Control method and device for adjusting equipment of drying oven, terminal equipment and program product
By using the combination of the LSTM prediction model and the PID control model in the oven, the problem of inaccurate oven temperature and atmosphere control in the prior art is solved, and efficient and accurate control effect is achieved.
Patent Information
- Application Number
- CN202411854195.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-13
- Publication Date
- 2025-04-18
AI Technical Summary
The prior art is difficult to achieve accurate and efficient control in oven temperature and atmosphere control, resulting in adverse effects on product performance.
By obtaining the actual status data of the oven and the preset target status data, input it to the pre-trained LSTM prediction model, output theoretical operation parameters, and control the adjustment device using the PID control model.
Accurate and efficient control of oven adjustment equipment is achieved, reducing dependence on a large amount of historical data, and improving control accuracy and efficiency.
Smart Images
Figure CN119846941A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of oven control, and in particular to a control method, device, terminal equipment and program product of an oven regulating device. Background Art
[0002] The oven is a typical high-precision sintering equipment. The temperature and atmosphere control inside it is a complex process with multiple inputs and outputs, which involves very large time delays, nonlinearity, and multi-factor spatial distribution characteristics. If the temperature and atmosphere of the oven are not accurately controlled, it will have an adverse effect on the performance of the products produced by the oven.
[0003] In the current technical solution, the corresponding training samples are generally determined by collecting a large amount of historical operating parameters of the oven's regulating equipment and the historical actual state data in the oven, and learning and training are performed based on the training samples to obtain the LSTM prediction model; after the actual state data of the oven is collected, the LSTM prediction model is used to predict the theoretical operating parameters corresponding to the actual state data, and the oven's regulating equipment is controlled based on the theoretical operating parameters. However, in this technical solution, a large amount of historical actual data needs to be collected as training samples, and the process of training the LSTM prediction model is complicated, resulting in inaccurate control of the oven's regulating equipment.
[0004] Therefore, how to accurately and efficiently control the regulating equipment of the oven, so as to accurately control the status data in the oven, is a technical problem that technical personnel in this field currently need to solve. Summary of the invention
[0005] The purpose of the present application is to provide a control method, device, terminal device, computer-readable storage medium and computer program product for an oven regulating device, aiming to accurately and efficiently control the oven regulating device, thereby accurately controlling the status data in the oven.
[0006] In a first aspect, the present application provides a method for controlling an oven regulating device. The method comprises:
[0007] Obtaining actual state data and preset target state data of the oven;
[0008] The actual state data and the preset target state data are input into a pre-trained LSTM prediction model, and the LSTM prediction model is used to output corresponding theoretical operating parameters; the training sample set of the LSTM prediction model is determined according to the input and output parameters of the model prediction control model; the input and output parameters include the input simulated operating parameters of the regulating device of the oven and the corresponding output predicted state data in the oven;
[0009] The regulating device of the oven is controlled according to the theoretical operating parameters.
[0010] In one embodiment, determining the training sample set of the LSTM prediction model according to the input and output parameters of the model prediction control model includes:
[0011] Determining the simulation operation parameters;
[0012] Inputting the simulated operation parameters into the model predictive control model, and using the model predictive control model to output predicted state data in the oven corresponding to the simulated operation parameters;
[0013] Determine a simulated difference between the predicted state data and the actual state data, and update the simulated operation parameters according to the simulated difference, and return to the step of inputting the simulated operation parameters into the model predictive control model, and using the model predictive control model to output the predicted state data in the oven corresponding to the simulated operation parameters;
[0014] After the simulation operation parameters are updated in multiple cycles, the training sample set is determined.
[0015] In one embodiment, the method further comprises:
[0016] If the preset target state data is different from the target state data when training the LSTM prediction model, the LSTM prediction model is fine-tuned through transfer learning to update the LSTM prediction model.
[0017] In one embodiment, controlling the regulating device of the oven according to the theoretical operating parameters includes:
[0018] The theoretical operating parameters are input into a PID control model, so that the PID control model controls the regulating device of the oven according to the theoretical operating parameters.
[0019] In one embodiment, the PID control model controls the regulating device of the oven according to the theoretical operating parameters, including:
[0020] The PID control model obtains the theoretical operating parameters;
[0021] Determining a parameter difference between the theoretical operating parameter and the actual operating parameter;
[0022] An adjustment control signal is determined according to the parameter difference, and the adjustment control signal is used to control the regulating device.
