Intelligent kitchen ware temperature control method, device and equipment and storage medium

Abstract

The invention discloses an intelligent kitchenware temperature control method, which comprises the steps of predicting operation control parameters of a next time period by utilizing an optimization control model based on internal environment data of kitchenware and operation control parameters of a PID (Proportion Integration Differentiation) controller in a current time period, the optimization control model is used for obtaining operation control parameters of the PID controller through the change trend of the internal environment data; updating the operation control parameter of the PID controller to be the operation control parameter of the next time period; and controlling the heating power of a heating element in the kitchen ware by using the PID controller with the updated operation control parameter, so that the internal temperature of the kitchen ware is maintained at a target constant value. According to the intelligent kitchenware temperature control method disclosed by the invention, the problem of relatively high energy consumption of the oven caused by continuously adjusting the working state of the heating element in the constant-temperature state is solved, so that the heating temperature of the heating element in the kitchenware is accurately controlled, the heating temperature does not need to be continuously adjusted, and the kitchenware runs at the lowest energy consumption in the constant-temperature state.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of household appliances, and in particular to a method, device, equipment and storage medium for controlling the temperature of intelligent kitchen appliances. Background Art

[0002] As people's living standards improve, the intelligence and performance of kitchen appliances have received more and more attention, and their performance and intelligence have received more and more attention.

[0003] In some technologies, kitchen appliances have certain requirements for temperature control, such as ovens, which are important components of kitchen appliances. In order to achieve the expected taste and flavor when cooking food in the oven, a constant temperature state is set in the oven to ensure the stability of the temperature inside the oven, thereby ensuring that the food is heated evenly during the cooking process.

[0004] However, in a constant temperature state, in order to maintain a certain temperature, the oven needs to constantly adjust the working state of its heating element to prevent the temperature from dropping or being too high, resulting in a large energy consumption of the oven, which does not meet the requirements of energy saving and environmental protection. Summary of the invention

[0005] The purpose of the present invention is to at least provide a method, device, equipment and storage medium for controlling the temperature of intelligent kitchenware, which can at least solve the technical problem that in a constant temperature state, in order to maintain a certain temperature, the oven needs to continuously adjust the working state of its heating element to prevent the temperature from dropping or being too high, resulting in large energy consumption of the oven and not meeting the requirements of energy conservation and environmental protection. At least the heating temperature of the heating element in the kitchenware can be accurately controlled so that the kitchenware is in a constant temperature state, and there is no need to continuously adjust the heating temperature of the heating element, so that the kitchenware can operate with the lowest energy consumption in the constant temperature state, avoiding unnecessary energy waste, achieving constant temperature energy saving, improving energy utilization efficiency, and saving energy and environmental protection.

[0006] In order to solve the above technical problems, at least one embodiment of the present application provides a temperature control method for smart kitchenware, where the smart kitchenware is a kitchenware controlled by temperature, and the method includes:

[0007] Get the internal environment data of the kitchenware;

[0008] Based on the internal environment data of the kitchen appliance and the operation control parameters of the PID controller in the current period, a preset optimization control model is used to predict the operation control parameters of the PID controller in the next period, wherein the operation control parameters in the next period are related to the change trend of the internal environment data in the current period, and are optimized evaluation values ​​when the PID controller controls the heating power of the heating element in the kitchen appliance while maintaining the internal temperature of the kitchen appliance at a target constant value;

[0009] Updating the operation control parameters of the PID controller to the operation control parameters of the next time period;

[0010] The PID controller after the operation control parameter is updated is used to control the heating power of the heating element in the kitchen appliance so that the internal temperature of the kitchen appliance is maintained at the target constant value.

[0011] At least one embodiment of the present application further provides an intelligent kitchenware temperature control device, comprising:

[0012] An acquisition module is used to obtain the internal environment data of the kitchenware;

[0013] a parameter prediction module, configured to predict the operation control parameter of the PID controller in the next period of time by using a preset optimization control model based on the internal environment data of the kitchen appliance and the operation control parameter of the PID controller in the current period of time, wherein the operation control parameter of the next period of time is related to the change trend of the internal environment data in the current period of time, and is an optimized evaluation value when the PID controller controls the heating power of the heating element in the kitchen appliance while maintaining the internal temperature of the kitchen appliance at a target constant value;

[0014] An operation update module, used for updating the operation control parameters of the PID controller to the operation control parameters of the next time period;

[0015] A control module is used to control the heating power of the heating element in the kitchen appliance by using the PID controller after the operation control parameter is updated, so that the internal temperature of the kitchen appliance is maintained at the target constant value.

[0016] At least one embodiment of the present application also provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned smart kitchenware temperature control method.

[0017] At least one embodiment of the present application further provides a computer-readable storage medium storing a computer program, wherein the computer program implements the above-mentioned intelligent kitchenware temperature control method when executed by a processor.

[0018] The intelligent kitchenware temperature control method provided by the embodiment of the present application predicts the operation control parameters of the PID controller for the next period of time based on the internal environment data of the kitchenware and the operation control parameters of the PID controller for the current period of time using a preset optimization control model, and updates the operation control parameters of the PID controller as the operation control parameters of the next period of time, and then uses the PID controller after the operation control parameters are updated to control the heating temperature of the heating element in the kitchenware so that the internal temperature of the kitchenware is maintained at a target constant value. In this way, the operation control parameters of the PID controller are dynamically adjusted according to the changing trend of the internal environment of the kitchenware to accurately control the heating temperature of the heating element in the kitchenware, so that the kitchenware is in a constant temperature state, and there is no need to constantly adjust the heating temperature of the heating element, so that the kitchenware runs at the lowest energy consumption in a constant temperature state, avoiding unnecessary energy waste, achieving constant temperature energy saving, improving energy utilization efficiency, and saving energy and environmental protection.

