Oven and control method thereof

Abstract

The embodiment of the present application provides an oven and a control method thereof, which relates to the technical field of ovens and is used to improve the accuracy of temperature control of the oven. The oven includes: an inner tank, a heating cavity is formed inside the inner tank, a heating device, and a temperature sensor; a controller is configured to: obtain a cooking instruction input by a user, and determine a first dynamic temperature value according to a first target temperature value included in the cooking instruction; control the heating device to start working, and detect the temperature value of the heating cavity through the temperature sensor; after detecting that the temperature value of the heating cavity reaches the first dynamic temperature value, perform a step of adjusting the duty cycle of the heating device, and the adjustment step includes: predicting the duty cycle of the heating device in the next cycle after the current cycle according to the temperature value of the heating cavity in the current cycle; the duty cycle is the ratio of the duration of the heating device in a working state in a cycle to the duration of the cycle; and controlling the heating device to work according to the duty cycle of the next cycle.

Description

Technical Field

[0001] The present application relates to the technical field of ovens, and in particular to an oven and a control method thereof. Background Art

[0002] As people's living standards improve, users' requirements for home cooking are also gradually increasing. Users expect to use home ovens to cook better quality food. However, most current home ovens have large temperature fluctuations during cooking, that is, when the oven temperature is stable, the high and low temperatures vary greatly, which will affect the quality of food and even make some temperature-sensitive foods unable to be cooked successfully, resulting in users being unable to use the oven to achieve the desired effect.

[0003] There are existing methods to improve the temperature control accuracy of ovens. Due to the lag in the oven's own sensors and systems, the oven's heating action cannot be immediately fed back to the sensor, which makes it easy for temperature fluctuations to occur when controlling the temperature, resulting in insufficient accuracy in temperature control and affecting user experience. Summary of the invention

[0004] The present application provides an oven and a control method thereof, which are used to improve the accuracy of temperature control of the oven.

[0005] In a first aspect, an embodiment of the present application provides an oven, comprising:

[0006] The inner pot has a heating chamber formed inside, and the heating chamber is used to hold food;

[0007] A heating device is arranged on the inner pot and is used for heating the inner pot;

[0008] A temperature sensor is arranged inside the inner tank and is used to detect the temperature value of the heating chamber;

[0009] The controller connected to the heating device and the temperature sensor is configured as follows:

[0010] Acquire a cooking instruction input by a user, and determine a first dynamic temperature value according to a first target temperature value included in the cooking instruction, wherein the first dynamic temperature is below the first target temperature value;

[0011] Control the heating device to start working, and detect the temperature value of the heating chamber through the temperature sensor;

[0012] After detecting that the temperature value of the heating chamber reaches the first dynamic temperature value, a step of adjusting the duty cycle of the heating device is executed, and the adjustment step includes: predicting the duty cycle of the heating device in the next cycle after the current cycle based on the temperature value of the heating chamber in the current cycle; the duty cycle is the ratio of the time duration that the heating device is in a working state within a cycle to the duration of the cycle; and controlling the heating device to work according to the duty cycle of the next cycle.

[0013] The technical solution provided by the embodiment of the present application brings at least the following beneficial effects: the embodiment of the present application provides an oven, which performs a step of adjusting the duty cycle of the heating device after the temperature value of the heating chamber reaches the first dynamic temperature, that is, when the temperature value of the heating chamber is close to the first target temperature value but has not reached the first target temperature value. The adjustment step includes: predicting the duty cycle of the next cycle according to the temperature value in the current cycle, and controlling the heating device to start working according to the duty cycle of the next cycle. In this way, the duty cycle of the heating device in the next cycle is predicted according to the temperature value of the current cycle, and the heating device is controlled to work in the next cycle according to the duty cycle of the heating device in the next cycle, so that the oven can adjust the temperature of the heating chamber in time, avoid the influence of hysteresis on temperature control, and improve the accuracy of temperature control of the oven.

[0014] In some embodiments, after the controller is configured to execute the step of adjusting the duty cycle of the heating device, it is also configured to: if the current cooking time of the oven has not reached the cooking time indicated by the cooking instruction, repeat the step of adjusting the duty cycle of the heating device until the current cooking time of the oven reaches the cooking time indicated by the cooking instruction, and then control the oven to stop working.

[0015] In some embodiments, the controller is configured to predict the duty cycle of the heating device in the next cycle after the current cycle based on the temperature value of the heating chamber in the current cycle. The controller is specifically configured to: input the temperature value of the heating chamber in the current cycle into the duty cycle prediction model, and output the duty cycle of the heating device in the next cycle after the current cycle.