[0023] In one embodiment, the regulating device includes a temperature regulating device and an atmosphere regulating device.
[0024] In a second aspect, the present application also provides a control device for an oven adjustment device. The device comprises:
[0025] An acquisition module is used to acquire the actual state data and preset target state data of the oven;
[0026] A prediction module, used for inputting the actual state data and the preset target state data into a pre-trained LSTM prediction model, and using the LSTM prediction model to output corresponding theoretical operating parameters; the training sample set of the LSTM prediction model is determined according to the input and output parameters of the model prediction control model; the input and output parameters include the input simulated operating parameters of the regulating device of the oven and the corresponding output predicted state data in the oven;
[0027] A control module is used to control the regulating device of the oven according to the theoretical operating parameters.
[0028] In a third aspect, the present application further provides a terminal device, wherein the terminal device comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.
[0029] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.
[0030] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.
[0031] The present application provides a control method for an oven regulating device, which determines a training sample set of an LSTM prediction model according to the input and output parameters of a model predictive control model, wherein the input and output parameters include input simulated operating parameters of the oven regulating device and corresponding output predicted state data in the oven; then trains an LSTM prediction model based on the training sample set; after obtaining the actual state data and preset target state data of the oven, inputs the actual state data and the preset target state data into a pre-trained LSTM prediction model, and uses the LSTM prediction model to output corresponding theoretical operating parameters; and controls the oven regulating device according to the theoretical operating parameters. The method determines a training sample set based on the input and output parameters of a model predictive control model, and then trains an LSTM prediction model, which can efficiently and accurately learn the dynamic changes of the oven operating parameters based on the regulating device, without collecting a large amount of actual data as training samples, so the method can efficiently and accurately control the oven regulating device.
[0032] It can be understood that the control device, terminal device, computer-readable storage medium and computer program product of the oven regulating device provided in the embodiment of the present application have the same beneficial effects as the control method of the oven regulating device mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0034] Figure 1 A flow chart of a control method for an oven adjustment device provided in an embodiment of the present application;
[0035] Figure 2 A schematic diagram of the structure of a control device for an oven adjustment device provided in an embodiment of the present application;
[0036] Figure 3 A schematic diagram of the structure of a terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0037] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.
[0038] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.
[0039] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.
[0040] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.
[0041] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.
[0042] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways. "Multiple" means "two or more".
[0043] A control method for an oven regulating device provided in an embodiment of the present application may be executed by a processor of a terminal device when running a corresponding computer program.
[0044] Figure 1 This is a flow chart of a control method for an oven adjustment device provided in an embodiment of the present application. For ease of description, only the part related to the present embodiment is shown. The method provided in the present embodiment includes the following steps:
[0045] S100: Acquire actual state data and preset target state data of the oven.
[0046] The oven is a typical high-precision sintering equipment. The temperature and atmosphere control inside it is a complex process with multiple inputs and multiple outputs, which involves very large time delays, nonlinearity, and spatial distribution characteristics of multiple factors. Among them, the actual state data of the oven refers to the data corresponding to the state inside the oven. Specifically, the actual state data includes actual temperature, actual atmosphere, etc., which are not limited in this embodiment.
[0047] Specifically, a plurality of temperature sensors are arranged in the oven to detect the actual temperature in the oven, and a plurality of atmosphere sensors are arranged in the oven to detect the actual atmosphere in the oven.
[0048] The preset target state data refers to the state data that is expected to be achieved in the oven in advance, such as the target temperature, target atmosphere, etc.
[0049] S200: Input the actual state data and the preset target state data into the pre-trained LSTM prediction model, and use the LSTM prediction model to output the corresponding theoretical operating parameters; the training sample set of the LSTM prediction model is determined according to the input and output parameters of the model prediction control model; the input and output parameters include the input simulation operating parameters of the oven's regulating device and the corresponding output predicted state data in the oven.
