A temperature control method and device of a steam oven, the steam oven and a readable medium

Abstract

The embodiment of the application provides a temperature control method and device of a steam oven, the steam oven, a steam oven and a readable medium, which are applied to the steam oven, the steam oven comprising a variable-frequency heating device, the variable-frequency heating device being a graphene heating device and / or an eddy current variable heating device, a preset temperature sensor is used to collect a current temperature of the steam oven; a preset current sensor and a voltage sensor are used to collect a working current and a working voltage of the variable-frequency heating device respectively; based on the current temperature, the working current, the working voltage and a preset target temperature of the steam oven, a preset control strategy generation model is used to obtain a power control strategy of the variable-frequency heating device; based on the power control strategy, the current temperature of the steam oven is changed into the target temperature by adjusting the output power of the variable-frequency heating device, the current temperature of the steam oven can be changed into the target temperature, and the steam oven is controlled to perform constant-temperature operation according to the target temperature.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of steam ovens, and in particular to a temperature control method of a steam oven, a temperature control device of a steam oven, a steam oven and a computer readable medium. BACKGROUND

[0002] In related technologies, a steam oven usually adopts a PID (Proportional-Integral-Derivative) control algorithm for temperature control. However, the PID control algorithm is difficult to make the steam oven maintain a constant temperature for a long time to ensure cooking quality. SUMMARY

[0003] Embodiments of the present application provide a temperature control method and device of a steam oven, a steam oven and a computer readable storage medium to solve the problem that the PID control algorithm is difficult to make the steam oven maintain a constant temperature for a long time to ensure cooking quality.

[0004] Embodiments of the present application disclose a temperature control method of a steam oven, applied to a steam oven, the steam oven comprising a variable frequency heating device, the variable frequency heating device being a graphene heating device and / or an eddy current variable heating device, and the method comprising:

[0005] acquiring a current temperature of the steam oven by using a preset temperature sensor;

[0006] acquiring a working current and a working voltage of the variable frequency heating device by using a preset current sensor and a voltage sensor respectively;

[0007] generating a power control strategy of the variable frequency heating device by using a preset control strategy generation model based on the current temperature, the working current, the working voltage and a preset target temperature of the steam oven;

[0008] based on the power control strategy, converting the current temperature of the steam oven into the target temperature by adjusting an output power of the variable frequency heating device.

[0009] Optionally, the generating of the power control strategy of the variable frequency heating device by using the preset control strategy generation model based on the current temperature, the working current, the working voltage and the preset target temperature of the steam oven comprises:

[0010] acquiring a current power of the variable frequency heating device by using the working current and the working voltage;

[0011] inputting the current temperature, the current power and the target temperature into the control strategy generation model to obtain the power control strategy of the variable frequency heating device.

[0012] Optionally, the method comprises:

[0013] obtaining a training current temperature, a training target temperature of the steam oven, a training current frequency of the variable frequency heating device, and a training power control strategy for converting the training current temperature to the training target temperature;

[0014] training a preset machine learning model by using the training current temperature, the training target temperature, the training current frequency, and the training power control strategy, to obtain the control strategy generation model.

[0015] Optionally, the training of the preset machine learning model by using the training current temperature, the training target temperature, the training current frequency, and the training power control strategy, to obtain the control strategy generation model, comprises:

[0016] obtaining an inference power control strategy output by the machine learning model for the training current temperature, the training target temperature, and the training current frequency during the training process of the machine learning model;

[0017] obtaining at least one of a transition temperature, a transition speed, and a transition energy consumption corresponding to the inference power control strategy; the transition temperature is a temperature obtained by adjusting the output power of the variable frequency heating device by using the inference power control strategy, so that the training current temperature is changed; the transition speed is a speed at which the training current temperature is changed to the transition temperature; and the transition energy consumption is an energy consumption of the variable frequency heating device during the process of changing the training current temperature to the transition temperature;

[0018] training the machine learning model based on at least one of the transition temperature, the transition speed, and the transition energy consumption.

[0019] Optionally, the training of the machine learning model based on at least one of the transition temperature, the transition speed, and the transition energy consumption comprises:

[0020] if a difference between the transition temperature and the training target temperature is less than a preset difference threshold, providing a preset first reward for the machine learning model;

[0021] if the transition speed is higher than a preset speed threshold, providing a preset second reward for the machine learning model;

[0022] if the transition energy consumption is less than a preset energy consumption threshold, providing a preset third reward for the machine learning model;

[0023] training the machine learning model by using at least one of the first reward, the second reward, and the third reward.

[0024] Optionally, the training of the machine learning model by using at least one of the first reward, the second reward, and the third reward comprises:

[0025] The machine learning model is configured with preset temperature weight, speed weight, and energy consumption weight;

[0026] Based on the temperature weight, the first reward, the speed weight, the second reward, the energy consumption weight, and the third reward, the target reward of the machine learning model is obtained;

[0027] The machine learning model is trained by using the target reward.

[0028] Optionally, the conversion of the current temperature of the steaming oven to the target temperature by adjusting the output power of the variable frequency heating device comprises:

[0029] At least one of the to-be-processed temperature, the to-be-processed speed, and the to-be-processed energy consumption corresponding to the power control strategy is obtained; the to-be-processed temperature is the temperature obtained by adjusting the output power of the variable frequency heating device by using the power control strategy, so that the current temperature is converted; the to-be-processed speed is the speed of converting the current temperature to the to-be-processed temperature; and the to-be-processed energy consumption is the energy consumption of the variable frequency heating device in the process of converting the current temperature to the to-be-processed temperature.

[0030] The control strategy generation model is trained based on at least one of the to-be-processed temperature, the to-be-processed speed, and the to-be-processed energy consumption.

[0031] Optionally, the training of the control strategy generation model based on at least one of the to-be-processed temperature, the to-be-processed speed, and the to-be-processed energy consumption comprises:

[0032] Based on the to-be-processed temperature, the to-be-processed speed, and the to-be-processed energy consumption, at least one of the temperature weight, the speed weight, and the energy consumption weight is adjusted;

[0033] Based on at least one of the adjusted temperature weight, speed weight, and energy consumption weight, the reward in the training process of the control strategy generation model is obtained;

[0034] The control strategy generation model is trained by using the reward.

[0035] Optionally, the method comprises:

[0036] Based on the power control strategy, the on-off state of the graphene heating device and / or the eddy current heating device is adjusted.

[0037] The embodiment of the present application also discloses a temperature control device of a steam oven, which is applied to a steam oven, wherein the steam oven comprises a variable-frequency heating device, and the variable-frequency heating device is a graphene heating device and / or an eddy current variable heating device, and the device comprises:

[0038] a temperature collection module, which is used for collecting a current temperature of the steam oven by using a preset temperature sensor;

[0039] a voltage collection module, which is used for collecting a working current and a working voltage of the variable-frequency heating device by using a preset current sensor and a preset voltage sensor respectively;

[0040] a strategy obtaining module, which is used for obtaining a power control strategy of the variable-frequency heating device by using a preset control strategy generation model based on the current temperature, the working current, the working voltage and a preset target temperature of the steam oven;

[0041] a power adjustment module, which is used for converting the current temperature of the steam oven into the target temperature by adjusting an output power of the variable-frequency heating device based on the power control strategy.