[0019] In some optional embodiments, the optimization control model includes a prediction model unit and an optimization model unit;

[0020] The method of predicting the operation control parameters of the PID controller in the next period of time based on the internal environment data of the kitchen appliance and the operation control parameters of the PID controller in the current period of time by using a preset optimization control model includes:

[0021] Based on the internal environment data of the kitchen appliance, predicting the temperature change parameter of the kitchen appliance in the next period of time by the prediction model unit;

[0022] Based on the temperature change parameter and the operation control parameter of the PID controller in the current period, the operation control parameter of the PID controller in the next period is determined by the optimization model unit.

[0023] By dynamically adjusting the operating control parameters of the PID controller according to the temperature change parameters of the kitchenware in the next period of time, the heating temperature of the heating element in the kitchenware can be accurately controlled, so that the kitchenware is in a constant temperature state. Moreover, there is no need to constantly adjust the heating temperature of the heating element, so that the kitchenware can operate with the lowest energy consumption in a constant temperature state.

[0024] In some optional embodiments, the optimization control model is obtained by the following steps:

[0025] Build the original model;

[0026] The original model is trained using a reinforcement learning algorithm for the internal environment data samples acquired in multiple time periods and the corresponding operation control parameter samples of the PID controller to obtain the optimized control model.

[0027] The original model is continuously strengthened and trained through internal environment data samples and corresponding PID controller operation control parameter samples to obtain an optimized control model. The operation control parameters of the PID controller for the next period are output through the optimized control model. During the cooking process, the operation control parameters of the PID controller are continuously optimized to find the operation control parameters that best suit the current cooking task and achieve precise temperature control of kitchen utensils.

[0028] In some optional embodiments, the original model includes: a prediction model training unit and an optimization model training unit;

[0029] The internal environment data samples obtained in multiple time periods and the corresponding operation control parameter samples of the PID controller are trained on the original model using a reinforcement learning algorithm to obtain the optimized control model, including:

[0030] Inputting the internal environment data samples of multiple time periods and the operation control parameter samples of the current time period into the prediction model training unit for training, so as to predict the temperature change parameter samples of the kitchenware in the next time period;

[0031] The optimization model training unit is trained based on the temperature change parameter samples and the operation control parameter samples of the current time period of the PID controller to obtain the corresponding operation control parameter samples of the next time period of the PID controller, thereby constructing the optimization control model.

[0032] By training the prediction model training unit and the optimization model training unit, the prediction model unit and the optimization model unit are obtained after training, so as to construct an optimization control model. The operation control parameters of the next period of the PID controller are output by the optimization control model to accurately control the heating temperature of the heating element in the kitchenware, so that the kitchenware is in a constant temperature state.

[0033] In some optional embodiments, the method further includes:

[0034] Constructing a training sample library, wherein the training sample library is used to store internal environment data samples, operation control parameter samples of the current period, and operation control parameter samples of the next period;

[0035] After predicting the operation control parameters of the PID controller in the next period of time based on the internal environment data of the kitchen appliance and the operation control parameters of the PID controller in the current period of time by using a preset optimization control model, the method further includes:

[0036] The predicted operation control parameters of the PID controller for the next period, the corresponding internal environment data and the operation control parameters of the PID controller for the current period are added to the training sample library to provide samples required for the optimization training of the original model.

[0037] The predicted operation control parameters of the PID controller for the next period of time and the corresponding internal environment data and the operation control parameters of the PID controller for the current period of time are added to the training sample library to expand the sample size of the training sample library and increase the data volume of the training sample data, thereby improving the accuracy of the adjustment of the operation control parameters.

[0038] In some optional embodiments, the internal environment data includes temperature, humidity, air pressure, etc.;

[0039] The method further comprises:

[0040] Based on the internal environment data of the kitchen appliance, detecting whether the humidity value of the kitchen appliance is greater than a preset humidity threshold;

[0041] When the humidity value of the kitchenware is greater than a preset humidity threshold, a dehumidification control task is started;

[0042] The dehumidification device of the kitchen appliance is controlled to perform the dehumidification control task.

[0043] Through the above steps, the moisture accumulation inside the oven can be effectively reduced, ensuring the baking effect while keeping the oven dry and clean.

[0044] In some optional embodiments, the method further includes:

[0045] Based on the humidity value of the kitchenware, determining the temperature change parameter by the prediction model unit;

[0046] Based on the temperature change parameter, a temperature adjustment mode is selected from a plurality of preset temperature adjustment modes as the temperature adjustment mode followed by the PID controller to control the heating temperature of the heating element in the kitchen appliance after the operation control parameter is updated.

[0047] According to the water accumulation situation, adjust the baking mode and baking time in time to ensure the baking effect while reducing the occurrence of water accumulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] One or more embodiments are exemplarily described by the pictures in the corresponding drawings, and these exemplary descriptions do not constitute limitations on the embodiments.

[0049] Figure 1 It is a flowchart of a method for controlling temperature of an intelligent kitchen appliance provided by an embodiment of the present application;

[0050] Figure 2 It is a flow chart of an intelligent kitchenware temperature control device provided by an embodiment of the present application;

[0051] Figure 3 is a structural schematic diagram of an electronic device provided by another embodiment of the present application;

[0052] Figure 4 It is a flow chart of a smart kitchenware temperature control method provided in another embodiment of the present application. DETAILED DESCRIPTION

[0053] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the embodiments of the present application will be described in detail below in conjunction with the accompanying drawings. However, it will be appreciated by those skilled in the art that in the present application, many technical details are proposed in order to enable the reader to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical scheme claimed in the present application can also be implemented. The division of the following embodiments is for the convenience of description, and the specific implementation of the present application should not be construed as any limitation, and the various embodiments can be combined and referenced with each other under the premise of no contradiction.