[0050] It should be noted that before training the LSTM prediction model, a training sample set needs to be determined first. The training sample set in this embodiment is determined based on the input and output parameters of the model predictive control (MPC) model. Among them, the model predictive control model is a model that predicts how the regulating equipment in the oven responds to operating parameters; operating parameters refer to parameters that control the operation of the regulating equipment, including the operating power of the heating element, the operating power of the fan, the flow regulating equipment, the gas control valve, etc. The regulating equipment is controlled by the operating parameters to adjust the temperature and atmosphere in the oven.
[0051] In this embodiment, the simulated operating parameters of the regulating equipment of the oven are first obtained, such as the power of the heater, the speed of the fan, etc.; the simulated operating parameters are input into the model predictive control model, and the model predictive control model is used to output corresponding predicted state data, such as predicted temperature, predicted humidity and predicted atmosphere, etc.; the predicted atmosphere includes gas type and the content of each gas; and the training samples are determined based on the simulated operating parameters and the predicted state data.
[0052] Specifically, after determining the training sample set, learning and training are performed based on the training sample set to obtain the LSTM prediction model. The LSTM prediction model is a special recurrent neural network (RNN) that can learn long-term dependencies.
[0053] It should be noted that the input of the trained LSTM prediction model is the actual state data x(t) of the detection point in the oven and the preset target state data ref, and the output is the operating parameter u(t) of the regulating device; the input of the trained LSTM prediction model can also be the difference e(t) between the actual state data x(t) of the detection point in the oven and the preset target state data ref, and the output is the operating parameter u(t) of the regulating device.
[0054] In a specific embodiment, after the LSM prediction model is trained, the actual state data (such as the temperature and humidity in the oven) and the preset target state data (such as the expected temperature and humidity) are used as inputs to the pre-trained LSTM prediction model; these data are usually time series data, indicating the change of the system state over time. The LSTM prediction model predicts the theoretical operating parameters of the oven's regulating device at a certain point in the future based on the input actual state data and the preset target state data.
[0055] The theoretical operating parameters refer to the operating parameters of the regulating equipment determined by the LSTM prediction model. Controlling the regulating equipment based on the theoretical operating parameters can enable the oven to reach the state corresponding to the preset target state data.
[0056] S300: Controlling the regulating device of the oven according to theoretical operating parameters.
[0057] Specifically, after the theoretical operating parameters are determined, the regulating device of the oven is controlled based on the theoretical operating parameters.
[0058] In practical applications, taking the temperature control of an oven as an example, the theoretical operating parameter may be the operating power of the temperature regulating device. If it is determined that the actual temperature of the oven is lower than the preset target temperature, the operating power of the temperature regulating device is increased according to the theoretical operating parameter to increase the temperature in the oven until the preset target temperature is reached.
[0059] The embodiment of the present application provides a control method for an oven regulating device, which determines a training sample set of an LSTM prediction model according to the input and output parameters of a model predictive control model, wherein the input and output parameters include input simulated operating parameters of the oven regulating device and corresponding output predicted state data in the oven; then the LSTM prediction model is trained based on the training sample set; after obtaining the actual state data and preset target state data of the oven, the actual state data and the preset target state data are input into the pre-trained LSTM prediction model, and the corresponding theoretical operating parameters are output using the LSTM prediction model; the oven regulating device is controlled according to the theoretical operating parameters. The method determines a training sample set based on the input and output parameters of the model predictive control model, and then trains an LSTM prediction model, which can efficiently and accurately learn the dynamic changes of the oven operating parameters based on the regulating device, without collecting a large amount of actual data as training samples, so the method can efficiently and accurately control the oven regulating device.
[0060] In a specific embodiment, the regulating device includes a temperature regulating device and an atmosphere regulating device. It is understandable that the temperature and atmosphere in the oven are key factors affecting product quality, so this embodiment controls the temperature regulating device and the atmosphere regulating device of the oven.
[0061] The temperature regulating device may be a heating device. In practical applications, a plurality of temperature regulating devices may be arranged in the oven, and the temperature in the oven may be regulated by controlling the switches of the temperature regulating devices and the operating power of the temperature regulating devices.
[0062] Among them, the atmosphere adjustment equipment includes gas control valves, flow control equipment and circulating fans, etc. Among them, the gas control valve is used to control the opening and closing of each gas valve; the flow control equipment is used to control the gas flow input into the oven; the circulating fan is used to adjust the uniform distribution of gas in the oven.