[0042] Optionally, the strategy obtaining module comprises:

[0043] a frequency obtaining sub-module, which is used for obtaining a current power of the variable-frequency heating device by using the working current and the working voltage;

[0044] a strategy obtaining sub-module, which is used for inputting the current temperature, the current power and the target temperature into the control strategy generation model to obtain the power control strategy of the variable-frequency heating device.

[0045] Optionally, the device comprises:

[0046] a training data obtaining module, which is used for obtaining a training current temperature of the steam oven, a training target temperature, a training current frequency of the variable-frequency heating device and a training power control strategy for converting the training current temperature into the training target temperature;

[0047] a training module, which is used for training a preset machine learning model by using the training current temperature, the training target temperature, the training current frequency and the training power control strategy to obtain the control strategy generation model.

[0048] Optionally, the training module comprises:

[0049] The inference power control strategy obtaining submodule is configured to obtain an inference power control strategy output by the machine learning model for the training current temperature, the training target temperature, and the training current frequency during a training process of the machine learning model.

[0050] The transition temperature obtaining submodule is configured to obtain at least one of a transition temperature, a transition speed, and a transition energy consumption corresponding to the inference power control strategy; the transition temperature is a temperature obtained by adjusting an output power of the variable-frequency heating device by using the inference power control strategy, so that the training current temperature is transitioned; the transition speed is a speed at which the training current temperature is transitioned to the transition temperature; and the transition energy consumption is an energy consumption of the variable-frequency heating device in a process in which the training current temperature is transitioned to the transition temperature.

[0051] The training submodule is configured to train the machine learning model based on at least one of the transition temperature, the transition speed, and the transition energy consumption.

[0052] Optionally, the training submodule includes:

[0053] The first reward providing unit is configured to provide a preset first reward for the machine learning model if a difference between the transition temperature and the training target temperature is less than a preset difference threshold.

[0054] The second reward providing unit is configured to provide a preset second reward for the machine learning model if the transition speed is higher than a preset speed threshold.

[0055] The third reward providing unit is configured to provide a preset third reward for the machine learning model if the transition energy consumption is less than a preset energy consumption threshold.

[0056] The training unit is configured to train the machine learning model by using at least one of the first reward, the second reward, and the third reward.

[0057] Optionally, the training unit includes:

[0058] The weight configuring subunit is configured to configure preset temperature weights, speed weights, and energy consumption weights for the machine learning model.

[0059] The target reward obtaining subunit is configured to obtain a target reward of the machine learning model based on the temperature weights, the first reward, the speed weights, the second reward, the energy consumption weights, and the third reward.

[0060] The training subunit is configured to train the machine learning model by using the target reward.

[0061] Optionally, the power adjusting module includes:

[0062] a to-be-processed temperature obtaining submodule, configured to obtain at least one of a to-be-processed temperature, a to-be-processed speed and a to-be-processed energy consumption corresponding to the power control strategy; the to-be-processed temperature is a temperature obtained by adjusting an output power of the variable-frequency heating device by using the power control strategy, so that the current temperature is changed; the to-be-processed speed is a speed at which the current temperature is changed to the to-be-processed temperature; and the to-be-processed energy consumption is an energy consumption of the variable-frequency heating device in a process in which the current temperature is changed to the to-be-processed temperature;

[0063] a control strategy generation model training submodule, configured to train the control strategy generation model based on at least one of the to-be-processed temperature, the to-be-processed speed and the to-be-processed energy consumption.

[0064] Optionally, the control strategy generation model training submodule comprises:

[0065] a weight adjusting unit, configured to adjust at least one of the temperature weight, the speed weight and the energy consumption weight based on the to-be-processed temperature, the to-be-processed speed and the to-be-processed energy consumption;

[0066] a reward obtaining unit, configured to obtain a reward in a training process of the control strategy generation model based on at least one of the temperature weight, the speed weight and the energy consumption weight after the adjustment;

[0067] a control strategy generation model training unit, configured to train the control strategy generation model by using the reward.

[0068] Optionally, the device comprises:

[0069] a switch state adjusting module, configured to adjust a switch state of the graphene heating device and / or the eddy current variable heating device based on the power control strategy.

[0070] The embodiment of the present application further discloses a steaming oven, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete mutual communication through the communication bus;

[0071] The memory is used for storing a computer program.

[0072] The processor is used for executing the program stored on the memory, and realizes the method as described in the embodiment of the present application.

[0073] The embodiment of the present application further discloses one or more computer readable media, which store instructions, and when executed by one or more processors, make the processor execute the method as described in the embodiment of the present application.

[0074] Embodiments of the present application include the following advantages:

[0075] In embodiments of the present application, the steam oven includes a variable frequency heating device, which is a graphene heating device and / or an eddy current variable heating device. A preset temperature sensor is used to collect the current temperature of the steam oven, and a preset current sensor and a voltage sensor are used to collect the working current and working voltage of the variable frequency heating device, respectively. Based on the current temperature, working current, working voltage and preset target temperature of the steam oven, a preset control strategy generation model is used to obtain a power control strategy of the variable frequency heating device; based on the power control strategy, the output power of the variable frequency heating device is adjusted to change the current temperature of the steam oven to the target temperature. By using the power control strategy output by the control strategy generation model and cooperating with the variable frequency heating device, the output power of the variable frequency heating device can be adjusted to change the current temperature of the steam oven to the target temperature, and the steam oven can be controlled to operate at a constant temperature according to the target temperature. BRIEF DESCRIPTION OF DRAWINGS

[0076] Figure 1 is a step flow chart of a temperature control method of a steam oven provided in embodiments of the present application;

[0077] Figure 2 is a step flow chart of another temperature control method of a steam oven provided in embodiments of the present application;

[0078] Figure 3 is a structural block diagram of a temperature control device of a steam oven provided in embodiments of the present application;

[0079] Figure 4 is a block diagram of a steam oven provided in embodiments of the present application;

[0080] Figure 5 is a schematic diagram of a computer readable medium provided in embodiments of the present application. DETAILED DESCRIPTION

[0081] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application will be further described in detail below with reference to the drawings and specific embodiments.

[0082] In order to facilitate understanding of the technical solutions and technical effects of embodiments of the present application, the related technologies of the present application will be briefly described below.

