process of the fluctuation assessment coefficient is made into an integral time period; then the fluctuation assessment coefficient is calculated again. Multiple integral time periods can be obtained, and the environmental prediction data can be divided according to the integral time periods to obtain environmental data segments.
[0024] It should be noted that the evaluation coefficient threshold can be set based on experience. Once the fluctuation evaluation coefficient is greater than or equal to the evaluation coefficient threshold, it means that the environment fluctuations in the corresponding integration time period are large, and the previously determined gain parameters may not be suitable for the environment in the integration time period.
[0025] The present application divides the environmental prediction data into several environmental data segments by obtaining the fluctuation assessment coefficient, and calculates the gain parameter of each environmental data segment, which can improve the matching degree between the subsequent gain parameter and the corresponding use environment, thereby ensuring the accuracy of the oven temperature control. Moreover, by segmenting the environmental prediction data, the gain parameter can be adjusted at regular intervals, and the gain parameter does not need to be adjusted as soon as the environmental prediction data changes, which can improve the stability of the oven temperature control.
[0026] Preferably, the gain prediction model is constructed based on an artificial intelligence model, including:
[0027] Setting simulated environment data, and simulating usage scenarios based on the simulated environment data; wherein the simulated environment data includes environment temperature, environment humidity and wind strength;
[0028] Simulate the use process of the target oven in the use scenario, and extract and integrate standard training data according to the simulation results; wherein the standard training data includes standard input data constructed based on the simulation environment data, and standard output data constructed based on the optimal gain parameters;
[0029] The artificial intelligence model is trained by standard training data to obtain a gain prediction model; wherein the artificial intelligence model includes a BP neural network model or a RBF neural network model.
[0030] Generally speaking, the gain parameters (proportional gain, differential gain and integral gain) in PID control are mainly obtained through continuous adjustment through experiments. This method takes a lot of time each time and is not suitable for situations with diverse usage scenarios. It is difficult to achieve timely adjustment of the gain parameters.
[0031] When using an oven outdoors, the environmental factors have the greatest impact on the temperature control of the oven, that is, the environmental factors directly affect the gain parameters. Once the gain parameters do not match the environmental factors, the accuracy of the oven temperature control cannot be guaranteed. Therefore, this application predicts the gain parameters through an artificial intelligence model, and the mapping relationship between the gain parameters and the environmental factors can be constructed through the nonlinear processing capability of the artificial intelligence model, which can improve the accuracy and timeliness of the gain parameter prediction.
[0032] Preferably, the preprocessing of the plurality of environmental data segments and inputting them into the gain prediction model comprises:
[0033] Calculating environmental data groups of the plurality of environmental data segments within a corresponding time range; wherein the environmental data groups include a temperature mean, a humidity mean, and a wind strength mean;
[0034] After preprocessing a plurality of environmental data groups corresponding to the plurality of environmental data segments according to the format requirements of the gain prediction model, the plurality of environmental data groups are input into the gain prediction model to obtain a plurality of gain data groups.
[0035] This application processes each environmental data segment to obtain an environmental data group; all environmental data segments are input into the gain prediction model after data preprocessing to obtain the corresponding gain data group; the gain data group includes proportional gain, integral gain and differential gain, and each environmental data segment corresponds to a gain data group. It should be noted that the preprocessing here is mainly necessary processing of the environmental data segment to ensure that it meets the input format requirements of the gain prediction model; the same preprocessing is also required for standard input data when training artificial intelligence models.
[0036] Preferably, the step of splicing the gain data groups according to the time sequence of the corresponding environment data segments includes:
[0037] Extracting the integral time periods corresponding to the environmental data segments, and splicing them in the order of time in the integral time periods to generate a time series;
[0038] The gain data group corresponding to the environmental data segment is associated with the corresponding integral time period in the time series to obtain a gain data sequence.
[0039] After obtaining the gain data group corresponding to each environmental data segment, the present application associates the gain data group with the integral time period corresponding to the environmental data segment, so as to obtain a gain data sequence. According to the gain data sequence, the PID parameters can be automatically set, and the oven temperature can be automatically controlled.
[0040] Preferably, adjusting the gain parameters of the PID controller in the target oven according to the gain data sequence includes:
[0041] After calibrating the clock in the target oven, the clock time is extracted in real time;
[0042] When the clock time is consistent with the initial moment of the integration time period in the time series, the gain data group associated with the integration time period is extracted;
[0043] The gain data set is sent to a PID controller, and the PID controller adjusts the temperature of the target oven based on the gain data set and a temperature error; wherein the temperature error is the difference between the actual temperature and the set temperature.