[0063] In this embodiment, the oven can be controlled more accurately by cooperatively controlling the temperature adjustment device and the atmosphere adjustment device.
[0064] On the basis of the above embodiments, this embodiment further illustrates and optimizes the technical solution. Specifically, in this embodiment, a training sample set of the LSTM prediction model is determined according to the input and output parameters of the model prediction control model, including:
[0065] Determine simulation operation parameters;
[0066] Inputting the simulated operation parameters into the model predictive control model, and using the model predictive control model to output predicted state data in the oven corresponding to the simulated operation parameters;
[0067] Determine a simulated difference between the predicted state data and the actual state data, update the simulated operation parameters according to the simulated difference, and return to the step of inputting the simulated operation parameters into the model predictive control model, and use the model predictive control model to output the predicted state data in the oven corresponding to the simulated operation parameters;
[0068] After updating the simulation parameters in multiple cycles, the training sample set is determined.
[0069] It should be noted that the model predictive control model is divided into three core parts: prediction model, feedback correction and rolling optimization. It predicts the future behavior of the controlled system through its mathematical model, and selects the best control scheme based on the online optimization strategy to ensure that the output of the controlled system is consistent with the predetermined target.
[0070] Specifically, the model predictive control model outputs the corresponding predicted state data in the oven, such as predicted temperature, humidity, etc., based on the input simulation operation parameters; the predicted state data output by the model predictive control model is compared with the actual state data obtained by actual measurement, and the simulation difference is calculated; wherein the simulation difference represents the deviation between the prediction result of the model predictive control model and the actual situation.
[0071] The simulation operation parameters are updated according to the simulation difference, and the simulation operation parameters are used to reduce the difference between the predicted state data and the actual state data; the simulation operation parameters can be determined by the optimization algorithm so that the predicted state data is as close as possible to the actual state data; after the simulation operation parameters are updated, the simulation operation parameters are input into the model predictive control model again, and the process of prediction and difference calculation is repeated, that is, the simulation operation parameters are input into the model predictive control model, and the model predictive control model is used to output the predicted state data in the oven corresponding to the simulation operation parameters.
[0072] After updating the simulation operation parameters for multiple cycles, that is, continuously optimizing the simulation operation parameters, the simulation operation parameters, the predicted state data and the actual state data corresponding to the simulation operation parameters are collected to form a training sample set of the LSTM prediction model.
[0073] This embodiment combines the predictive ability of the model predictive control model and the learning ability of the LSTM prediction model, and generates a high-quality training data set through iterative optimization and simulation, providing a basis for the training of the LSTM prediction model; therefore, by using the training data set determined by the method of this embodiment for learning and training, the LSTM prediction model can be obtained efficiently.
[0074] In the temperature control process of the oven, the model mismatch of the LSTM prediction model refers to the difference between the LSTM prediction model used and the actual system. Since the oven temperature control involves complex factors such as nonlinearity, time-varying characteristics and external interference, the model mismatch problem is more obvious when the reference value (preset target state data) changes. This is because the dynamic response characteristics of the LSTM prediction model may change with different temperature ranges. It should be noted that the LSTM prediction model is good at learning and predicting dynamic changes from time series data, but its performance depends largely on the training samples during the training process. If the reference value (preset target state data) changes significantly, the LSTM prediction model may not be able to quickly adapt to this new condition, because its training process does not contain a large amount of data related to the newly set preset target state data, so it may overfit the dynamic response mode under the original set point during the training process.
[0075] On the basis of the above embodiments, this embodiment further illustrates and optimizes the technical solution. Specifically, in this embodiment, the method further includes:
[0076] If the preset target state data is different from the target state data when training the LSTM prediction model, the LSTM prediction model is fine-tuned through transfer learning to update the LSTM prediction model.
[0077] That is to say, if the preset target state data is different from the target state data when training the LSTM prediction model, that is, when the preset target state data changes significantly compared with the target state data when training the LSTM prediction model, the LSTM prediction model will tend to run according to the previous mode, resulting in the output theoretical operating parameters being inaccurate.
[0078] Specifically, transfer learning is a machine learning technique that acquires knowledge from an existing model and applies the knowledge to a new but related problem. In this embodiment, if the preset target state data is different from the target state data when training the LSTM prediction model, the LSTM prediction model is fine-tuned through transfer learning to update the LSTM prediction model.