[0016] In some embodiments, the duty cycle prediction model is obtained in the following manner: the controller determines a second dynamic temperature value according to a second target temperature value input by a user, and the second dynamic temperature value is below the second target temperature value; the heating device is controlled to start working, and the temperature value of the heating chamber is detected by a temperature sensor; after detecting that the temperature value of the heating chamber reaches the second dynamic temperature value, the optimization step of the original duty cycle prediction model based on the neural network algorithm is repeatedly performed, and when it is detected that the preset condition is met, the optimization step is stopped, and the original duty cycle prediction model when the preset condition is met is used as the optimized duty cycle prediction model;

[0017] The optimization step includes: inputting the temperature value of the heating chamber in the first cycle into the original duty cycle prediction model, outputting the duty cycle of the heating device in the second cycle, and the second cycle is after the first cycle; controlling the heating device to work according to the duty cycle of the second cycle, and obtaining the temperature value of the heating chamber in the second cycle through a temperature sensor; optimizing the parameters of the original duty cycle prediction model according to the temperature value of the heating chamber in the second cycle, the second target temperature value and the soft actor critic (SAC) algorithm;

[0018] The preset conditions include: the number of executions of the optimization step reaches a preset number, and the cumulative reward value of the original duty cycle prediction model is above the preset reward value, and the reward value of the original duty cycle prediction model is obtained based on the temperature value of the heating chamber and the second target temperature value.

[0019] In some embodiments, the controller is configured to optimize the parameters of the original duty cycle prediction model based on the temperature value of the heating chamber in the second period, the second target temperature value and the SAC algorithm. Specifically, it is configured to: determine the reward value of the duty cycle of the heating device in the second period based on the temperature value of the heating chamber in the second period and the second target temperature value; optimize the parameters of the original duty cycle prediction model based on the reward value of the duty cycle of the heating device in the second period and the SAC algorithm.

[0020] In a second aspect, an embodiment of the present application provides a method for controlling an oven, the method comprising: obtaining a cooking instruction input by a user, and determining a first dynamic temperature value according to a first target temperature value included in the cooking instruction, the first dynamic temperature being below the first target temperature value;

[0021] Control the heating device to start working and detect the temperature value of the heating chamber;

[0022] After detecting that the temperature value of the heating chamber reaches the first dynamic temperature value, a step of adjusting the duty cycle of the heating device is executed, and the adjustment step includes: predicting the duty cycle of the heating device in the next cycle after the current cycle based on the temperature value of the heating chamber in the current cycle; the duty cycle is the ratio of the time duration that the heating device is in a working state within a cycle to the duration of the cycle; and controlling the heating device to work according to the duty cycle of the next cycle.

[0023] In some embodiments, after performing the step of adjusting the duty cycle of the heating device, the method further comprises:

[0024] When the current cooking time of the oven does not reach the cooking time indicated by the cooking instruction, the step of adjusting the duty cycle of the heating device is repeated until the current cooking time of the oven reaches the cooking time indicated by the cooking instruction, and then the oven is controlled to stop working.

[0025] In some embodiments, predicting the duty cycle of the heating device in a next cycle after the current cycle according to the temperature value of the heating chamber in the current cycle includes:

[0026] The temperature value of the heating chamber in the current cycle is input into the duty cycle prediction model, and the duty cycle of the heating device in the next cycle after the current cycle is output.

[0027] In some embodiments, the duty cycle prediction model is obtained by: determining a second dynamic temperature value according to a second target temperature value input by a user, the second dynamic temperature value being below the second target temperature value; controlling the heating device to start working, and detecting the temperature value of the heating chamber; after detecting that the temperature value of the heating chamber reaches the second dynamic temperature value, repeatedly performing the optimization step of the original duty cycle prediction model based on the neural network algorithm, and when it is detected that the preset condition is met, stopping the optimization step, and using the original duty cycle prediction model when the preset condition is met as the optimized duty cycle prediction model;

[0028] The optimization step includes: inputting the temperature value of the heating chamber in the first cycle into the original duty cycle prediction model, outputting the duty cycle of the heating device in the second cycle, the second cycle being after the first cycle; controlling the heating device to work according to the duty cycle of the second cycle, and obtaining the temperature value of the heating chamber in the second cycle; optimizing the parameters of the original duty cycle prediction model according to the temperature value of the heating chamber in the second cycle, the second target temperature value and the SAC algorithm;

[0029] The preset conditions include: the number of executions of the optimization step reaches a preset number, and the cumulative reward value of the original duty cycle prediction model is above the preset reward value, and the reward value of the original duty cycle prediction model is obtained based on the temperature value of the heating chamber and the second target temperature value.