[0044] After the oven is turned on, its internal clock needs to be calibrated first. There are many ways to calibrate the clock. A built-in clock calibration chip can be used, or the clock can be calibrated by scanning mobile phones, computers and other smart terminals through Bluetooth technology.
[0045] After the clock is calibrated, the internal clock is compared with the initial moment of each integral time period in the gain data sequence. Once it is consistent with the initial moment, the gain data group corresponding to the integral time period is extracted to adjust the parameters of the PID controller, and then the PID calculation is completed according to the difference between the set temperature and the actual temperature of the oven to achieve accurate control of the oven temperature.
[0046] It is worth noting that both the oven parameter tuning and PID calculation require a certain amount of time, so the tuning process and the calculation process can be appropriately advanced to ensure that the PID calculation results are output at the initial moment of each integral time period.
[0047] Preferably, the target oven includes a data processing unit, a data sensor and a temperature setting unit;
[0048] The data processing unit is used to perform data interaction with the cloud platform to obtain and update the gain data sequence; the cloud platform is used to train and update the gain prediction model and obtain the gain data sequence;
[0049] The data sensor is used to obtain the actual temperature of the target oven;
[0050] The temperature setting unit is used to set a target temperature of a target oven.
[0051] Compared with the prior art, the beneficial effects of this application are:
[0052] 1. The present application first obtains the characteristic position of the target oven, and continuously extracts the environmental prediction data corresponding to the target oven based on the characteristic position; processes the environmental prediction data through a pre-trained gain prediction model to obtain the optimal gain data group; and adjusts the parameters of the PID controller in the oven through the gain data group; the present application timely obtains the use environment of the target oven, and then determines the optimal gain parameters, which can improve the accuracy of the oven temperature control.
[0053] 2. The present application performs segmented processing on the environmental prediction data according to the fluctuation state to obtain a number of environmental data segments; and then predicts the optimal gain data group of each environmental data segment through the gain prediction model; the present application performs segmented processing and segmented prediction according to volatility to avoid frequent parameter adjustment of the PID controller, which can improve the stability of the oven temperature control. BRIEF DESCRIPTION OF THE DRAWINGS
[0054] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0055] Figure 1 This is a schematic diagram of the process of the automatic temperature control method for an oven in an embodiment of the present application;
[0056] Figure 2 Schematic diagram of gain data sequence in an embodiment of the present application. DETAILED DESCRIPTION
[0057] The technical solution of the present application will be described clearly and completely in conjunction with the embodiments below. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.
[0058] See also Figure 1-Figure 2 The first embodiment of the present application provides an automatic temperature control method for an oven, comprising:
[0059] Acquire the characteristic position of the target oven, and continuously extract the environmental prediction data corresponding to the target oven based on the characteristic position; segment the environmental prediction data according to the fluctuation state to obtain a number of environmental data segments;
[0060] After preprocessing several environmental data segments, input them into the gain prediction model to obtain several gain data groups; splicing each gain data group according to the time sequence of the corresponding environmental data segments to obtain a gain data sequence; wherein the gain prediction model is constructed based on the artificial intelligence model;
[0061] The gain parameters of the PID controller in the target oven are adjusted according to the gain data sequence to achieve dynamic adjustment of the gain parameters; wherein the gain parameters include proportional gain, integral gain and differential gain.
[0062] The oven has different usage scenarios when used outdoors and indoors. Generally, the indoor altitude is not high, and the temperature and humidity are relatively constant; however, when used outdoors, if it is used in a high altitude area, the altitude will definitely affect the temperature control effect. If the original calibrated gain parameters are still used, the oven temperature cannot be accurately controlled. In addition, the oven temperature control will also be affected by the different calorific values of the pellets and the different amounts of grilled food.
[0063] This application first obtains the optimal gain data set for each usage scenario through a large amount of simulation test data training, and trains the artificial intelligence model to obtain a gain prediction model. Then, based on the gain prediction model, the gain parameters of the environmental prediction data corresponding to the target oven usage scenario are predicted, and the PID controller of the target oven is parameterized according to the predicted gain parameters. The temperature of the target oven is adjusted in time through the adjusted PID controller to improve the accuracy and stability of temperature control. It should be noted that in addition to the simulation of usage scenarios during simulation training, simulations are also performed for different particle calorific values or amounts of grilled food to further improve the accuracy of oven temperature control and expand the usage scenarios of the oven.