[0079] In a specific example, the time series pattern learned in the existing LSTM prediction model can be used to migrate it to the new preset target state data. Directly using the LSTM prediction model to determine the theoretical operation data based on the budget target state data and the actual state data is equivalent to directly using the LSTM prediction model to make predictions based on the new preset target state data.
[0080] In this embodiment, temperature data near the preset target state data can be obtained, and corresponding training samples can be determined; the LSTM prediction model can be retrained using the newly determined training samples to fine-tune the LSTM prediction model and update the LSTM prediction model. After the LSTM prediction model is updated, the updated LSTM prediction model is used to determine the theoretical operation data based on the budget target state data and the actual state data.
[0081] According to the method of this embodiment, when the preset target state data is different from the target state data when training the LSTM prediction model, the LSTM prediction model is fine-tuned through transfer learning, and the LSTM prediction model is updated so that the updated LSTM prediction model can be used to determine the theoretical operating data based on the budget target state data and the actual state data. This method can accelerate the LSTM prediction model to adapt to the new preset target state data without the need to retrain the entire model from scratch, greatly improving the response speed and accuracy of the LSTM prediction model. Therefore, the method of this embodiment can efficiently and accurately determine the theoretical operating data.
[0082] On the basis of the above embodiment, this embodiment further illustrates and optimizes the technical solution. Specifically, in this embodiment, the regulating device of the oven is controlled according to the theoretical operating parameters, including:
[0083] The theoretical operating parameters are input into the PID control model, so that the PID control model controls the regulating equipment of the oven according to the theoretical operating parameters.
[0084] The PID control model is a control model composed of a proportion unit, an integral unit, and a differential unit. In this embodiment, after the theoretical operating parameters are determined, the theoretical operating parameters are input into the PID control model. After obtaining the theoretical operating parameters, the PID control model determines the adjustment control signal for the adjustment device of the oven through calculation, and inputs the adjustment control signal into the adjustment device to control the adjustment device.
[0085] In this embodiment, the theoretical operating parameters generated by the LSTM prediction model are used as the optimal control solution and the input of the PID control model. The theoretical operating parameters are optimized using the PID adjustment method to manage and adjust the state changes in the oven.
[0086] This embodiment controls the regulating device of the oven through the PID control model, which can improve the control accuracy of the oven.
[0087] In a specific embodiment, the PID control model controls the regulating device of the oven according to the theoretical operating parameters, including:
[0088] The PID control model obtains theoretical operating parameters;
[0089] Determine the parameter difference between theoretical operating parameters and actual operating parameters;
[0090] An adjustment control signal is determined according to the parameter difference, and the adjustment control signal is used to control the regulating device.
[0091] Specifically, after the LSTM prediction model determines the theoretical operating parameters and inputs the theoretical operating parameters into the PID control model, the PID control model obtains the theoretical operating parameters; the PID control model determines the parameter difference between the theoretical operating parameters and the actual operating parameters, and determines the adjustment control signal according to the parameter difference; the adjustment control signal is the amount by which the regulating device currently needs to be adjusted.
[0092] After determining the adjustment control signal, the calculated control signal is applied to the regulating device, and the regulating device is controlled by the adjustment control signal, such as opening or closing the valve, increasing or decreasing the motor speed, etc.; after the regulating device is adjusted according to the adjustment control signal, the actual state data in the oven will be changed accordingly.
[0093] Furthermore, after the actual state data in the oven changes, the parameter difference between the theoretical operating parameters and the actual operating parameters will be updated accordingly, as well as the adjustment control signal, and the updated adjustment control signal will be used again to control the regulating device.
[0094] After the regulating device is cyclically adjusted and controlled, the actual state data in the oven can reach the preset target state data.
[0095] According to the method of this embodiment, the regulating device of the oven can be accurately controlled through the PID control model.
[0096] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0097] It should be noted that the information collection process (such as face image collection process, fingerprint information collection process, etc.) / feature extraction process involved in this application is performed with the user's knowledge and permission, that is, the information collection process / feature extraction process complies with the requirements of laws and regulations and does not constitute an act that harms the public interest.