[0083] With the increasing demand for cooking quality in modern families, as an integrated and intelligent kitchen appliance, the steam oven has gradually been popularized. In the related art, the steam oven usually adopts a PID (Proportional-Integral-Derivative) control algorithm for temperature control. When the PID control algorithm is used for temperature control, the relative stability of the temperature is achieved to some extent. However, in the face of complex and changeable cooking environment, the steam oven has problems of slow response speed, large overshoot and high energy consumption. The slow response speed means that the PID control algorithm does not respond quickly to temperature changes and cannot quickly adjust the temperature of the steam oven to the target temperature. The overshoot means that in the process of adjusting the temperature to the target temperature by the PID control algorithm, the temperature of the steam oven may first exceed the set target temperature and then fall back to the target temperature. The large overshoot means that the temperature of the steam oven will first exceed the target temperature by a large margin.

[0084] In addition, it is difficult for the PID control algorithm to keep the steam oven at a constant temperature for a long time to ensure the cooking quality. In the process of using the PID control algorithm to control the steam oven to keep a constant temperature for cooking, it is also difficult to maximize the use of energy.

[0085] Reference Figure 1 A step flowchart of a temperature control method of a steam oven is shown, which is applied to a steam oven, the steam oven comprising a variable frequency heating device, the variable frequency heating device being a graphene heating device and / or an eddy current variable heating device, and specifically can comprise the following steps:

[0086] Step 101, collecting the current temperature of the steam oven by using a preset temperature sensor;

[0087] In the embodiment of the present application, the steam oven comprises a variable frequency heating device, which can be a graphene heating device and / or an eddy current variable heating device. Therefore, the steam oven is a variable frequency oven.

[0088] In the embodiment of the present application, a temperature sensor, a humidity sensor and a current sensor can be arranged in the steam oven. The temperature sensor can collect the current temperature inside the steam oven, the humidity sensor can collect the current humidity inside the steam oven, and the current sensor can collect the current current inside the steam oven.

[0089] Step 102, collecting the working current and working voltage of the variable frequency heating device by using a preset current sensor and a voltage sensor, respectively;

[0090] In the embodiment of the present application, the temperature sensor, the current sensor and the voltage sensor can be arranged on the frequency conversion heating device of the steam oven. The temperature sensor can collect the working temperature of the frequency conversion heating device, the current sensor can collect the working current of the frequency conversion heating device, and the voltage sensor can collect the working voltage of the frequency conversion heating device. The working voltage and the working current can be multiplied to obtain the current power of the frequency conversion heating device. The data of the working temperature, the current power, the working current and the working voltage can reflect the real-time working state and the efficiency of the frequency conversion heating device. It should be noted that the data collection frequency of the sensors inside the steam oven and the sensors on the frequency conversion heating device can be reasonably set according to the working characteristics and control requirements of the steam oven, so as to ensure the real-time and accuracy of data collection. For example, data is collected once per second to quickly respond to environmental changes.

[0091] In step 103, based on the current temperature, the working current, the working voltage and the preset target temperature of the steam oven, a power control strategy of the frequency conversion heating device is generated by using a preset control strategy generation model.

[0092] In the embodiment of the present application, based on the current temperature, the preset target temperature, the working current and the working voltage of the frequency conversion heating device, a power control strategy of the frequency conversion heating device can be obtained by using a control strategy generation model.

[0093] In some embodiments of the present application, the power control strategy of the frequency conversion heating device is obtained by using the preset control strategy generation model based on the current temperature, the working current, the working voltage and the preset target temperature of the steam oven, including:

[0094] The current power of the frequency conversion heating device is obtained by using the working current and the working voltage.

[0095] The current temperature, the current power and the target temperature are input into the control strategy generation model to obtain the power control strategy of the frequency conversion heating device.

[0096] In the embodiment of the present application, the working voltage and the working current can be multiplied to obtain the current power of the frequency conversion heating device. If I represents the working current, V represents the working voltage, and P represents the current power, the power calculation formula of the current power is:

[0097] P = IV

[0098] In the embodiment of the present application, the current power of the frequency conversion heating device, the current temperature of the steam oven and the preset target temperature are input into the control strategy generation model to obtain the power control strategy of the frequency conversion heating device.

[0099] The current power of the variable frequency heating device, the current temperature and the preset target temperature of the steaming oven can be used as the state space input of the control strategy generation model. The design of the state space should fully consider the actual operation and control requirements of the steaming oven, and be used to predict and determine the next control strategy.

[0100] The power control strategy can be used as the action space output of the control strategy generation model. The design of the action space ensures that the steaming oven can achieve accurate temperature control. The action space output also includes the power adjustment range of the variable frequency heating device.

[0101] In some embodiments of the present application, the method comprises:

[0102] obtaining the training current temperature, the training target temperature, the training current frequency of the variable frequency heating device of the steaming oven, and the training power control strategy for converting the training current temperature into the training target temperature;

[0103] training the preset machine learning model using the training current temperature, the training target temperature, the training current frequency, and the training power control strategy to obtain the control strategy generation model.

[0104] In embodiments of the present application, the training current temperature, the training target temperature, the training current frequency of the variable frequency heating device, and the training power control strategy for converting the training current temperature into the training target temperature of the steaming oven can be obtained. It should be noted that these training data include simulation data and actual operation data of the steaming oven.

[0105] Then, the training data is preprocessed, such as filtering and denoising, to reduce noise interference and improve data quality. At the same time, the training data is normalized to adapt to the input requirements of the machine learning model. Then, the preprocessed training current temperature, training target temperature, training current frequency, and training power control strategy are used to train the preset machine learning model, and the control strategy generation model can be obtained. During the training process of the machine learning model, the model parameters and training strategies are constantly adjusted to improve the generalization ability and control performance of the model.

[0106] It should be noted that, according to the complexity and real-time requirements of the steaming oven temperature control, advanced reinforcement learning algorithms such as Deep Q-Networks (DQN) or Proximal Policy Optimization (PPO) can be used. These algorithms can perform well when dealing with continuous state and action space. The machine learning model embeds the reinforcement learning algorithm of Deep Q-Networks or Proximal Policy Optimization.

[0107] In a specific example, first, a virtual environment of the steam oven is constructed using simulation software to simulate different cooking scenarios and temperature changes. Then, the machine learning model is trained in the simulation environment by continuously adjusting the model parameters and training strategies to improve the performance of the power control strategy output by the machine learning model in temperature regulation, temperature regulation response speed, and energy consumption during temperature regulation.

[0108] Based on simulation training, the trained model can be verified on the actual steam oven. By real-time acquisition of the current temperature of the steam oven, the current power of the variable frequency heating device and other state parameters, and inputting these parameters into the model, the performance of the power control strategy output by the model in temperature regulation, temperature regulation speed and energy consumption during temperature regulation is observed. At the same time, the data of the model in actual operation are recorded, including the accuracy of temperature control, temperature regulation response speed and energy consumption and other indicators.