[0030] In some embodiments, the parameters of the original duty cycle prediction model are optimized according to the temperature value of the heating chamber in the second cycle, the second target temperature value and the SAC algorithm, including: determining the reward value of the duty cycle of the heating device in the second cycle according to the temperature value of the heating chamber in the second cycle and the second target temperature value; optimizing the parameters of the original duty cycle prediction model according to the reward value of the duty cycle of the heating device in the second cycle and the SAC algorithm.

[0031] In a third aspect, an embodiment of the present application provides a controller comprising: one or more processors; one or more memories; wherein the one or more memories are used to store computer program codes, the computer program codes include computer instructions, and when the one or more processors execute the computer instructions, the controller executes any one of the oven control methods provided in the second aspect.

[0032] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which includes computer instructions. When the computer instructions are executed on a computer, the computer executes any one of the oven control methods provided in the second aspect.

[0033] In a fifth aspect, an embodiment of the present application provides a computer program product, which can be directly loaded into a memory and contains software code. After being loaded and executed by a computer, the computer program product can implement any oven control method provided in the second aspect.

[0034] It should be noted that the above computer instructions may be stored in whole or in part on a computer-readable storage medium, wherein the computer-readable storage medium may be packaged together with the processor of the controller, or may be packaged separately from the processor of the controller, which is not limited in this application.

[0035] The beneficial effects described in the second to fifth aspects of the present application can be referred to the beneficial effect analysis of the first aspect and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings are used to provide a further understanding of the technical solution of the present invention and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present invention and do not constitute a limitation on the technical solution of the present invention.

[0037] Figure 1 A schematic diagram of an oven provided in an embodiment of the present application;

[0038] Figure 2 A schematic diagram of the structure of an oven provided in an embodiment of the present application;

[0039] Figure 3 A schematic diagram of the hardware configuration of an oven provided in an embodiment of the present application;

[0040] Figure 4 A schematic diagram of interaction between a controller of an oven and a terminal device provided in an embodiment of the present application;

[0041] Figure 5 A schematic flow chart of a method for controlling an oven provided in an embodiment of the present application;

[0042] Figure 6 A schematic diagram of the temperature control effect of a duty cycle prediction model for an oven provided in an embodiment of the present application;

[0043] Figure 7 A schematic diagram of a training process of a duty cycle prediction model for an oven provided in an embodiment of the present application;

[0044] Figure 8A schematic diagram of the cumulative reward value of a duty cycle prediction model for an oven provided in an embodiment of the present application;

[0045] Fig. 9 A schematic diagram of the overall process of a duty cycle prediction model training method provided in an embodiment of the present application;

[0046] Fig.10 A schematic diagram of the overall flow of a method for controlling an oven provided in an embodiment of the present application;

[0047] Fig.11 A schematic diagram of the hardware structure of a controller of an oven provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0049] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0050] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0051] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "connected" and "connection" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances. In addition, when describing a pipeline, the "connected" and "connection" used in this application have the meaning of conduction. The specific meaning needs to be understood in conjunction with the context.

[0052] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0053] With the development of society, people's quality of life is constantly improving, and the requirements for home cooking are also constantly increasing. Nowadays, ovens are generally controlled by proportional-integral-derivative (PID), but the control effect of this control method depends on the setting of the working parameters at the factory, and the actual temperature control effect depends more on the experience of technicians. In addition, there is a certain hysteresis in PID control, which makes it impossible for the heating action of the oven to be fed back to the sensor immediately, resulting in large temperature fluctuations during the baking process. Too high a temperature will cause the food to crack or over-color, and even produce harmful substances; too low a temperature will cause the food to mature inside, affecting the user experience.

[0054] Based on this, the present application proposes an oven, which performs a step of adjusting the duty cycle of the heating device after the temperature value of the heating chamber reaches the first dynamic temperature, that is, when the temperature value of the heating chamber is close to the first target temperature value but has not yet reached the first target temperature value. According to the temperature value in the current cycle, the duty cycle of the next cycle is predicted, and the heating device is controlled to start working according to the duty cycle of the next cycle. In this way, according to the temperature value of the current cycle, the duty cycle of the heating device in the next cycle is predicted, and according to the duty cycle of the heating device in the next cycle, the heating device is controlled to work in the next cycle, so that the oven can adjust the temperature of the heating chamber in time, avoid the influence of hysteresis on temperature control, and improve the accuracy of temperature control of the oven.