[0098] Figure 2 The figure shows a schematic diagram of the structure of a control device for an oven adjustment device provided in an embodiment of the present application. Figure 2As shown, the control device of the oven regulating device of this embodiment includes an acquisition module 210, a prediction module 220 and a control module 230; wherein,
[0099] An acquisition module 210 is used to acquire actual state data and preset target state data of the oven;
[0100] The prediction module 220 is used to input the actual state data and the preset target state data into the pre-trained LSTM prediction model, and use the LSTM prediction model to output the corresponding theoretical operating parameters; the training sample set of the LSTM prediction model is determined according to the input and output parameters of the model prediction control model; the input and output parameters include the input simulated operating parameters of the regulating device of the oven and the corresponding output predicted state data in the oven;
[0101] The control module 230 is used to control the regulating device of the oven according to the theoretical operating parameters.
[0102] A control device for an oven regulating device provided in an embodiment of the present application has the same beneficial effects as the control method for an oven regulating device described above.
[0103] In one embodiment, the prediction module includes:
[0104] A simulation operation parameter determination submodule is used to determine simulation operation parameters;
[0105] A predicted state data determination submodule is used to input the simulated operation parameters into the model predictive control model, and use the model predictive control model to output predicted state data in the oven corresponding to the simulated operation parameters;
[0106] A simulation operation parameter updating submodule is used to determine the simulation difference between the predicted state data and the actual state data, and to update the simulation operation parameters according to the simulation difference, and to call the predicted state data determining submodule;
[0107] The training sample set determination submodule is used to determine the training sample set after updating the simulation operation parameters in multiple cycles.
[0108] In one embodiment, a control device for an oven regulating device further includes:
[0109] The model fine-tuning module is used to fine-tune the LSTM prediction model through transfer learning and update the LSTM prediction model if the preset target state data is different from the target state data when training the LSTM prediction model.
[0110] In one embodiment, the control module includes:
[0111] The control submodule is used to input theoretical operating parameters into the PID control model so that the PID control model controls the regulating equipment of the oven according to the theoretical operating parameters.
[0112] In one embodiment, the control submodule includes:
[0113] Theoretical operation parameter acquisition unit, used for PID control model to acquire theoretical operation parameters;
[0114] A parameter difference determination unit, used to determine the parameter difference between a theoretical operating parameter and an actual operating parameter;
[0115] The control unit is used to determine an adjustment control signal according to the parameter difference and use the adjustment control signal to control the regulating device.
[0116] In one embodiment, the regulating device includes a temperature regulating device and an atmosphere regulating device.
[0117] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.
[0118] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.
[0119] Figure 3 A schematic diagram of the structure of a terminal device provided in an embodiment of the present application. Figure 3As shown, the terminal device 300 of this embodiment includes a memory 301, a processor 302, and a computer program 303 stored in the memory 301 and executable on the processor 302; when the processor 302 executes the computer program 303, the steps in the control method embodiments of the regulating devices of the above-mentioned ovens are implemented; or when the processor 302 executes the computer program 303, the functions of the modules / units in the above-mentioned device embodiments are implemented.
[0120] Exemplarily, the computer program 303 may be divided into one or more modules / units, one or more modules / units are stored in the memory 301, and are executed by the processor 302 to implement the method of the embodiment of the present application. One or more modules / units may be a series of computer program instruction segments that can perform specific functions, and the instruction segments are used to describe the execution process of the computer program 303 in the terminal device 300. For example, the computer program 303 may be divided into an acquisition module, a prediction module, and a control module, and the specific functions of each module are as follows:
[0121] An acquisition module is used to acquire the actual state data and preset target state data of the oven;
[0122] The prediction module is used to input the actual state data and the preset target state data into the pre-trained LSTM prediction model, and use the LSTM prediction model to output the corresponding theoretical operating parameters; the training sample set of the LSTM prediction model is determined according to the input and output parameters of the model prediction control model; the input and output parameters include the input simulated operating parameters of the regulating device of the oven and the corresponding output predicted state data in the oven;
[0123] The control module is used to control the regulating equipment of the oven according to theoretical operating parameters.