[0109] According to the verification results of the model on the actual steam oven, the parameters and training strategies of the model are adjusted. For example, the weights of the reward function can be adjusted to better balance the relationship between temperature control and energy consumption; the neural network structure of the model can be optimized to improve the generalization ability of the model; the data acquisition frequency and preprocessing method can also be adjusted to improve the accuracy and real-time performance of the data. These adjustments can be flexibly combined and optimized according to specific verification results and actual needs. Through continuous iteration of the above process, the performance of the power control strategy output by the model can be gradually optimized to achieve better constant temperature and energy saving effect on the actual steam oven.

[0110] In some embodiments of the present application, the training of the preset machine learning model using the training current temperature, the training target temperature, the training current frequency and the training power control strategy to obtain the control strategy generation model comprises:

[0111] In the training process of the machine learning model, an inference power control strategy output by the machine learning model for the training current temperature, the training target temperature and the training current frequency is obtained.

[0112] At least one of the transition temperature, the transition speed and the transition energy consumption corresponding to the inference power control strategy is obtained; the transition temperature is the temperature obtained by adjusting the output power of the variable frequency heating device using the inference power control strategy, so that the training current temperature is changed; the transition speed is the speed of the training current temperature changing to the transition temperature; the transition energy consumption is the energy consumption of the variable frequency heating device during the process of the training current temperature changing to the transition temperature.

[0113] train the machine learning model based on at least one of the transition temperature, the transition speed, and the transition energy consumption.

[0114] In the embodiments of the present application, during the training process of the machine learning model, a reasonable reward function can be designed to guide the training process of the machine learning model.

[0115] Specifically, an inference power control strategy output by the machine learning model for a training current temperature, a training target temperature, and a training current frequency can be obtained. Then, at least one of a transition temperature, a transition speed, and a transition energy consumption corresponding to the inference power control strategy is obtained. The transition temperature is a temperature obtained by adjusting the output power of the variable frequency heating device using the inference power control strategy, so that the training current temperature is changed. The transition speed is the speed of changing the training current temperature to the transition temperature. The transition energy consumption is the energy consumption of the variable frequency heating device during the process of changing the training current temperature to the transition temperature.

[0116] In the embodiments of the present application, the machine learning model can be trained based on at least one of the transition temperature, the transition speed, and the transition energy consumption.

[0117] In some embodiments of the present application, the training of the machine learning model based on at least one of the transition temperature, the transition speed, and the transition energy consumption includes:

[0118] If the difference between the transition temperature and the training target temperature is less than a preset difference threshold, a preset first reward is provided for the machine learning model;

[0119] If the transition speed is higher than a preset speed threshold, a preset second reward is provided for the machine learning model;

[0120] If the transition energy consumption is less than a preset energy consumption threshold, a preset third reward is provided for the machine learning model;

[0121] The machine learning model is trained using at least one of the first reward, the second reward, and the third reward.

[0122] In the embodiments of the present application, the machine learning model can be trained based on at least one of the transition temperature, the transition speed, and the transition energy consumption.

[0123] Specifically, if the difference between the transition temperature and the training target temperature is less than a preset difference threshold, a preset first reward is provided for the machine learning model; if the transition speed is higher than a preset speed threshold, a preset second reward is provided for the machine learning model; if the transition energy consumption is less than a preset energy consumption threshold, a preset third reward is provided for the machine learning model. At least one of the first reward, the second reward and the third reward can be used to train the machine learning model. The first reward, the second reward and the third reward can be set, adjusted and optimized according to specific control requirements and targets.

[0124] In a specific example, when the deviation between the transition temperature and the training target temperature is small, for example, within ±1℃ (Celsius), a higher reward is given to encourage the machine learning model to improve the accuracy of temperature control. When the variable frequency heating device is in a low power consumption state, for example, the transition energy consumption is lower than the preset energy consumption threshold, a certain reward is given to encourage the machine learning model to reduce energy consumption. When the response time of temperature regulation is short, for example, the time from temperature change to reaching the transition temperature is less than a certain set value, a reward can also be given to encourage the machine learning model to improve the response speed.

[0125] In some embodiments of the present application, the training of the machine learning model using at least one of the first reward, the second reward and the third reward comprises:

[0126] The preset temperature weight, speed weight and energy consumption weight are configured for the machine learning model.

[0127] Based on the temperature weight, the first reward, the speed weight, the second reward, the energy consumption weight and the third reward, a target reward of the machine learning model is obtained.

[0128] The machine learning model is trained using the target reward.

[0129] In embodiments of the present application, the machine learning model can be configured with preset temperature weight, speed weight and energy consumption weight. Then, based on the temperature weight, the first reward, the speed weight, the second reward, the energy consumption weight and the third reward, the target reward of the machine learning model can be obtained using a reward function.

[0130] The reward function can be:

[0131] R = W1*R1 + W2*R2 + W3*R3

[0132] Wherein, R is the target reward, W1 is the temperature weight, R1 is the first reward, W2 is the speed weight, R2 is the second reward, W3 is the energy consumption weight, and R3 is the third reward. The reward function fully considers the accuracy of temperature control, response speed and energy consumption, etc.

[0133] In the embodiments of the present application, the machine learning model can be trained by using the target reward.

[0134] In step 104, based on the power control strategy, the current temperature of the steam oven is converted to the target temperature by adjusting the output power of the variable frequency heating device.

[0135] In the embodiments of the present application, the power control strategy includes power adjustment instructions. According to the power adjustment instructions, the current temperature of the steam oven can be converted to the target temperature by adjusting the output power of the variable frequency heating device, and constant temperature control at the target temperature can be achieved.

[0136] In some embodiments of the present application, the method comprises:

[0137] Based on the power control strategy, the on-off state of the graphene heating device and / or the eddy current heating device is adjusted.

[0138] In the embodiments of the present application, the power control strategy includes adjustment instructions for the on-off state of the variable frequency heating device. According to the adjustment instructions for the on-off state of the variable frequency heating device, the on-off state of the graphene heating device and / or the eddy current heating device can be adjusted to convert the current temperature of the steam oven to the target temperature and achieve constant temperature control at the target temperature.

[0139] In some embodiments of the present application, the current temperature of the steam oven is converted to the target temperature by adjusting the output power of the variable frequency heating device, comprising:

[0140] At least one of the to-be-processed temperature, the to-be-processed speed and the to-be-processed energy consumption corresponding to the power control strategy is obtained; the to-be-processed temperature is the temperature obtained by adjusting the output power of the variable frequency heating device using the power control strategy so that the current temperature is converted; the to-be-processed speed is the speed at which the current temperature is converted to the to-be-processed temperature; and the to-be-processed energy consumption is the energy consumption of the variable frequency heating device during the process of converting the current temperature to the to-be-processed temperature.

[0141] Based on at least one of the to-be-processed temperature, the to-be-processed speed and the to-be-processed energy consumption, the control strategy generation model is trained.