[0055] Figure 1 A schematic diagram of an oven provided in an embodiment of the present application. Figure 1 As shown, the oven 100 may include: a housing 10, an inner container 11 ( Figure 1 ), oven door 12 and temperature sensor 13.

[0056] Among them, the housing 10 can be as follows Figure 1 The housing 10 is approximately a rectangular parallelepiped, but may also be in other shapes. The top side of the housing 10 is provided with an upper cover plate, the two sides are provided with side covers, the front side is connected to an oven door 12, and the rear side is connected to a rear cover plate.

[0057] The inner pot 11 is arranged in the outer shell 10, and a heating cavity with an opening is formed inside the inner pot 11, and food materials that need to be processed in the oven can be placed in the heating cavity.

[0058] The oven door 12 is hinged to the housing 10 through a door hinge assembly. When cooking is required, the inner pot 11 is opened by the oven door 12, and the food to be cooked is placed into the inner pot 11 from the access opening, and then the inner pot 11 is closed by the oven door 12, and the power is turned on to cook. After cooking is finished, the food is taken out to achieve cooking of the food.

[0059] In some embodiments, the oven 100 further includes a temperature sensor 13, which is disposed inside the inner pot and is used to detect a temperature value of a heating cavity formed by the inner pot.

[0060] Figure 2 It is a structural schematic diagram of an oven provided in an embodiment of the present application.

[0061] like Figure 2 As shown, the oven 100 may further include a plurality of heating devices 14, which are disposed on the inner pot and are used to heat the food placed in the heating cavity. The heating device 14 may be straight, round, flat square or other shapes. The heating device 14 may be a light wave auxiliary heating tube, a far infrared heating tube, a coated heating plate, a carbon fiber heating device, a graphene heating device, a resistance tube, etc.

[0062] In some embodiments, the oven 100 may further include a plurality of guide plates, which are disposed around the heating device 14 to ensure that the heat radiated by the heating device 14 is radiated to the surface of the food at a certain angle.

[0063] In some embodiments, the oven 100 may further include a baking tray for holding food so that the food can be placed inside the oven 100 .

[0064] Figure 3 FIG. 1 is a hardware configuration diagram of an oven 100 provided in accordance with an exemplary embodiment of the present application. Figure 3 As shown, the oven 100 also includes one or more of the following: a display panel 15 , an operation panel 16 , a voice device 17 , a controller 18 and a power supply 19 .

[0065] In some embodiments, the display panel 15 is installed on the outer surface of the oven and can be rectangular or elliptical.

[0066] Optionally, the display panel 15 displays the real-time temperature value of the heating chamber detected by the temperature sensor 13 .

[0067] In some embodiments, the operation panel 16 has function buttons. Exemplarily, the function buttons may include a switch button, a mode selection button, a temperature selection button, + (increase button), - (decrease button), etc. The user can interact with the oven 100 through the operation panel 16 to control the operation of the oven 100.

[0068] In some embodiments, the voice device 17 is used to issue voice prompt information.

[0069] In some embodiments, the controller 18 refers to a device that can generate an operation control signal according to the instruction operation code and the timing signal to instruct the oven 100 to execute the control instruction. Exemplarily, the controller 18 can be a central processing unit (CPU), a general-purpose processor network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a programmable logic device (PLD), or any combination thereof. The controller 18 can also be other devices with processing functions, such as circuits, devices, or software modules, and the embodiments of the present application do not impose any restrictions on this.

[0070] The controller 18 is electrically connected to the power supply 19 , the heating device 14 , the temperature sensor 13 , the display panel 15 , the operation panel 16 and the voice device 17 , and is used to control the operation of each component electrically connected thereto so as to realize various predetermined functions of the oven 100 .

[0071] In some embodiments, the power supply 19, under the control of the controller 18, uses the power input from the external power supply to provide power supply support for the oven 100. The power supply 19 may include a built-in power supply circuit installed inside the oven 100, or may be an external power supply installed in the oven 100 to provide a power interface for an external power supply in the oven 100.

[0072] In some embodiments, the oven 100 also has a communicator, which is connected to the controller 18 and is used to establish a communication connection with other network entities. Taking the RF module as an example, the RF module can be used to receive and send signals, especially to send the received information to the controller 18 for processing; in addition, the signal generated by the controller is sent out. Generally, the RF circuit can include but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (LNA), a duplexer, etc.

[0073] For example, the oven 100 may receive a control instruction sent by a terminal device through a communicator, and perform corresponding processing according to the control instruction to realize interaction between the user and the oven 100 .

[0074] Figure 4 It is a schematic diagram of the interaction between a controller 18 of an oven and a terminal device 500 provided in accordance with an exemplary embodiment of the present application.