[0064] The technical solution of this application is mainly to dynamically adjust the PID controller according to the current usage scenario of the target oven to ensure that the gain parameters in the PID controller best match the current usage scenario. Therefore, it is necessary to first obtain the characteristic position of the target oven, and then obtain the environmental prediction data at the characteristic position through the meteorological platform to complete the subsequent gain parameter prediction.
[0065] In this embodiment, the characteristic position of the target oven can be directly acquired through an internal sensor when the target oven is turned on.
[0066] In a preferred embodiment, if a powerful data processing chip is installed inside the target oven, the acquisition of characteristic positions, prediction of gain parameters, construction of gain prediction models, etc. can all be completed through the data processing chip. In another preferred embodiment, in order to reduce the cost of the target oven, a cloud platform can be set up to process data through the cloud platform. The target oven only needs to set the parameters of the PID controller according to the obtained gain data sequence to complete the temperature control; and the cloud platform can process the data of multiple ovens simultaneously, which can significantly reduce the cost when the number of ovens is large enough.
[0067] Whether through the meteorological platform or outdoors, it is not very convenient to obtain environmental data of a certain point. Therefore, this embodiment takes the characteristic position as a circle and the setting parameters as the radius to construct the target area; of course, a cube area centered on the characteristic position can also be constructed as the target area. The minimum unit area that can be obtained from the oven to the meteorological platform is different, so the setting parameters can refer to the data format setting of the meteorological platform, that is, the setting parameters are determined according to the minimum volume / area of the meteorological platform data. For example:
[0068] If the minimum unit of environmental data obtained by the meteorological platform is 1 square kilometer, the setting parameter should be an integer multiple of 1 square kilometer. Integrate the temperature data, humidity data and wind strength at the corresponding altitude in the target area into environmental prediction data. Of course, if the altitude at the feature location is very high, it will have a great impact on the oven temperature control process, and the altitude can also be integrated into the environmental prediction data.
[0069] In order to improve the efficiency of data processing and the control efficiency of the oven temperature, the time span corresponding to the environmental prediction data may be relatively long, such as an afternoon, a day or longer. Within this time span, it is difficult to ensure that the environmental data is unchanged. Once the environmental data changes, it is necessary to ensure that the gain parameters in the PID controller are updated synchronously, which helps to improve the accuracy of the oven temperature control.
[0070] This embodiment divides the environmental prediction data into segments according to its volatility, with the purpose of ensuring that each environmental data segment can use the same set of gain parameters without affecting the temperature control effect of the oven. The volatility of this embodiment is mainly based on the instantaneous change of each environmental factor, and the instantaneous change is integrated in the time dimension; the instantaneous change of the environmental factor is accumulated as the fluctuation evaluation coefficient, and the integration time period is continuously adjusted. Once the fluctuation evaluation coefficient is greater than or equal to the evaluation coefficient threshold, the environmental prediction data is divided according to the corresponding integration time period to obtain an environmental data segment. The acquired environmental data segment is removed from the environmental prediction data, and the fluctuation evaluation coefficient is recalculated for the remaining environmental prediction data, and segmentation continues.
[0071] In this embodiment, the construction of a gain prediction model is also a core step. The gain prediction model is mainly obtained by training an artificial intelligence model based on simulated environmental data.
[0072] First, the simulated environmental data is to determine the value range of each environmental factor in advance according to the possible use environment of the oven. It should be noted that the possible use environment should be determined according to the materials used by the oven. For example, the oven can only be used below 5,000 meters above sea level, and the altitude can be set to [0, 5000]. The value range determined in this way can better improve the application scenario of the oven. In another preferred embodiment, the value range of environmental factors can also be determined by survey or data statistics.
[0073] The values of ambient temperature, ambient humidity, wind strength, and altitude are taken according to the set step size within their respective ranges, and then several groups of simulated environmental data are obtained through permutations and combinations. Each group of simulated environmental data contains an ambient temperature, an ambient humidity, a wind strength, and an altitude. It should be noted that there are mutual influences between various environmental factors. For example, at high places, the air is dry and the relative humidity is low; at low places, the air is humid and the relative humidity is high. Therefore, after obtaining the simulated environmental data, the simulated environmental data is screened based on the mutual influence between the various environmental factors, and those that are obviously unreasonable are eliminated.