[0142] In the embodiments of the present application, the training of the machine learning model for the steam oven is performed by the manufacturer of the steam oven. After the control strategy generation model is obtained by training the machine learning model, the steam oven can be run in the user's home. During the running of the steam oven in the user's home, the sensors in the steam oven and the sensors of the variable frequency heating device can continue to collect the data of the actual running of the steam oven, and input these data as feedback information into the control strategy generation model, to perform a new round of iteration optimization and training on the control strategy generation model, and through continuous trial and error and adjustment, the power control strategy output by the control strategy generation model gradually tends to be optimal.

[0143] In the embodiments of the present application, during the training of the control strategy generation model, the power control strategy output by the control strategy generation model can be obtained, and at least one of the to-be-processed temperature, the to-be-processed speed and the to-be-processed energy consumption corresponding to the power control strategy can be obtained. The to-be-processed temperature is the temperature obtained by adjusting the output power of the variable frequency heating device using the power control strategy, so that the current temperature is changed; the to-be-processed speed is the speed at which the current temperature changes to the to-be-processed temperature; and the to-be-processed energy consumption is the energy consumption of the variable frequency heating device during the process of changing the current temperature to the to-be-processed temperature.

[0144] In the embodiments of the present application, based on at least one of the to-be-processed temperature, the to-be-processed speed and the to-be-processed energy consumption, the control strategy generation model can be trained and optimized.

[0145] In some embodiments of the present application, based on at least one of the to-be-processed temperature, the to-be-processed speed and the to-be-processed energy consumption, the control strategy generation model is trained, including:

[0146] Based on the to-be-processed temperature, the to-be-processed speed and the to-be-processed energy consumption, at least one of the temperature weight, the speed weight and the energy consumption weight is adjusted;

[0147] Based on at least one of the adjusted temperature weight, speed weight and energy consumption weight, the reward in the training process of the control strategy generation model is obtained;

[0148] The control strategy generation model is trained by using the reward.

[0149] In the embodiment of the present application, during the operation of the steam oven in the user's home, the sensors in the steam oven and the sensors of the variable frequency heating device can continue to collect data of the actual operation of the steam oven. The running state of the steam oven is monitored in real time through these data, and the actual effect of the power control strategy output by the control strategy generation model is evaluated. The changes of key indicators such as the accuracy of temperature adjustment, the response speed of temperature adjustment, and the energy consumption in the temperature adjustment process are focused on. The control strategy generation model is optimized and adjusted according to the evaluation results of the key indicators, including adjusting the weights of the reward function, optimizing the model parameters, and adjusting the training strategy to improve the performance of the model. At the same time, the applicability and robustness in different cooking scenarios are tested to ensure the wide applicability of the control strategy.

[0150] Therefore, during the training process of the control strategy generation model, based on the to-be-processed temperature, the to-be-processed speed, and the to-be-processed energy consumption, at least one of the temperature weight, the speed weight, and the energy consumption weight can be adjusted. For example: if the difference between the to-be-processed temperature and the target temperature is large, the temperature weight can be increased; if the to-be-processed speed is slow, the speed weight can be increased; and if the to-be-processed energy consumption is high, the energy consumption weight can be increased.

[0151] During the training process of the control strategy generation model, similar to the training process of the machine learning model, the first reward, the second reward, and the third reward can be provided for the control strategy generation model according to the to-be-processed temperature, the to-be-processed speed, and the to-be-processed energy consumption. Then, the target reward in the training process of the control strategy generation model is obtained by using the adjusted temperature weight, speed weight, and energy consumption weight and the first reward, second reward, and third reward. And the control strategy generation model is trained by using the target reward.

[0152] In the embodiment of the present application, the current power and working temperature of the variable frequency heating device, the current temperature, current humidity, current current, preset target temperature, and preset target humidity of the steam oven can also be input into another control strategy generation model to obtain another power control strategy of the variable frequency heating device. The other power control strategy is used to adjust the output power of the variable frequency heating device, so as to change the current temperature into the target temperature and change the current humidity into the target humidity. The state space input of the other control strategy generation model is the current power and working temperature of the variable frequency heating device, the current temperature, current humidity, current current, preset target temperature, and preset target humidity of the steam oven, and the action space output of the other control strategy generation model is the other power control strategy. The model training process of the other control strategy generation model corresponding to the production factory and the user's home is similar to the training process of the control strategy generation model, which will not be described herein.

[0153] In the embodiment of the present application, the steam oven has a safety mechanism, which can automatically stop or take other protective measures to avoid safety accidents when there is an abnormal situation in the steam oven. During the operation of the steam oven, if any device on the steam oven is found to have a fault, an alarm will be given and fault diagnosis will be performed.

[0154] In the training process of the machine learning model or the control strategy generation model, the machine learning model or the control strategy generation model has a redundant design. The parameters of the machine learning model or the control strategy generation model before training are initial parameters. If in the training process of the machine learning model or the control strategy generation model, the initial parameters change while the performance of the model becomes worse and worse, the changed parameters can be replaced by the initial parameters, and then the training is continued.

[0155] In the embodiment of the present application, the steam oven includes a variable frequency heating device, which is a graphene heating device and / or an eddy current variable heating device. The current temperature of the steam oven is collected by using a preset temperature sensor, and the working current and working voltage of the variable frequency heating device are collected by using preset current and voltage sensors. Based on the current temperature, working current, working voltage and preset target temperature of the steam oven, a power control strategy of the variable frequency heating device is obtained by using a preset control strategy generation model; based on the power control strategy, the output power of the variable frequency heating device is adjusted to change the current temperature of the steam oven to the target temperature. By using the power control strategy output by the control strategy generation model and cooperating with the variable frequency heating device, the output power of the variable frequency heating device can be adjusted to change the current temperature of the steam oven to the target temperature and control the steam oven to run at a constant temperature according to the target temperature.

[0156] In the embodiment of the present application, the control strategy generation model is trained by using a machine learning model. In the training process of the machine learning model and the optimization process of the control strategy generation model, the temperature regulation accuracy, the response speed of temperature regulation and the energy consumption in the temperature regulation process of the steam oven are considered, so as to solve the problems of slow response speed, large overshoot and high energy consumption in the temperature control method of the steam oven. By introducing a constant temperature energy-saving method based on reinforcement learning and combining different power graphene heating devices and eddy current variable heating devices, fast, accurate and energy-saving temperature control of the steam oven in a complex cooking environment is realized.

[0157] In the embodiment of the present application, the model is trained by a reinforcement learning algorithm, which can continuously try and error and optimize the control strategy, and combines the variable frequency heating technology to make the steaming oven maintain more stable and accurate temperature during the cooking process. In addition, the reinforcement learning algorithm in the training process can quickly adapt to environmental changes and reduce overshoot, combined with efficient heating devices (such as graphene heating devices and eddy current heating devices), thereby shortening the response time of temperature regulation. In the embodiment of the present application, the model is generated by optimizing the control strategy, thereby optimizing the power control strategy. The power control strategy can automatically adjust the power and on-off state of the graphene heating device and the eddy current heating device according to the needs of different cooking stages, ensure that the steaming oven can maintain the best temperature state in different cooking stages, and reduce unnecessary energy waste, realize on-demand heating, and realize energy saving and consumption reduction of the steaming oven in the constant temperature cooking process.