[0075] like Figure 4 As shown, the terminal device 500 can establish a communication connection with the controller 18 of the oven. Exemplarily, any known network communication protocol can be used to establish the communication connection. The above-mentioned network communication protocol can be various wired or wireless communication protocols, such as Ethernet, universal serial bus (USB), FireWire (FIREWIRE), any cellular network communication protocol (such as 3G / 4G / 5G), Bluetooth, wireless fidelity (wireless fidelity, Wi-Fi), NFC or any other suitable communication protocol. The above-mentioned communication connection can be a Bluetooth connection, NFC, Zigbee, wireless fidelity (wireless fidelity, Wi-Fi), etc. The embodiments of the present application do not impose specific restrictions on this.

[0076] It should be noted that Figure 4 The terminal device 500 shown is only an example of a terminal device. The terminal device 300 in the present application may be a remote control, a mobile phone, a tablet computer, a personal computer (PC), a personal digital assistant (PDA), a smart watch, a netbook, a wearable electronic device, an augmented reality (AR) device, a virtual reality (VR) device, a robot, etc. The present application does not impose any special restrictions on the specific form of the terminal device.

[0077] It is understood that the structure illustrated in the embodiment of the present invention does not constitute a specific limitation on the oven. In other embodiments of the present application, the oven may include more or fewer components than shown in the figure, or combine some components, or split some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0078] The following is a detailed introduction to the embodiments of the present application in conjunction with the accompanying drawings.

[0079] The present application embodiment provides a method for controlling an oven, the method being applied to a controller, which may be the controller 18 in the oven 100. Figure 5 As shown, the control method may include the following steps:

[0080] S101. Acquire a cooking instruction input by a user, and determine a first dynamic temperature value according to a first target temperature value included in the cooking instruction.

[0081] The first dynamic temperature value is below the first target temperature value.

[0082] In some embodiments, when a user needs to use an oven for cooking, after placing ingredients into the heating chamber, the user can input a cooking instruction to the oven to instruct the oven to work. Then, the controller obtains the cooking instruction input by the user.

[0083] In some embodiments, the user may input the cooking instruction in one or more of the following ways:

[0084] Method 1: Enter cooking instructions through the operation panel.

[0085] Exemplarily, the housing of the oven has an operation panel, and the operation panel has function buttons, including: a switch button, a mode selection button, a temperature selection button, + (increase button), - (decrease button), etc. The user can interact with the oven through the operation panel and issue cooking instructions.

[0086] Method 2: Input cooking instructions through the smart terminal.

[0087] In some implementations, the smart terminal may be a mobile phone. The user may set the cooking instructions through an application software (such as a smart home application software) on the mobile phone, and then send the cooking instructions to the controller through a Wi-Fi network or Bluetooth.

[0088] In some embodiments, the cooking instruction includes: a first target temperature, a cooking time, a cooking mode, etc. The first target temperature is the cooking temperature that the oven is to reach when cooking, which is set by the user.

[0089] In some embodiments, the cooking instructions may further include: a cooking start time and a heat preservation time after the cooking ends.

[0090] Optionally, determining the first dynamic temperature value according to the first target temperature value included in the cooking instruction may be specifically implemented as follows: taking the temperature difference between the first target temperature value and the first preset temperature value as the first dynamic temperature value.

[0091] The first preset temperature value may be preset when the oven leaves the factory, for example, the first preset temperature value is 3 degrees Celsius (° C.) That is, the difference between the first target temperature value and the first dynamic temperature value is 3° C.

[0092] S102, controlling the heating device to start working and detecting the temperature value of the heating chamber.

[0093] After determining the first dynamic temperature value, the controller controls the heating device to start working so that the temperature value in the heating chamber reaches the first dynamic temperature value. In the heating process, in order to timely know that the temperature value in the heating chamber reaches the first dynamic temperature value, the controller can detect the temperature value of the heating chamber in real time or periodically through a temperature sensor.

[0094] S103 . After detecting that the temperature value of the heating chamber reaches a first dynamic temperature value, executing a step of adjusting the duty cycle of the heating device.

[0095] It is understandable that after detecting that the temperature value of the heating chamber reaches the first dynamic temperature value, it means that the temperature value of the heating chamber is close to the first target temperature value. In order to ensure the accuracy of the temperature control of the oven, the controller performs a step of adjusting the duty cycle of the heating device.

[0096] Among them, the adjustment step includes: predicting the duty cycle of the heating device in the next cycle after the current cycle based on the temperature value of the heating chamber in the current cycle; controlling the heating device to work according to the duty cycle of the next cycle; the duty cycle is the ratio of the time the heating device is in a working state in a cycle to the length of the cycle.