[0074] Next, we simulated usage scenarios based on the simulated environment data, and conducted temperature control tests on ovens (of the same model as the target oven) in each usage scenario to obtain the optimal gain parameters corresponding to each usage scenario. That is, in the usage scenario, the PID controller in the oven is tuned by the corresponding optimal gain parameters, and the temperature control effect (accuracy and stability) is the best.
[0075] Preprocess the simulated environment data to make it meet the input requirements of the artificial intelligence model; preprocess the optimal gain parameters corresponding to each simulated environment data to make it meet the output requirements of the artificial intelligence model. Train the artificial intelligence model with a large amount of simulated environment data and optimal gain parameters, and use the trained artificial intelligence model as a gain prediction model.
[0076] According to the above content, the characteristic position of the target oven is obtained, and then several environmental data segments are obtained according to the characteristic position. The several environmental data segments are preprocessed and input into the gain prediction model, so that the gain data group corresponding to each environmental data segment can be obtained. The gain data group is the optimal gain parameter corresponding to the environmental data segment.
[0077] In order to enable the target oven to adjust the temperature adaptively, the present embodiment first splices the integral time periods corresponding to the environmental data segments in chronological order to generate a time series, and then associates the gain data groups with the integral time periods corresponding to the time series to obtain a gain data sequence.
[0078] Before adjusting the gain parameters of the PID controller (the gain parameters are the default parameters at this time), the clock in the target oven needs to be calibrated. After calibration, the optimal gain parameters at each moment can be obtained according to the gain data sequence, and the PID controller is parameterized by the optimal gain parameters. After tuning, the actual temperature and target temperature of the oven are obtained through the data sensor and temperature setting unit in the target oven, and the temperature errors of the two are brought into the PID formula to calculate the oven output; where the formula is: PID output = Kp×error+Ki×integral error+Kd×differential error, Kp is the proportional gain, Ki is the integral gain, and Kd is the differential gain.
[0079] See also Figure 2 , specific examples:
[0080] The integration time periods corresponding to each environmental data segment are [10:00, 10:01], [10:01, 10:02], ..., [10:59, 11:00]; the gain data groups corresponding to each integration time period are ZYZ1, ZYZ2, ..., ZYZ60.
[0081] When the target oven clock reaches 10:00, the gain data set ZYZ1 is extracted to adjust the PID controller parameters; when it reaches 10:59, the gain data set ZYZ60 is extracted to adjust the PID controller parameters. If the oven reaches the parameter adjustment time, the gain data set can be extracted in advance for parameter adjustment, and the output can be directly controlled by PID calculation after the corresponding time is reached.
[0082] It is worth noting that the environmental data segments of this embodiment are divided according to the fluctuation state, so the integral time periods corresponding to the environmental data segments may not have equal step lengths.
[0083] The control system of the target oven in this embodiment mainly includes a data processing unit, a PID controller, a data sensor and a temperature setting unit. The data processing unit is used to obtain the optimal gain parameter of each time period, and the PID is parameterized according to the optimal gain parameter, and then the output of the PID is calculated according to the error between the set temperature and the actual temperature.
[0084] In some other preferred embodiments, the characteristic position of the target oven may change, or the obtained environmental data may change. Therefore, the environmental prediction data should be obtained once at a certain interval, even if the previously obtained gain data sequence has not been completely adjusted. If the newly obtained gain data sequence has a different overlap with the previously obtained gain data sequence or the error is large, the newly obtained gain data sequence is used to improve the accuracy of the PID controller parameter adjustment.
[0085] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.
[0086] The above embodiments are only used to illustrate the technical method of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the preferred embodiments, a person of ordinary skill in the art should understand that the technical method of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present application.