[0054] In order to facilitate understanding of the embodiments of the present application, relevant contents about the temperature control method of intelligent kitchen appliances are first introduced here.

[0055] As people's living standards improve, the intelligence and performance of kitchen appliances have received more and more attention, and their performance and intelligence have received more and more attention.

[0056] In some technologies, there are certain requirements for temperature control of kitchen appliances, such as ovens, which are important components of kitchen appliances. In order to achieve the expected taste and flavor when cooking food in the oven, a constant temperature state is set in the oven to ensure the stability of the temperature inside the oven, thereby ensuring that the food is heated evenly during the cooking process. Traditional oven temperature control systems mostly use PID (proportional-integral-differential) control algorithms, and the parameters of the PID control algorithm need to be manually adjusted.

[0057] However, in a constant temperature state, in order to maintain a certain temperature, the oven needs to constantly adjust the working state of its heating element to prevent the temperature from dropping or being too high, resulting in a large energy consumption of the oven, which does not meet the requirements of energy saving and environmental protection.

[0058] In order to solve the technical problem that in a constant temperature state, in order to maintain a certain temperature, the oven needs to constantly adjust the working state of its heating element to prevent the temperature from dropping or being too high, resulting in large energy consumption of the oven and not meeting the requirements of energy saving and environmental protection, the present invention proposes a smart kitchen temperature control method. The implementation details of the smart kitchen temperature control method of this embodiment are specifically described below. The following content is only the implementation details provided for easy understanding and is not necessary for the implementation of this solution.

[0059] Embodiment 1:

[0060] The intelligent kitchenware temperature control method of this embodiment can be applied to electronic devices with communication, computing and data storage capabilities. The specific process can be as follows: Figure 1 As shown, including:

[0061] Step 101, obtaining internal environment data of the kitchen appliance.

[0062] Specifically, smart kitchen appliances are kitchen appliances that are controlled by temperature, such as ovens, microwave ovens, etc. In some examples, the internal environmental data of the kitchen appliances include temperature, humidity, air pressure and other data.

[0063] In this embodiment, in order to obtain real-time information about the internal environment of the kitchenware, a high-precision environment perception module is equipped. The module integrates multiple sensors such as temperature sensors and humidity sensors, and can monitor key parameters such as temperature and humidity inside the oven in real time. In some examples, after obtaining the internal environment data of the kitchenware, preprocessing and feature extraction are performed to better capture the trend of environmental changes. For example, features such as the rate of change of temperature and the fluctuation range of humidity can be calculated to more accurately describe the changes in the internal environment of the kitchenware.

[0064] Step 102, based on the internal environment data of the kitchen appliance and the operation control parameters of the PID controller in the current time period, a preset optimization control model is used to predict the operation control parameters of the PID controller in the next time period, wherein the operation control parameters in the next time period are related to the change trend of the internal environment data in the current time period, and are optimized evaluation values ​​when the PID controller controls the heating power of the heating element in the kitchen appliance while maintaining the internal temperature of the kitchen appliance at a target constant value.

[0065] Specifically, the optimization control model is a reinforcement learning model, that is, a model obtained by training a reinforcement learning algorithm to obtain the operation control parameters of the PID controller according to the change trend of the internal environment data. In some examples, the change trend of the internal environment data includes a temperature change trend, which is a temperature change in the future time or the next period of time.

[0066] In this embodiment, the PID controller can be set in the kitchenware, or the PID controller can be externally connected to the kitchenware to control the temperature of the kitchenware. During the cooking process, the operation control parameters of the PID controller in the current period are obtained, and the internal environment data of the kitchenware and the operation control parameters of the PID controller in the current period are input into the optimization control model for operation. Since the optimization control model is used to obtain the operation control parameters of the PID controller through the change trend of the internal environment data, the operation control parameters of the PID controller in the next period are predicted after the operation. In some examples, based on the internal environment data of the kitchenware and the operation control parameters of the PID controller at the current time point, the operation control parameters of the PID controller at the next time point are predicted using a preset optimization control model. It should be understood that when predicting the operation control parameters, it is not necessarily necessary to completely process the operation control parameters of a certain period, and it mainly refers to the operation control parameters at the current time and the operation control parameters at the future time.

[0067] In this embodiment, the operating control parameters of the PID controller include a proportional coefficient, an integral coefficient and a differential coefficient. The proportional coefficient (P), integral coefficient (I) and differential coefficient (D) of the PID controller are predicted by optimizing the control model to find the operating control parameters that best suit the current cooking task, thereby achieving precise temperature control and keeping the temperature of the kitchenware constant, thereby allowing the kitchenware to operate at a constant temperature with the lowest energy consumption and avoiding unnecessary energy waste.

[0068] Step 103: Update the operation control parameters of the PID controller to the operation control parameters of the next period.

[0069] Specifically, the operation control parameters of the next period are the operation control parameters that are most suitable for the current cooking task, which are used to adjust the heating power of the kitchenware heating element to keep the temperature constant. Therefore, after the operation control parameters of the next period are predicted, the operation control parameters of the PID controller in the current period are updated to the operation control parameters of the next period to dynamically adjust the operation control parameters of the PID controller.

[0070] Step 104 : Using the PID controller with the updated operation control parameters to control the heating power of the heating element in the kitchen appliance, so that the internal temperature of the kitchen appliance is maintained at a target constant value.