[0158] Referring to Figure 2 , a step flow chart of another temperature control method of a steaming oven provided in the embodiment of the present application is shown, which can specifically include the following steps:

[0159] Step 201, data acquisition and preprocessing.

[0160] The training current temperature, the training target temperature, the training current frequency of the variable frequency heating device of the steaming oven, and the training power control strategy for converting the training current temperature into the training target temperature are obtained.

[0161] Step 202, model building and training.

[0162] The preset machine learning model is trained by using the training current temperature, the training target temperature, the training current frequency, and the training power control strategy to obtain a control strategy generation model.

[0163] Step 203, model embedded deployment.

[0164] The control strategy generation model is embedded into the steaming oven.

[0165] Step 204, user use, and use the data in the user use process as training data to train the model.

[0166] In the process of running the control strategy generation model in the user's home, the state space input data in the running process is collected, and the data is used to train and optimize the control strategy generation model.

[0167] It should be noted that for the method embodiments, the series of acts complement each other to achieve the purpose of this embodiment, therefore, the sequence of the method should not be construed as limiting the application. Optionally, the sequence of the acts can be changed or two or more acts can be combined, however, the disclosure should not be construed as limited to the sequence provided and order provided, unless there is a clear indication that the sequence or order is important. Furthermore, embodiments of the application can take other forms than the act listed in the embodiments. Therefore, the disclosure should not be construed as limited to the embodiments set forth herein; rather these embodiments are provided because they illustrate the principles of the application and the best mode of practicing the application at the time the application was made. Later developments in technology can mean that the principles of the application can be implemented in other ways.

[0168] With reference to Figure 3 , a structural block diagram of a temperature control device of a steam oven is shown, which is applied to a steam oven, the steam oven comprising a variable frequency heating device, the variable frequency heating device being a graphene heating device and / or an eddy current variable heating device, and specifically can comprise the following modules:

[0169] A temperature acquisition module 301 is configured to acquire a current temperature of the steam oven by using a preset temperature sensor.

[0170] A voltage acquisition module 302 is configured to acquire a working current and a working voltage of the variable frequency heating device by using a preset current sensor and a voltage sensor respectively.

[0171] A strategy obtaining module 303 is configured to obtain a power control strategy of the variable frequency heating device by using a preset control strategy generation model based on the current temperature, the working current, the working voltage and a preset target temperature of the steam oven.

[0172] A power adjustment module 304 is configured to change the current temperature of the steam oven into the target temperature by adjusting an output power of the variable frequency heating device based on the power control strategy.

[0173] In an optional embodiment of the application, the strategy obtaining module comprises:

[0174] A frequency acquisition sub-module is configured to acquire a current power of the variable frequency heating device by using the working current and the working voltage.

[0175] A strategy obtaining sub-module is configured to input the current temperature, the current power and the target temperature into the control strategy generation model to obtain the power control strategy of the variable frequency heating device.

[0176] In an optional embodiment of the application, the device comprises:

[0177] A training data acquisition module is configured to acquire a training current temperature of the steam oven, a training target temperature, a training current frequency of the variable frequency heating device and a training power control strategy for converting the training current temperature into the training target temperature.

[0178] a training module, configured to train a preset machine learning model by using the training current temperature, the training target temperature, the training current frequency, and the training power control strategy, to obtain the control strategy generation model.

[0179] In an optional embodiment of the present application, the training module comprises:

[0180] an inference power control strategy obtaining submodule, configured to obtain an inference power control strategy output by the machine learning model for the training current temperature, the training target temperature, and the training current frequency during training of the machine learning model;

[0181] a transition temperature obtaining submodule, configured to obtain at least one of a transition temperature, a transition speed, and a transition energy consumption corresponding to the inference power control strategy; the transition temperature is a temperature obtained by adjusting the output power of the variable-frequency heating device by using the inference power control strategy, so that the training current temperature is changed; the transition speed is a speed at which the training current temperature is changed to the transition temperature; and the transition energy consumption is an energy consumption of the variable-frequency heating device during the process of changing the training current temperature to the transition temperature;

[0182] a training submodule, configured to train the machine learning model based on at least one of the transition temperature, the transition speed, and the transition energy consumption.

[0183] In an optional embodiment of the present application, the training submodule comprises:

[0184] a first reward providing unit, configured to provide a preset first reward for the machine learning model if a difference between the transition temperature and the training target temperature is less than a preset difference threshold;

[0185] a second reward providing unit, configured to provide a preset second reward for the machine learning model if the transition speed is higher than a preset speed threshold;

[0186] a third reward providing unit, configured to provide a preset third reward for the machine learning model if the transition energy consumption is less than a preset energy consumption threshold;

[0187] a training unit, configured to train the machine learning model by using at least one of the first reward, the second reward, and the third reward.

[0188] In an optional embodiment of the present application, the training unit comprises:

[0189] a weight configuration subunit, configured to configure preset temperature weights, speed weights, and energy consumption weights for the machine learning model;

[0190] a target reward obtaining subunit, configured to obtain a target reward of the machine learning model based on the temperature weight, the first reward, the speed weight, the second reward, the energy consumption weight, and the third reward;

[0191] a training subunit, configured to train the machine learning model by using the target reward.

[0192] In an optional embodiment of the present application, the power adjustment module comprises:

[0193] a to-be-processed temperature obtaining sub-module, configured to obtain at least one of a to-be-processed temperature, a to-be-processed speed, and a to-be-processed energy consumption corresponding to the power control strategy; the to-be-processed temperature is a temperature obtained by changing the current temperature by using the power control strategy to adjust the output power of the variable-frequency heating device; the to-be-processed speed is a speed of changing the current temperature to the to-be-processed temperature; and the to-be-processed energy consumption is energy consumption of the variable-frequency heating device in the process of changing the current temperature to the to-be-processed temperature;

[0194] a control strategy generation model training sub-module, configured to train the control strategy generation model based on at least one of the to-be-processed temperature, the to-be-processed speed, and the to-be-processed energy consumption.

[0195] In an optional embodiment of the present application, the control strategy generation model training sub-module comprises:

[0196] a weight adjustment unit, configured to adjust at least one of the temperature weight, the speed weight, and the energy consumption weight based on the to-be-processed temperature, the to-be-processed speed, and the to-be-processed energy consumption;

[0197] a reward obtaining unit, configured to obtain a reward in a training process of the control strategy generation model based on at least one of the adjusted temperature weight, speed weight, and energy consumption weight;

[0198] a control strategy generation model training unit, configured to train the control strategy generation model by using the reward.