Claims
1. An automatic temperature control method for an oven, characterized in that: include: Obtaining a characteristic position of a target oven, and continuously extracting environmental prediction data corresponding to the target oven based on the characteristic position; The environmental prediction data is segmented according to the fluctuation state to obtain a number of environmental data segments; After preprocessing several environmental data segments, input them into the gain prediction model to obtain several gain data groups; splicing each gain data group according to the time sequence of the corresponding environmental data segments to obtain a gain data sequence; wherein the gain prediction model is constructed based on the artificial intelligence model; The gain parameters of the PID controller in the target oven are adjusted according to the gain data sequence to achieve dynamic adjustment of the gain parameters; wherein the gain parameters include proportional gain, integral gain and differential gain; The segmented processing of the environmental prediction data according to the fluctuation state includes: Construct an environmental prediction curve based on the environmental prediction data; mark the corresponding functions of the temperature change curve, humidity change curve, and wind strength curve in the environmental prediction curve as WBQ, SBQ, and FBQ, respectively; The volatility assessment coefficient BPX is calculated by the formula BPX=∫[α1×d(WBQ)+α2×d(SBQ)+α2×d(FBQ)]; where α1, α2 and α3 are weight coefficients, For function The differential of For function The integral of Whenever the fluctuation assessment coefficient BPX is greater than or equal to the fluctuation assessment threshold, the environmental prediction data corresponding to the integral time period is used as an environmental data segment; wherein the fluctuation assessment threshold is set according to the degree of influence of environmental changes on the gain parameters.
2. The automatic temperature control method of an oven according to claim 1, characterized in that: The continuously extracting the environmental prediction data corresponding to the target oven based on the characteristic position includes: Extracting a characteristic position; wherein the characteristic position is obtained by a sensor disposed in the target oven, or by an intelligent terminal, and the characteristic position includes latitude, longitude and altitude; A target area is constructed with the characteristic position as the center and the set parameters as the radius; environmental prediction data at the characteristic position in the target area is obtained through the meteorological platform; wherein the environmental prediction data includes ambient temperature, ambient humidity and wind strength.
3. The automatic temperature control method of an oven according to claim 1, characterized in that: The gain prediction model is constructed based on an artificial intelligence model, including: Setting simulated environment data, and simulating usage scenarios based on the simulated environment data; wherein the simulated environment data includes environment temperature, environment humidity and wind strength; Simulate the use process of the target oven in the use scenario, and extract and integrate standard training data according to the simulation results; wherein the standard training data includes standard input data constructed based on the simulation environment data, and standard output data constructed based on the optimal gain parameters; The artificial intelligence model is trained by standard training data to obtain a gain prediction model; wherein the artificial intelligence model includes a BP neural network model or a RBF neural network model.
4. The automatic temperature control method of an oven according to claim 1, characterized in that: The preprocessing of the plurality of environmental data segments and inputting them into the gain prediction model comprises: Calculating environmental data groups of the plurality of environmental data segments within a corresponding time range; wherein the environmental data groups include a temperature mean, a humidity mean, and a wind strength mean; After preprocessing a plurality of environmental data groups corresponding to the plurality of environmental data segments according to the format requirements of the gain prediction model, the plurality of environmental data groups are input into the gain prediction model to obtain a plurality of gain data groups.
5. The automatic temperature control method of an oven according to claim 4, characterized in that: The step of splicing the gain data groups according to the time sequence of the corresponding environment data segments includes: Extracting the integral time periods corresponding to the environmental data segments, and splicing them in the order of time in the integral time periods to generate a time series; The gain data group corresponding to the environmental data segment is associated with the corresponding integral time period in the time series to obtain a gain data sequence.
6. The automatic temperature control method of an oven according to claim 1, characterized in that: The step of adjusting the gain parameters of the PID controller in the target oven according to the gain data sequence includes: After calibrating the clock in the target oven, the clock time is extracted in real time; When the clock time is consistent with the initial moment of the integration time period in the time series, the gain data group associated with the integration time period is extracted; The gain data set is sent to a PID controller, and the PID controller adjusts the temperature of the target oven based on the gain data set and a temperature error; wherein the temperature error is the difference between the actual temperature and the set temperature.
7. The automatic temperature control method of an oven according to claim 1, characterized in that: The target oven includes a data processing unit, a data sensor and a temperature setting unit; The data processing unit is used to perform data interaction with the cloud platform to obtain and update the gain data sequence; the cloud platform is used to train and update the gain prediction model and obtain the gain data sequence; The data sensor is used to obtain the actual temperature of the target oven; The temperature setting unit is used to set a target temperature of a target oven.
Citation Information
Patent Citations
Hot air circulation electric oven and control method thereof
CN117663814A
Solar compensation type electric boiler heat supply control method based on valley electricity price change
CN107783941A
Filter auxiliary debugging method and system based on PID controller, and medium
CN117874523A
PID (Proportion Integration Differentiation) control parameter setting method of master-slave control structure in dynamic environment
CN118170002A
Air-conditioning device for vehicle
JP1986232913A