[0071] Specifically, the smart kitchenware is a kitchenware controlled by temperature, and a heating element is provided in the kitchenware to output heating power so as to adjust the heating temperature for cooking the ingredients. After the PID controller is updated based on the operation control parameters of the next period, the heating power of the heating element is controlled by the updated PID controller so that the internal temperature of the kitchenware is maintained at a target constant value. Among them, the internal temperature of the kitchenware can be maintained at a target constant value by controlling the temperature adjustment mode, and the temperature adjustment mode can be understood as a temperature control strategy, which can achieve precise temperature control so that the kitchenware keeps the temperature constant, so that the kitchenware runs at the lowest energy consumption under a constant temperature state, avoids unnecessary energy waste, achieves constant temperature energy saving, and improves energy efficiency. In some examples, the operation control parameters of the PID controller for the next period are predicted based on the change trend of the internal environment data by using the optimization control model, and the heating power of the heating element in the kitchenware is controlled based on the PID controller updated by the operation control parameters to keep the temperature constant, so that the kitchenware can react in advance and avoid adjusting the kitchenware when the environment has changed significantly.

[0072] In some examples, the internal environment data of the kitchenware is obtained in real time. As time changes, the operating control parameters of the PID controller are continuously optimized, so that the kitchenware can operate at a constant temperature with the lowest energy consumption. In addition, the heating power can be controlled by controlling the heating power of the heating element. In some examples, the kitchenware is equipped with a display screen, and the user can set the baking parameters through the display screen and view the baking progress and energy consumption information of the kitchenware for the ingredients.

[0073] In this embodiment, based on the internal environment data of the kitchenware and the operation control parameters of the PID controller in the current period, the operation control parameters of the PID controller in the next period are predicted using a preset optimization control model, and the operation control parameters of the PID controller are updated as the operation control parameters of the next period, and then the PID controller after the operation control parameters are updated is used to control the heating power of the heating element in the kitchenware so that the internal temperature of the kitchenware is maintained at a target constant value. In this way, the operation control parameters of the PID controller are dynamically adjusted according to the change trend of the internal environment of the kitchenware to accurately control the heating temperature of the heating element in the kitchenware, so that the kitchenware is in a constant temperature state, and there is no need to constantly adjust the heating temperature of the heating element, so that the kitchenware operates with the lowest energy consumption in a constant temperature state, avoiding unnecessary energy waste, achieving constant temperature energy saving, improving energy utilization efficiency, and saving energy and protecting the environment.

[0074] In some embodiments, the optimization control model includes a prediction model unit and an optimization model unit;

[0075] Based on the internal environment data of the kitchen appliance and the operation control parameters of the PID controller in the current period, the operation control parameters of the PID controller in the next period are predicted using a preset optimization control model, including:

[0076] Based on the internal environment data of the kitchenware, the temperature change parameters of the kitchenware in the next period are predicted by the prediction model unit;

[0077] Based on the temperature change parameter and the operation control parameter of the PID controller in the current period, the operation control parameter of the PID controller in the next period is determined by optimizing the model unit.

[0078] Specifically, the optimization control model includes a prediction model unit and an optimization model unit, and the prediction model unit and the optimization model unit work in series, that is, the prediction model unit is used to predict the temperature change parameters of the kitchenware in the next period according to the internal environment data of the kitchenware, and then the operation control parameters of the PID controller in the next period are determined by the optimization model unit based on the temperature change parameters and the operation control parameters of the PID controller in the current period. Among them, the temperature change parameters are used to characterize the temperature change trend of the kitchenware in the next period, and the temperature change parameters include at least one of the temperature value, temperature change curve, and temperature change rate of the next period. The operation control parameters of the PID controller are dynamically adjusted according to the temperature change parameters of the kitchenware in the next period, so as to accurately control the heating temperature of the heating element in the kitchenware, so that the kitchenware is in a constant temperature state, and there is no need to constantly adjust the heating temperature of the heating element, so that the kitchenware can operate with the lowest energy consumption in a constant temperature state.

[0079] In some examples, the operating control parameters of the PID controller for the current period are set to P_{current}, I_{current}, and D_{current}, and the operating control parameters of the next period output by the optimization control model are set to P_{new}, I_{new}, and D_{new}, by updating the operating control parameters of the PID controller to the operating control parameters of the next period: P_{current}=P_{new}, I_{current}=I_{new}, and D_{current}=D_{new}. The PID controller after the running control parameters are updated outputs the control signal through the following relationship: u(t)=P_{\text{new}}\cdot e(t)+I_{\text{new}}\cdot\int e(t),dt+D_{\text{new}}\cdot\frac{de(t)}{dt}, where (e(t)) is the error between the current temperature and the target temperature, (u(t)) is the control output, (P_{\text{new}}) is the new proportional gain, (I_{\text{new}}) is the new integral gain, (D_{\text{new}}) is the new differential gain, (\int e(t),dt) represents the integral of the error, (\frac{de(t)}{dt}) represents the differential of the error, and in the formula, (\cdot) represents a multiplication operation. The output (u(t)) of the PID controller is a comprehensive control signal. By adjusting the control signal, the input of the system (such as heating power) can be directly controlled, thereby achieving precise control of the system state (such as heating temperature). In some examples, the heating power of the heating element adjusted by the control signal can be calculated by the following relationship: [Power(t)=f(u(t))], where Power(t) is the heating power of the heating element, u(t)) is the control signal, and (f(u(t))) is a function that converts the control output into the actual heating power.

[0080] In some embodiments, the optimized control model is obtained by the following steps:

[0081] Build the original model;

[0082] The original model is trained using a reinforcement learning algorithm for the internal environment data samples obtained in multiple time periods and the corresponding operation control parameter samples of the PID controller to obtain an optimized control model.