[0097] It is worth noting that the step of adjusting the duty cycle of the heating device can be repeated, that is, after controlling the heating device according to the duty cycle of the next cycle, the duty cycle of the heating device in the next cycle can be predicted according to the temperature value in the next cycle, and the heating device can be controlled to work in the next cycle according to the duty cycle of the next cycle.

[0098] In some embodiments, the current cycle in which the temperature value of the heating chamber reaches the first dynamic temperature value may be a cycle formed by tracing back one cycle length when the temperature value of the heating chamber reaches the first dynamic temperature value.

[0099] For example, a cycle is 60 seconds (second, S), and the current cycle when the temperature value of the heating chamber reaches the first dynamic temperature value is a cycle formed by tracing back 60 seconds from the time when the temperature value of the heating chamber reaches the first dynamic temperature value. In other words, the moment when the temperature value of the heating chamber reaches the first dynamic temperature value is traced back 60 seconds, and these 60 seconds are regarded as the current cycle when the temperature value of the heating chamber reaches the first dynamic temperature value.

[0100] In some embodiments, the temperature value in the current cycle may be a plurality of temperature values ​​detected at regular intervals within the cycle.

[0101] In some embodiments, based on the temperature value of the heating chamber in the current cycle, the duty cycle of the heating device in the next cycle after the current cycle is predicted. This can be specifically implemented as follows: the temperature value of the heating chamber in the current cycle is input into a duty cycle prediction model to obtain the duty cycle of the next cycle after the current cycle.

[0102] In some embodiments, the duty cycle prediction model is a prediction model based on a neural network algorithm. The prediction model based on the neural network algorithm is a mathematical model described based on neurons, represented by network topology, node characteristics and learning rules, and has the following characteristics: 1. Parallel distributed processing. 2. High robustness and fault tolerance. 3. Distributed storage and learning capabilities. 4. Ability to fully approximate complex nonlinear relationships.

[0103] In some embodiments, during the process of executing the step of adjusting the duty cycle of the heating device, if the current cooking time of the oven has not reached the cooking time indicated by the cooking instruction, the step of adjusting the duty cycle of the heating device is repeated until the current cooking time of the oven reaches the cooking time indicated by the cooking instruction, and the cooking is completed, and the oven is controlled to stop working.

[0104] Figure 6 A schematic diagram of the temperature control effect of a duty cycle prediction model of an oven provided in an embodiment of the present application. Figure 6 As shown, the first target temperature value is Figure 6 The target temperature is called the target temperature, and the temperature of the heating chamber is Figure 6 When the first target temperature is 162°C, the temperature of the heating cavity of the oven is controlled within a range of 161.1°C to 162.7°C within 30 minutes.

[0105] The technical solution provided by the embodiment of the present application brings at least the following beneficial effects: the control method of an oven provided by the embodiment of the present application, after the temperature value of the heating chamber reaches the first dynamic temperature, that is, when the temperature value of the heating chamber is close to the first target temperature value but has not reached the first target temperature value, performs a step of adjusting the duty cycle of the heating device. The adjustment step includes: predicting the duty cycle of the next cycle according to the temperature value in the current cycle, and controlling the heating device to start working according to the duty cycle of the next cycle. In this way, the duty cycle of the heating device in the next cycle is predicted according to the temperature value and duty cycle prediction model of the current cycle, so that the oven can adjust the temperature of the heating chamber in time, avoid the influence of hysteresis on temperature control, and improve the accuracy of temperature control of the oven.

[0106] The above embodiments focus on how the controller controls the temperature of the heating chamber of the oven. In some embodiments, the oven control method provided by the embodiments of the present application also involves a step of training a duty cycle prediction model, such as Figure 7 As shown, the training steps of the duty cycle prediction model include the following steps:

[0107] S201. Determine a second dynamic temperature value according to a second target temperature value input by a user.

[0108] The second dynamic temperature value is below the second target temperature value.

[0109] In some embodiments, an original duty cycle prediction model is pre-stored in the memory of the oven. In order to improve the accuracy of the prediction of the original duty cycle prediction model and improve the accuracy of the temperature control of the oven, the original duty cycle prediction model needs to be trained. The original duty cycle prediction model can be a prediction model based on a neural network algorithm. The second target temperature value is a target temperature value that needs to be trained during the duty cycle prediction model training process.

[0110] In some embodiments, in order to improve the temperature control range of the duty cycle prediction model, after training a second target temperature value, the second target temperature value can be changed, and then training can be continued according to the changed second target temperature value.