[0124] In application, the terminal device 300 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal device 300 may include but is not limited to a memory 301 and a processor 302. Those skilled in the art will appreciate that Figure 3 It is only an example of a terminal device and does not constitute a limitation of the terminal device. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal device may also include input and output devices, network access devices, buses, etc.; among which, the input and output devices may include cameras, audio acquisition / playback devices, display screens, etc.; the network access device may include a communication module for wireless communication with external devices.
[0125] In applications, the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.
[0126] In applications, the memory can be an internal storage unit of a terminal device, such as a hard disk or memory of the terminal device; it can also be an external storage device of the terminal device, such as a plug-in hard disk equipped on the terminal device, a smart media card (SMC), a secure digital (SD) card, a flash card, etc.; it can also include both the internal storage unit and the external storage device of the terminal device. The memory is used to store operating systems, applications, boot loaders, data, and other programs, such as program codes of computer programs. The memory can also be used to temporarily store data that has been output or is about to be output.
[0127] The embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.
[0128] The present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device capable of carrying the computer program code to a terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electric carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk.
[0129] A computer-readable storage medium provided in an embodiment of the present application has the same beneficial effects as the control method of the above-mentioned oven regulating device.
[0130] An embodiment of the present application further provides a computer program product, including a computer program, which can implement the steps in the above-mentioned method embodiments when executed by a processor.
[0131] A computer program product provided in an embodiment of the present application has the same beneficial effects as the control method of the above-mentioned oven regulating device.
[0132] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0133] Those of ordinary skill in the art will appreciate that the devices and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0134] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of devices, which can be electrical, mechanical or other forms.
[0135] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.
Claims
1. A control method for an oven regulating device, characterized in that: The method comprises: Obtaining actual state data and preset target state data of the oven; The actual state data and the preset target state data are input into a pre-trained LSTM prediction model, and the LSTM prediction model is used to output corresponding theoretical operating parameters; the training sample set of the LSTM prediction model is determined according to the input and output parameters of the model prediction control model; the input and output parameters include the input simulated operating parameters of the regulating device of the oven and the corresponding output predicted state data in the oven; The regulating device of the oven is controlled according to the theoretical operating parameters.
2. The method according to claim 1, characterized in that: Determining the training sample set of the LSTM prediction model according to the input and output parameters of the model prediction control model includes: Determining the simulation operation parameters; Inputting the simulated operation parameters into the model predictive control model, and using the model predictive control model to output predicted state data in the oven corresponding to the simulated operation parameters; Determine a simulated difference between the predicted state data and the actual state data, and update the simulated operation parameters according to the simulated difference, and return to the step of inputting the simulated operation parameters into the model predictive control model, and using the model predictive control model to output the predicted state data in the oven corresponding to the simulated operation parameters; After the simulation operation parameters are updated in multiple cycles, the training sample set is determined.
3. The method according to claim 1, characterized in that: The method further comprises: If the preset target state data is different from the target state data when training the LSTM prediction model, the LSTM prediction model is fine-tuned through transfer learning to update the LSTM prediction model.
4. The method according to claim 1, characterized in that: The controlling the regulating device of the oven according to the theoretical operating parameters comprises: The theoretical operating parameters are input into a PID control model, so that the PID control model controls the regulating device of the oven according to the theoretical operating parameters.
5. The method according to claim 4, characterized in that The PID control model controls the regulating device of the oven according to the theoretical operating parameters, including: The PID control model obtains the theoretical operating parameters; Determining a parameter difference between the theoretical operating parameter and the actual operating parameter; An adjustment control signal is determined according to the parameter difference, and the adjustment control signal is used to control the regulating device.
6. The method according to any one of claims 1 to 5, characterized in that: The regulating equipment includes a temperature regulating equipment and an atmosphere regulating equipment.
7. A control device for an oven regulating device, characterized in that: The device comprises: An acquisition module is used to acquire the actual state data and preset target state data of the oven; A prediction module, used for inputting the actual state data and the preset target state data into a pre-trained LSTM prediction model, and using the LSTM prediction model to output corresponding theoretical operating parameters; the training sample set of the LSTM prediction model is determined according to the input and output parameters of the model prediction control model; the input and output parameters include the input simulated operating parameters of the regulating device of the oven and the corresponding output predicted state data in the oven; A control module is used to control the regulating device of the oven according to the theoretical operating parameters.
8. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.
9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.