[0083] Specifically, the original model can be constructed through reinforcement learning algorithms such as deep Q network (DQN) or asynchronous advantage actor critic (A3C), which can continuously learn and adjust strategies in the process of interaction with the environment to adapt to the dynamically changing environment. In addition, by collecting internal environmental data of multiple periods in history and the corresponding operating control parameters of the PID controller as training sample data, the original model is trained using a reinforcement learning algorithm to obtain an optimized control model.

[0084] In some examples, the initial PID parameters and the initial weights of the original model are set. The initial PID parameters can be determined by empirical methods and the Ziegler-Nichols method. The initial weights can be randomly initialized using Gaussian distribution and uniform distribution to avoid symmetry destruction, promote gradient propagation, and accelerate convergence. By taking environmental data and current PID parameters as states and new PID parameters as actions, a reward function is set in the original model. The reward function can be based on temperature stability, energy consumption, and baking effect, for example: reward = -(temperature fluctuation + energy consumption) + baking effect score. In the model training process: through repeated trial and error and learning, the original model continuously adjusts the weights to maximize the reward function, so that the constructed optimization control model is more accurate, so as to find the most suitable operating control parameters for the current cooking task and achieve accurate temperature control of the kitchenware.

[0085] In some embodiments, the original model includes: a prediction model training unit and an optimization model training unit;

[0086] The original model is trained using a reinforcement learning algorithm for the internal environment data samples obtained in multiple time periods and the corresponding operation control parameter samples of the PID controller to obtain an optimized control model, including:

[0087] Inputting the internal environment data samples of multiple time periods and the operation control parameter samples of the current time period into the prediction model training unit for training to predict the temperature change parameter samples of the kitchenware in the next time period;

[0088] The optimization model training unit is trained based on the temperature change parameter samples and the operation control parameter samples of the PID controller in two adjacent time periods to obtain the optimization control model.

[0089] Specifically, the original model includes a prediction model training unit and an optimization model training unit, and the prediction model training unit and the optimization model training unit also work in series, that is, the prediction model training unit is used to predict the temperature change parameter samples of the kitchenware in the next period according to the internal environment data samples of multiple periods and the operation control parameter samples of the current period, and then the optimization model unit is trained according to the temperature change parameter samples and the operation control parameter samples of the current period of the PID controller to obtain the corresponding operation control parameters of the next period of the PID controller, and the internal environment data samples, the operation control parameter samples of the current time, and the operation control parameters of the next period are in a one-to-one correspondence. The prediction model training unit and the optimization model training unit are trained so that the prediction model unit and the optimization model unit are obtained after training, thereby constructing an optimization control model.

[0090] In some embodiments, the method further comprises:

[0091] Constructing a training sample library, wherein the training sample library is used to store internal environment data samples, operation control parameter samples of the current period, and operation control parameter samples of the next period;

[0092] Based on the internal environment data of the kitchen appliance and the operation control parameters of the PID controller in the current period, after predicting the operation control parameters of the PID controller in the next period by using a preset optimization control model, the method further includes:

[0093] The predicted operation control parameters of the PID controller for the next period, the corresponding internal environment data and the operation control parameters of the PID controller for the current period are added to the training sample library to provide the samples required for the original model optimization training.

[0094] Specifically, based on the internal environment data of the kitchenware and the operation control parameters of the PID controller in the current period, the operation control parameters of the PID controller in the next period are predicted using a preset optimization control model, and the operation control parameters of the PID controller are updated to the operation control parameters of the next period. The PID controller after the operation control parameters are updated controls the temperature of the heating element in the kitchenware, so that the kitchenware operates with the lowest energy consumption. At this time, the predicted operation control parameters of the PID controller in the next period and the corresponding internal environment data and the operation control parameters of the PID controller in the current period are added to the training sample library to expand the sample size of the training sample library, increase the data volume of the training sample data, and thus improve the accuracy of the adjustment of the operation control parameters.

[0095] In some embodiments, the internal environment data includes temperature, humidity, air pressure, etc.;

[0096] The method also includes:

[0097] Based on the internal environment data of the kitchen appliance, detecting whether the humidity value of the kitchen appliance is greater than a preset humidity threshold;

[0098] When the humidity value of the kitchenware is greater than the preset humidity threshold, the dehumidification control task is started;

[0099] The dehumidification device controlling the kitchen appliance performs the dehumidification control task.

[0100] Specifically, the internal environmental data of the kitchenware includes temperature, humidity, air pressure, etc. When the kitchenware is prone to water accumulation during use, the humidity changes inside the kitchenware are monitored in real time through the environmental perception module, and the humidity value of the kitchenware is detected in real time whether it is greater than the preset humidity threshold. When the humidity value of the kitchenware is greater than the preset humidity threshold, the dehumidification control task is started, and the dehumidification device of the kitchenware is controlled to perform the dehumidification control task. In some examples, the dehumidification device can be a heating element or a ventilation element. The dehumidification control task includes enhancing ventilation (adjusting the ventilation settings of the oven, increasing the ventilation volume, and promoting the discharge of moisture inside the oven), adjusting the baking mode (such as optimizing the temperature curve, changing the working mode of the heating element), extending the preheating time or increasing intermittent baking, etc., to reduce the accumulation of moisture inside the oven, ensure the baking effect while keeping the oven dry and clean.

[0101] In some embodiments, the method further comprises:

[0102] Based on the humidity value of the kitchenware, the temperature change parameter is determined by the prediction model unit;

[0103] Based on the temperature variation parameter, a temperature adjustment mode is selected from a plurality of preset temperature adjustment modes as the temperature adjustment mode followed by the PID controller after the operation control parameters are updated to control the heating temperature of the heating element in the kitchen appliance.