[0111] As a possible implementation manner, the changed second target temperature value is gradually increased or gradually decreased based on the second target value after the training is completed.

[0112] For example, during the duty cycle prediction model training, the second target temperature value is 162° C. After the duty cycle prediction model training is completed with 162° C. as the second target temperature value, the second target temperature value is changed to 167° C., and the duty cycle prediction model training is continued.

[0113] Optionally, determining the second dynamic temperature value according to the second target temperature value may be specifically implemented as follows: taking the temperature difference between the second target temperature value and the second preset temperature value as the second dynamic temperature value.

[0114] The second preset temperature value may be the first preset temperature value preset when the oven leaves the factory, for example, the second preset temperature value is 3° C. That is, the difference between the second target temperature value and the second dynamic temperature value is 3° C.

[0115] S202, controlling the heating device to start working and detecting the temperature value of the heating chamber.

[0116] After determining the second dynamic temperature value, the controller controls the heating device to start working so that the temperature value in the heating chamber reaches the second dynamic temperature value. In the heating operation, in order to timely know that the temperature value in the heating chamber reaches the second dynamic temperature value, the controller can detect the temperature value of the heating chamber in real time or periodically through the temperature sensor.

[0117] S203. After detecting that the temperature value of the heating chamber reaches the second dynamic temperature value, repeatedly execute the optimization step of the original duty cycle prediction model based on the neural network algorithm. When it is detected that the preset conditions are met, stop executing the optimization step, and use the original duty cycle prediction model when the preset conditions are met as the optimized duty cycle prediction model.

[0118] The optimization step includes the following steps:

[0119] S1. Input the temperature value of the heating chamber in the first cycle into the original duty cycle prediction model, and output the duty cycle of the heating device in the second cycle.

[0120] The second cycle is after the first cycle.

[0121] In some embodiments, when the temperature value of the heating chamber reaches the second dynamic temperature value, a cycle formed by tracing back a period of time becomes the first cycle.

[0122] For example, if one cycle is 60 seconds, the first cycle is formed by tracing back 60 seconds from when the temperature value of the heating chamber reaches the second dynamic temperature value. That is, tracing back 60 seconds from when the temperature value of the heating chamber reaches the second dynamic temperature value is regarded as the first cycle.

[0123] By inputting the temperature value of the first cycle into the original duty cycle model, the duty cycle of the added device in the second cycle can be obtained, which is used to control the heating device to work in the second cycle.

[0124] S2. Control the heating device to operate according to the duty cycle of the second cycle, and obtain the temperature value of the heating chamber in the second cycle.

[0125] The heating device operates according to the duty cycle of the second cycle output by the original duty cycle model, and detects the temperature value of the heating chamber in the second cycle for the following two purposes: 1. Inputting the temperature value of the second cycle into the original duty cycle model to obtain the duty cycle of the third cycle; 2. Serving as data for optimizing the original duty cycle prediction model.

[0126] S3. Optimize the parameters of the original duty cycle prediction model according to the temperature value of the heating chamber in the second cycle, the second target temperature value and the SAC algorithm.

[0127] In some embodiments, the parameters of the original duty cycle prediction model are optimized according to the temperature value of the heating chamber in the second cycle, the second target temperature value and the SAC algorithm. This can be specifically implemented as follows: according to the temperature value of the heating chamber in the second cycle and the second target temperature value, the reward value of the duty cycle of the heating device in the second cycle is determined; according to the reward value of the duty cycle of the heating device in the second cycle and the SAC algorithm, the parameters of the original duty cycle prediction model are optimized.

[0128] In some embodiments, the reward value of the duty cycle of the heating device in the second period is determined according to the temperature value of the heating chamber in the second period and the second target temperature value, which can be shown as the following formula:

[0129]

[0130] Among them, Reward is the reward value, T target is the second target temperature value, T center is the temperature of the heating chamber of the oven, that is, the temperature value of the heating chamber in the second cycle.

[0131] In some embodiments, after determining the reward value of the duty cycle of the second period, the parameters of the original duty cycle prediction model are optimized according to the reward value of the duty cycle of the second period and the SAC algorithm.

[0132] In some embodiments, the SAC algorithm is a different-strategy algorithm developed for maximum entropy reinforcement learning. The goal of maximum entropy reinforcement learning is to maximize the cumulative reward value.