[0199] In an optional embodiment of the present application, the device comprises:

[0200] a switch state adjustment module, configured to adjust a switch state of the graphene heating device and / or the eddy current heating device based on the power control strategy.

[0201] For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the related parts refer to the part of the method embodiment.

[0202] In addition, the embodiment of the present application also provides a steaming oven, such as Figure 4 As shown, the steaming oven comprises a processor 401, a communication interface 402, a memory 403 and a communication bus 404, wherein the processor 401, the communication interface 402 and the memory 403 complete mutual communication through the communication bus 404,

[0203] The memory 403 is used for storing a computer program.

[0204] The processor 401 is used for executing the program stored in the memory 403 to realize the following steps:

[0205] The current temperature of the steaming oven is collected by using a preset temperature sensor.

[0206] The working current and the working voltage of the variable-frequency heating device are collected by using preset current and voltage sensors respectively.

[0207] Based on the current temperature, the working current, the working voltage and the preset target temperature of the steaming oven, a power control strategy of the variable-frequency heating device is obtained by using a preset control strategy generation model.

[0208] Based on the power control strategy, the current temperature of the steaming oven is changed to the target temperature by adjusting the output power of the variable-frequency heating device.

[0209] In an optional embodiment of the present application, based on the current temperature, the working current, the working voltage and the preset target temperature of the steaming oven, the power control strategy of the variable-frequency heating device is obtained by using a preset control strategy generation model, comprising:

[0210] The current power of the variable-frequency heating device is obtained by using the working current and the working voltage.

[0211] The current temperature, the current power and the target temperature are input into the control strategy generation model to obtain the power control strategy of the variable-frequency heating device.

[0212] In an optional embodiment of the present application, the method comprises:

[0213] The training current temperature, the training target temperature, the training current frequency of the variable-frequency heating device and the training power control strategy for converting the training current temperature into the training target temperature of the steaming oven are obtained.

[0214] The preset machine learning model is trained by using the training current temperature, the training target temperature, the training current frequency and the training power control strategy to obtain the control strategy generation model.

[0215] In an optional embodiment of the present application, the training of the preset machine learning model by using the training current temperature, the training target temperature, the training current frequency and the training power control strategy to obtain the control strategy generation model comprises:

[0216] In the training process of the machine learning model, an inference power control strategy output by the machine learning model for the training current temperature, the training target temperature and the training current frequency is acquired;

[0217] At least one of a transition temperature, a transition speed and a transition energy consumption corresponding to the inference power control strategy is acquired; the transition temperature is a temperature obtained by adjusting the output power of the variable-frequency heating device by using the inference power control strategy so that the training current temperature is changed; the transition speed is a speed of changing the training current temperature to the transition temperature; and the transition energy consumption is an energy consumption of the variable-frequency heating device in the process of changing the training current temperature to the transition temperature;

[0218] The machine learning model is trained based on at least one of the transition temperature, the transition speed and the transition energy consumption.

[0219] In an optional embodiment of the present application, the training of the machine learning model based on at least one of the transition temperature, the transition speed and the transition energy consumption comprises:

[0220] If a difference between the transition temperature and the training target temperature is less than a preset difference threshold, a preset first reward is provided for the machine learning model;

[0221] If the transition speed is higher than a preset speed threshold, a preset second reward is provided for the machine learning model;

[0222] If the transition energy consumption is less than a preset energy consumption threshold, a preset third reward is provided for the machine learning model;

[0223] The machine learning model is trained by using at least one of the first reward, the second reward and the third reward.

[0224] In an optional embodiment of the present application, the training of the machine learning model by using at least one of the first reward, the second reward and the third reward comprises:

[0225] A preset temperature weight, a speed weight and an energy consumption weight are configured for the machine learning model;

[0226] obtain a target reward of the machine learning model based on the temperature weight, the first reward, the speed weight, the second reward, the energy consumption weight and the third reward;

[0227] train the machine learning model by using the target reward.

[0228] In an optional embodiment of the present application, the converting the current temperature of the steam oven into the target temperature by adjusting the output power of the variable frequency heating device comprises:

[0229] obtain at least one of a to-be-processed temperature, a to-be-processed speed and a to-be-processed energy consumption corresponding to the power control strategy; the to-be-processed temperature is a temperature obtained by adjusting the output power of the variable frequency heating device by using the power control strategy so that the current temperature is converted; the to-be-processed speed is a speed at which the current temperature is converted into the to-be-processed temperature; and the to-be-processed energy consumption is an energy consumption of the variable frequency heating device in the process of converting the current temperature into the to-be-processed temperature;

[0230] train the control strategy generation model based on at least one of the to-be-processed temperature, the to-be-processed speed and the to-be-processed energy consumption.

[0231] In an optional embodiment of the present application, the training the control strategy generation model based on at least one of the to-be-processed temperature, the to-be-processed speed and the to-be-processed energy consumption comprises:

[0232] adjust at least one of the temperature weight, the speed weight and the energy consumption weight based on the to-be-processed temperature, the to-be-processed speed and the to-be-processed energy consumption;

[0233] obtain a reward in a training process of the control strategy generation model based on at least one of the adjusted temperature weight, the speed weight and the energy consumption weight;

[0234] train the control strategy generation model by using the reward.

[0235] In an optional embodiment of the present application, the method comprises:

[0236] adjust the on-off state of the graphene heating device and / or the eddy current variable heating device based on the power control strategy.

[0237] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0238] The communication interface is used for communication between the aforementioned terminal and other devices.

[0239] The memory may include random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0240] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0241] like Figure 5 As shown, in another embodiment of the present invention, a computer-readable storage medium 501 is also provided, which stores instructions that, when executed on a computer, cause the computer to perform a temperature control method for a steam oven as described in the above embodiment.

[0242] In another embodiment of the present invention, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to execute a temperature control method for a steam oven as described in the above embodiments.

[0243] In the embodiments described above, all or some of the steps can be implemented by software, hardware, firmware or any combination thereof. When implemented in software, all or some of the steps can be implemented in the form of one or more computer programs which are stored in a computer readable storage medium. The computer readable storage medium can be located in a computing device which is in operation. These computer programs (which may

[0244] It is to be noted that, in the present document, the terms such as first and second, etc., are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between such entities or operations. Moreover, the terms "comprising", "including", or any other variant are intended to cover a non-exclusive inclusion, such that processes, methods, articles, or apparatuses that comprise a list of elements are not required to include only those elements in the list, but can include other elements not expressly listed, or also include elements inherent in such processes, methods, articles, or apparatuses. Without more limitations, an element defined by the statement "comprising a..." does not exclude the existence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0245] Each of the embodiments in the present document is described in a related manner, and the same or similar parts among the embodiments can be referred to each other. Each of the embodiments focuses on the difference from other embodiments. In particular, for the system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the description of the method embodiments.