[0104] Specifically, after obtaining the humidity value of the kitchenware, the temperature change parameter is determined by the prediction model unit, and the temperature change parameter here is used to reduce the humidity value in the kitchenware. The temperature adjustment mode includes adjusting the working mode of the heating element, adjusting the baking time (such as extending or shortening the baking time, or using intermittent baking), etc. Based on the temperature change parameter, a temperature adjustment mode is selected from a plurality of preset temperature adjustment modes as the temperature adjustment mode followed by the PID controller after the operation control parameter is updated to control the heating temperature of the heating element in the kitchenware, so as to adjust the baking mode and baking time in time according to the water accumulation situation, so as to ensure the baking effect while reducing the water accumulation.

[0105] Embodiment 2:

[0106] like Figure 4 As shown, this embodiment provides exemplary content of the first embodiment, that is, provides an exemplary process of the intelligent kitchenware temperature control method, and the specific content includes:

[0107] The reinforcement learning module uses advanced reinforcement learning algorithms, such as Deep Q Network (DQN) or Asynchronous Advantage Actor Critic (A3C), to achieve continuous optimization of the oven temperature control strategy. Through continuous trial and error and learning, the reinforcement learning module can gradually understand and predict the changing trend of the oven's internal environment, and then generate the optimal temperature control strategy.

[0108] Secondly, in order to obtain real-time information about the internal environment of the oven, the system is equipped with a high-precision environmental perception module. This module integrates multiple sensors such as temperature sensors and humidity sensors, which can monitor key parameters such as temperature and humidity inside the oven in real time, and transmit the data in real time to the reinforcement learning module for analysis and processing.

[0109] In the implementation of temperature control strategy, the system uses an advanced PID controller. Unlike traditional PID controllers, the PID controller parameters of this system are not fixed, but are dynamically adjusted by the optimization logic processing module according to the output of the reinforcement learning module. In this way, the system can automatically adjust the heating power and temperature setting values ​​according to the needs of different foods and baking conditions to achieve precise temperature control.

[0110] In addition, in order to reduce the energy consumption of the oven under constant temperature, the system also introduces energy-saving strategies. When the oven reaches the set temperature and remains stable, the system automatically reduces the heating power to reduce unnecessary energy consumption. At the same time, the system will also predict and adjust the heating power in advance according to the changing trend of the oven's internal environment to keep the temperature constant.

[0111] 1. Water accumulation optimization

[0112] In view of the problem that the oven is prone to water accumulation during use, this system uses the environmental perception module to monitor the humidity changes inside the oven in real time. When the humidity exceeds the preset threshold, the system will start the water accumulation optimization strategy. This strategy includes adjusting the ventilation settings of the oven, increasing the ventilation volume, and promoting the discharge of moisture inside the oven; at the same time, the system will adjust the baking mode and time in time according to the water accumulation situation to ensure the baking effect while reducing the accumulation of water. When the humidity inside the oven exceeds the preset threshold, the accumulation of moisture inside the oven is reduced by enhancing ventilation, adjusting the baking mode (such as optimizing the temperature curve, changing the working mode of the heating element), extending the preheating time or increasing intermittent baking, etc., to ensure the baking effect while keeping the oven dry and clean. In addition, it may also include intelligent reminders to users to pay attention to water accumulation, give corresponding operation suggestions, and use self-cleaning and drainage functions to further maintain the internal environment of the oven.

[0113] 2. Constant temperature and energy saving

[0114] In order to achieve the goal of constant temperature and energy saving, this system uses a reinforcement learning algorithm to dynamically adjust the parameters of the PID controller. Through continuous learning and optimization, the system can find the PID parameter combination that best suits the current baking task, ensuring that the oven can operate at the lowest energy consumption under a constant temperature state. In addition, the system will predict and adjust the heating power in advance according to the changing trend of the internal temperature of the oven to avoid unnecessary energy waste. The system continuously collects oven operation data and uses a reinforcement learning algorithm to learn how to adjust the parameters (P, I, D values) of the PID controller according to the current state (such as temperature and energy consumption) to maximize the constant temperature and energy saving effect. This process is real-time. With the accumulation and learning of data, the PID parameters will gradually be optimized, so that the oven can operate at the lowest energy consumption under a constant temperature state.

[0115] The optimized control model is constructed by the reinforcement learning algorithm. The input parameters are: environmental data: temperature, humidity, air pressure and other data inside the oven; current state: current PID controller parameters (P, I, D); historical data: environmental data and controller output signals collected during the previous baking processes, where the controller output signal is the control signal, which refers to the control signal or control output value of the PID controller at each time step. Specifically, the output of the PID controller is a control signal calculated based on the current temperature error (i.e., the difference between the current temperature and the target temperature). This signal is used to adjust the heating power of the oven so that the temperature reaches and remains at the target value as soon as possible, where the target temperature is the predicted temperature value for the next period of time. The output parameters are: temperature change trend: predicted future temperature change (the predicted future temperature change can be the temperature value at a specific time point, the temperature change curve, or the temperature change rate, the specific form depends on the actual application requirements), new PID controller parameters (P, I, D). When choosing a reinforcement learning algorithm, you can choose a reinforcement learning algorithm such as a deep Q network (DQN) or an asynchronous advantage actor-critic (A3C).

[0116] Specifically, the internal environment data is collected and preprocessed: Data collection: The temperature, humidity, and air pressure data in the oven are collected in real time through the environment perception module. Data preprocessing: The collected data is normalized so that it can be input into the reinforcement learning algorithm.

[0117] Train the original model to obtain the optimized control model: Initialize the original model: set the initial PID parameters and the initial weights of the reinforcement learning model. State-action pair: take the internal environment data and the current PID parameters (i.e., the operating control parameters of the current period) as the state, and the new PID parameters (i.e., the operating control parameters of the next period) as the action. Reward mechanism: Set the reward function, which can be based on temperature stability, energy consumption, and baking effect. For example: reward = -(temperature fluctuation + energy consumption) + baking effect score. Training process: Through repeated trial and error and learning, the model continuously adjusts the weights to maximize the reward function.

[0118] By inputting the current PID parameters and internal environmental parameters into the optimization control model, the optimized PID parameters (P, I, D) are output, that is, the proportional (P), integral (I) and differential (D) coefficients of the current PID controller are dynamically adjusted. Predict future temperature changes so that the control strategy can be adjusted in advance, that is, the operating control parameters of the PID controller are dynamically adjusted according to the changing trend of the internal environment of the kitchenware, so as to accurately control the heating temperature of the heating element in the kitchenware, so that the kitchenware is in a constant temperature state, and there is no need to constantly adjust the heating temperature of the heating element, so that the kitchenware can operate at the lowest energy consumption under the constant temperature state, avoiding unnecessary energy waste, achieving constant temperature energy saving, improving energy utilization efficiency, and saving energy and protecting the environment.

[0119] When updating the parameters of the PID controller, the following steps are performed: Read the current environmental data: Get the current temperature, humidity, air pressure and other data. Input the reinforcement learning model: Input the current environmental data into the trained reinforcement learning model. Get new PID parameters: The model outputs new PID parameters (P, I, D). Update the PID controller: Apply the new PID parameters to the PID controller. Assume that the current PID parameters are P_{current}, I_{current}, D_{current}), and the optimization control model outputs new PID parameters P_{new}, I_{new}, D_{new}; PID controller update formula: P_{current}=P_{new}][I_{current}=I_{new}][D_{current}=D_{new}. The PID controller calculates the current control output signal according to the new PID parameters: u(t)=P_{new}\cdot e(t)+I_{new}\cdot\int e(t),dt+D_{new}\cdot\frac{de(t)}{dt}, where (e(t)) is the error between the current temperature and the target temperature, (u(t)) is the control output, (P_{\text{new}}) is the new proportional gain, (I_{\text{new}}) is the new integral gain, (D_{\text{new}}) is the new differential gain, (\int e(t),dt) represents the integral of the error, (\frac{de(t)}{dt}) represents the differential of the error, and in the formula, (\cdot) represents a multiplication operation. The output (u(t)) of the PID controller is a comprehensive control signal. By adjusting this signal, the input of the system (such as heating power) can be directly controlled, thereby achieving precise control of the system state (such as heating temperature). The control signal is calculated based on the current error, cumulative error and error change rate, so that the system can respond quickly and stabilize near the set value.

[0120] After obtaining the control signal of the PID controller based on the new PID parameters, the power of the heating element is adjusted according to the control signal (u(t)) of the PID controller: Power(t) = f(u(t)), wherein Power(t) is the heating power of the heating element, u(t)) is the control signal, and (f(u(t))) is a function that converts the control output into actual heating power.

[0121] 3.PID logic optimization

[0122] Traditional PID control algorithms often show certain limitations when dealing with complex environments. To overcome this problem, this system optimizes the PID logic. By introducing a reinforcement learning algorithm, the system can analyze the changing trends of the oven's internal environment in real time and dynamically adjust the parameters of the PID controller based on these trends. This adaptive PID logic enables the system to better adapt to the needs of different foods and baking conditions, achieving more accurate and stable temperature control.

[0123] In summary, in this embodiment, significant improvements in oven temperature control are achieved by optimizing water accumulation, constant temperature energy saving, and PID logic. This system not only improves the baking effect of the oven and reduces energy consumption, but also brings a more convenient and intelligent user experience to users.

[0124] Embodiment three:

[0125] Another embodiment of the present application relates to an intelligent kitchen temperature control device. The implementation details of the intelligent kitchen temperature control device of this embodiment are specifically described below. The following content is only for the convenience of understanding the implementation details, and is not necessary for the implementation of this solution. The schematic diagram of the intelligent kitchen temperature control device of this embodiment can be as follows Figure 2 As shown, including:

[0126] An acquisition module 201 is used to acquire internal environment data of the kitchenware;

[0127] a parameter prediction module 202, for predicting the operation control parameters of the PID controller in the next period of time by using a preset optimization control model based on the internal environment data of the kitchen appliance and the operation control parameters of the PID controller in the current period of time, wherein the operation control parameters in the next period of time are related to the change trend of the internal environment data in the current period of time, and are the optimized evaluation values ​​when the PID controller controls the heating power of the heating element in the kitchen appliance while maintaining the internal temperature of the kitchen appliance at a target constant value;

[0128] An operation update module 203 is used to update the operation control parameters of the PID controller to the operation control parameters of the next period;

[0129] The control module 204 is used to control the heating power of the heating element in the kitchen appliance by using the PID controller with the updated operation control parameters, so that the internal temperature of the kitchen appliance is maintained at a target constant value.

[0130] It is worth mentioning that all modules involved in this embodiment are logic modules. In practical applications, a logic unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. In addition, in order to highlight the innovative part of this application, this embodiment does not introduce units that are not closely related to solving the technical problems proposed by this application, but this does not mean that there are no other units in this embodiment.

[0131] Embodiment 4:

[0132] Another embodiment of the present application relates to an electronic device, such as Figure 3 As shown, it includes: at least one processor 901; and a memory 902 that is communicatively connected to the at least one processor 901; wherein the memory 902 stores instructions that can be executed by the at least one processor 901, and the instructions are executed by the at least one processor 901 so that the at least one processor 901 can execute the intelligent kitchen appliance temperature control method in the above-mentioned embodiments.