[0246] The above merely provides the preferred embodiments of the application, and not intended to limit the protection scope of the application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the application shall fall within the protection scope of the application.

Claims

1. A temperature control method for a steam oven, characterized in that, The method is applied to a steam oven, wherein the steam oven includes a frequency conversion heating device, the frequency conversion heating device being a graphene heating device and / or an eddy current heating device, and the method includes: The current temperature of the steam oven is collected using a preset temperature sensor; The operating current and operating voltage of the variable frequency heating equipment are collected using preset current and voltage sensors, respectively. The training current temperature and training target temperature of the steam oven, the training current frequency of the variable frequency heating device, and the training power control strategy for converting the training current temperature into the training target temperature are obtained. Using the current training temperature, the target training temperature, the current training frequency, and the training power control strategy, a preset machine learning model is trained to obtain a control strategy generation model; Based on the current temperature, the operating current, the operating voltage, and the preset target temperature of the steam oven, the power control strategy of the variable frequency heating device is obtained by generating a model using the control strategy. Based on the power control strategy, the current temperature of the steam oven is converted into the target temperature by adjusting the output power of the variable frequency heating device; The step of training a preset machine learning model using the current training temperature, the target training temperature, the current training frequency, and the training power control strategy to obtain a control strategy generation model includes: During the training process of the machine learning model, the inference power control strategy of the machine learning model for the current training temperature, the target training temperature, and the current training frequency is obtained. The transition temperature, transition speed, and transition energy consumption corresponding to the inference power control strategy are obtained; the transition temperature is the temperature obtained by adjusting the output power of the variable frequency heating device using the inference power control strategy to transition the current training temperature; the transition speed is the speed at which the current training temperature changes to the transition temperature; and the transition energy consumption is the energy consumption of the variable frequency heating device during the process of the current training temperature changing to the transition temperature. If the difference between the transition temperature and the training target temperature is less than a preset difference threshold, then a preset first reward is provided to the machine learning model; If the transformation speed is higher than a preset speed threshold, a preset second reward is provided to the machine learning model; If the energy consumption of the transformation is less than the preset energy consumption threshold, then a preset third reward is provided to the machine learning model; Configure preset temperature weights, speed weights, and energy consumption weights for the machine learning model; Based on the temperature weight, the first reward, the speed weight, the second reward, the energy consumption weight, and the third reward, the target reward of the machine learning model is obtained; The machine learning model is trained using the target reward.

2. The method according to claim 1, characterized in that, The process of generating a power control strategy for the variable frequency heating device using the control strategy model based on the current temperature, the operating current, the operating voltage, and the preset target temperature of the steam oven includes: The current power of the variable frequency heating device is obtained using the operating current and the operating voltage; The current temperature, the current power, and the target temperature are input into the control strategy generation model to obtain the power control strategy of the variable frequency heating device.

3. The method according to claim 1, characterized in that, The step of adjusting the output power of the variable frequency heating device to convert the current temperature of the steam oven into the target temperature includes: The power control strategy is used to obtain at least one of the following: the temperature to be processed, the speed to be processed, and the energy consumption to be processed. The temperature to be processed is the temperature obtained by adjusting the output power of the variable frequency heating device using the power control strategy to transform the current temperature. The speed to be processed is the speed at which the current temperature transforms into the temperature to be processed. The energy consumption to be processed is the energy consumption of the variable frequency heating device during the process of transforming the current temperature into the temperature to be processed. The control strategy generation model is trained based on at least one of the temperature to be processed, the speed to be processed, and the energy consumption to be processed.

4. The method according to claim 3, characterized in that, The step of training the control strategy generation model based on at least one of the temperature to be processed, the speed to be processed, and the energy consumption to be processed includes: Based on the temperature to be processed, the speed to be processed, and the energy consumption to be processed, adjust at least one of the temperature weight, the speed weight, and the energy consumption weight; The reward during the training process of the control strategy generation model is obtained based on at least one of the adjusted temperature weight, speed weight, and energy consumption weight. The control policy generation model is trained using the reward.

5. The method according to claim 1, characterized in that, The method includes: Based on the power control strategy, adjust the switching state of the graphene heating device and / or the eddy current heating device.

6. A temperature control device for a steam oven, characterized in that, Applied to a steam oven, the steam oven includes a frequency conversion heating device, wherein the frequency conversion heating device is a graphene heating device and / or an eddy current heating device, and the device includes: The temperature acquisition module is used to acquire the current temperature of the steam oven using a preset temperature sensor; The voltage acquisition module is used to acquire the operating current and operating voltage of the variable frequency heating equipment using preset current and voltage sensors, respectively. The training power control strategy acquisition module is used to acquire the current training temperature and target training temperature of the steam oven, the current training frequency of the variable frequency heating device, and the training power control strategy for converting the current training temperature into the target training temperature. The model training module is used to train a preset machine learning model using the current training temperature, the target training temperature, the current training frequency, and the training power control strategy to obtain a control strategy generation model. The strategy acquisition module is used to obtain the power control strategy of the variable frequency heating device based on the current temperature, the operating current, the operating voltage and the preset target temperature of the steam oven, using the control strategy generation model. A power adjustment module is used to adjust the output power of the variable frequency heating device based on the power control strategy to change the current temperature of the steam oven to the target temperature. The model training module includes: The inference power control strategy acquisition submodule is used to acquire, during the training process of the machine learning model, the inference power control strategy output by the machine learning model for the current training temperature, the target training temperature, and the current training frequency. The transition temperature acquisition submodule is used to acquire the transition temperature, transition speed, and transition energy consumption corresponding to the inference power control strategy; the transition temperature is the temperature obtained by adjusting the output power of the variable frequency heating device using the inference power control strategy to transition from the current training temperature; the transition speed is the speed at which the current training temperature transitions to the transition temperature; and the transition energy consumption is the energy consumption of the variable frequency heating device during the transition from the current training temperature to the transition temperature. The first reward provision submodule is used to provide a preset first reward to the machine learning model if the difference between the transition temperature and the training target temperature is less than a preset difference threshold. The second reward provision submodule is used to provide a preset second reward to the machine learning model if the transformation speed is higher than a preset speed threshold. The third reward provision submodule is used to provide a preset third reward to the machine learning model if the conversion energy consumption is less than a preset energy consumption threshold. The weight configuration submodule is used to configure preset temperature weights, speed weights, and energy consumption weights for the machine learning model. The target reward acquisition submodule is used to acquire the target reward of the machine learning model based on the temperature weight, the first reward, the speed weight, the second reward, the energy consumption weight, and the third reward. The model training submodule is used to train the machine learning model using the target reward.

7. A steam oven, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; The memory is used to store computer programs; When the processor executes a program stored in the memory, it implements the method as described in any one of claims 1-5.

8. One or more computer-readable media having instructions stored thereon that, when executed by one or more processors, cause the processors to perform the method as described in any one of claims 1-5.

Images