[0133] Among them, the memory and the processor are connected in a bus manner, and the bus may include any number of interconnected buses and bridges, and the bus connects various circuits of one or more processors and memories together. The bus can also connect various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be one element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on a transmission medium. The data processed by the processor is transmitted on a wireless medium via an antenna, and further, the antenna also receives data and transmits the data to the processor.

[0134] The processor is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory can be used to store data used by the processor when performing operations.

[0135] Embodiment five:

[0136] Another embodiment of the present application relates to a computer-readable storage medium storing a computer program, which implements the above method embodiment when executed by a processor.

[0137] That is, those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including a number of instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as: ROM), random access memory (Random Access Memory, referred to as: RAM), disk or optical disk and other media that can store program codes.

[0138] Those skilled in the art will appreciate that the above embodiments are specific embodiments for implementing the present application, and in actual applications, various changes may be made thereto in form and detail without departing from the spirit and scope of the present application.

Claims

1. A method for controlling temperature of intelligent kitchenware, characterized in that: The smart kitchen appliance is a kitchen appliance controlled by temperature, and the method comprises: Obtain the internal environment data of the kitchenware; Based on the internal environment data of the kitchen appliance and the operation control parameters of the PID controller in the current period, a preset optimization control model is used to predict the operation control parameters of the PID controller in the next period, wherein the operation control parameters in the next period are related to the change trend of the internal environment data in the current period, and are optimized evaluation values ​​when the PID controller controls the heating power of the heating element in the kitchen appliance while maintaining the internal temperature of the kitchen appliance at a target constant value; Updating the operation control parameters of the PID controller to the operation control parameters of the next time period; The PID controller after the operation control parameter is updated is used to control the heating power of the heating element in the kitchen appliance so that the internal temperature of the kitchen appliance is maintained at the target constant value.

2. The intelligent kitchenware temperature control method according to claim 1, characterized in that: The optimization control model includes a prediction model unit and an optimization model unit; The method of predicting the operation control parameters of the PID controller in the next period of time based on the internal environment data of the kitchen appliance and the operation control parameters of the PID controller in the current period of time by using a preset optimization control model includes: Based on the internal environment data of the kitchen appliance, predicting the temperature change parameter of the kitchen appliance in the next period of time by the prediction model unit; Based on the temperature change parameter and the operation control parameter of the PID controller in the current period, the operation control parameter of the PID controller in the next period is determined by the optimization model unit.

3. The intelligent kitchenware temperature control method according to claim 1, characterized in that: The optimization control model is obtained by the following steps: Build the original model; The original model is trained using a reinforcement learning algorithm for the internal environment data samples acquired in multiple time periods and the corresponding operation control parameter samples of the PID controller to obtain the optimized control model.

4. The intelligent kitchenware temperature control method according to claim 3, characterized in that: The original model includes: a prediction model training unit and an optimization model training unit; The internal environment data samples obtained in multiple time periods and the corresponding operation control parameter samples of the PID controller are trained on the original model using a reinforcement learning algorithm to obtain the optimized control model, including: Inputting the internal environment data samples of multiple time periods and the operation control parameter samples of the current time period into the prediction model training unit for training, so as to predict the temperature change parameter samples of the kitchenware in the next time period; The optimization model training unit is trained based on the temperature change parameter samples and the operation control parameter samples of two adjacent time periods of the PID controller to obtain the optimization control model.

5. The intelligent kitchenware temperature control method according to claim 3, characterized in that: The method further comprises: Constructing a training sample library, wherein the training sample library is used to store internal environment data samples, operation control parameter samples of the current period, and operation control parameter samples of the next period; After predicting the operation control parameters of the PID controller in the next period of time based on the internal environment data of the kitchen appliance and the operation control parameters of the PID controller in the current period of time by using a preset optimization control model, the method further includes: The predicted operation control parameters of the PID controller for the next period, the corresponding internal environment data and the operation control parameters of the PID controller for the current period are added to the training sample library to provide samples required for the optimization training of the original model.

6. The intelligent kitchenware temperature control method according to claim 2, characterized in that: The internal environment data includes temperature, humidity, air pressure, etc.; The method further comprises: Based on the internal environment data of the kitchen appliance, detecting whether the humidity value of the kitchen appliance is greater than a preset humidity threshold; When the humidity value of the kitchenware is greater than a preset humidity threshold, a dehumidification control task is started; The dehumidification device of the kitchen appliance is controlled to perform the dehumidification control task.

7. The intelligent kitchenware temperature control method according to claim 6, characterized in that: The method further comprises: Based on the humidity value of the kitchenware, determining the temperature change parameter by the prediction model unit; Based on the temperature change parameter, a temperature adjustment mode is selected from a plurality of preset temperature adjustment modes as the temperature adjustment mode followed by the PID controller to control the heating temperature of the heating element in the kitchen appliance after the operation control parameter is updated.

8. An intelligent kitchenware temperature control device, characterized in that: include: An acquisition module is used to obtain the internal environment data of the kitchenware; a parameter prediction module, configured to predict the operation control parameter of the PID controller in the next period of time by using a preset optimization control model based on the internal environment data of the kitchen appliance and the operation control parameter of the PID controller in the current period of time, wherein the operation control parameter of the next period of time is related to the change trend of the internal environment data in the current period of time, and is an optimized evaluation value when the PID controller controls the heating power of the heating element in the kitchen appliance while maintaining the internal temperature of the kitchen appliance at a target constant value; An operation update module, used for updating the operation control parameters of the PID controller to the operation control parameters of the next time period; A control module is used to control the heating power of the heating element in the kitchen appliance by using the PID controller after the operation control parameter is updated, so that the internal temperature of the kitchen appliance is maintained at the target constant value.

9. An electronic device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the intelligent kitchen appliance temperature control method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the intelligent kitchen appliance temperature control method according to any one of claims 1 to 7 is implemented.

Images