[0133] In some embodiments, the SAC algorithm includes a policy network and a loss function. The policy network is used to determine the duty cycle of the next cycle after the current cycle and the temperature prediction value of the next cycle after the current cycle according to the temperature value in the current cycle; the loss function is used to determine the expected loss according to the temperature value in the current cycle and the temperature prediction value corresponding to the current cycle. The SAC model updates the weights of the policy network based on the reward value and the expected loss through the gradient descent method so that the temperature value approaches the second target temperature value in each cycle, and the accuracy of the temperature prediction value at the end of each cycle is improved.

[0134] Among them, the preset conditions in S203 include: the number of executions of the optimization step reaches a preset number, and the cumulative reward value of the original duty cycle prediction model is above the preset reward value, and the reward value of the original duty cycle prediction model is obtained based on the temperature value of the heating chamber and the second target temperature value.

[0135] The preset number of times and the preset reward value may be preset at the factory.

[0136] In some embodiments, during the training process of the duty cycle prediction model, the optimization step is repeatedly executed, and after the optimization step is executed a preset number of times, the cumulative reward value of the original duty cycle prediction model is judged. If the cumulative reward value of the original duty cycle prediction model is above the preset reward value, it means that the original duty cycle prediction model has completed training, the optimization step is stopped, and the original duty cycle prediction model is used as the optimized duty cycle prediction model; if the cumulative reward value of the original duty cycle prediction model is below the preset reward value, it means that the original duty cycle prediction model has not completed training, and the training is restarted.

[0137] Exemplarily, the preset number of times may be 16 times, and the preset reward value may be 13. When the number of executions of the optimization step does not reach 16 times, the optimization step is repeated, and when the number of executions of the optimization step reaches 16 times, the cumulative reward value of the original duty cycle prediction model is judged. If the cumulative reward value of the original duty cycle prediction model is below 13, it means that the original duty cycle prediction model has not completed training and needs to be restarted; otherwise, it means that the original duty cycle prediction model has completed training, the optimization step is stopped, and the original duty cycle prediction model is used as the optimized duty cycle prediction model. Figure 8 A schematic diagram of the cumulative reward value of the oven duty cycle prediction model provided in the embodiment of the present application. Figure 8 As shown, the cumulative reward value of the duty cycle prediction model fluctuates in the first 10 optimization steps, and reaches a higher level after 15 optimization steps.

[0138] In some embodiments, when the temperature value in a certain period exceeds a preset temperature range, it means that the training effect of the SAC algorithm on the duty cycle prediction model is poor and needs to be retrained.

[0139] Among them, the preset temperature range is a temperature range set according to the second target temperature value, the second target temperature value can be used as the middle value of the temperature range, the upper limit value of the temperature range can be the sum of the second target temperature and the preset value, and the lower limit value of the temperature range can be the difference between the second target temperature and the preset value, wherein the preset value can be pre-set when the oven leaves the factory.

[0140] In some embodiments, when the number of executions of the optimization step reaches a preset number and the cumulative reward value of the original duty cycle prediction model is above the preset reward value, it means that the original duty cycle prediction model has completed the training of the current second target temperature value, and then the second target temperature value is changed and retrained until the total number of executions of the optimization step is above the preset cumulative number.

[0141] Exemplarily, the preset cumulative number of times can be 200 times. When the original duty cycle prediction model completes the training of the current second target temperature value, it is determined whether the total number of executions of the optimization steps is more than 200 times. If it is determined whether the total number of executions of the optimization steps is more than 200 times, it means that the original duty cycle prediction model has completed the training, and the optimization steps are stopped. The duty cycle prediction model trained for the last time is used as the optimized duty cycle prediction model; otherwise, the second target temperature value is changed and retrained.

[0142] The preset cumulative number of times may be preset at the factory.

[0143] The following is an example of a training method for a duty cycle prediction model provided in an embodiment of the present application. Fig. 9 The figure is a schematic diagram of the overall process of a duty cycle prediction model training method provided in an embodiment of the present application.

[0144] After starting the training, the controller determines the second dynamic temperature value according to the second target temperature value input by the user, wherein the second dynamic temperature value is below the second target temperature value. The second target temperature value is the temperature value that the duty cycle prediction model needs to train this time, and the second dynamic temperature value is close to a certain temperature of the second target temperature value. In this way, when the temperature value of the heating chamber reaches the second dynamic temperature value, it means that the temperature value of the heating chamber is about to reach the second target temperature value, and subsequent temperature control is required.

[0145] After determining the second dynamic temperature value, the controller controls the heating device to start heating, and detects the temperature value of the heating chamber through the temperature sensor. After detecting that the temperature value of the heating chamber reaches the second dynamic temperature value, the optimization step of the original duty cycle prediction model based on the neural network algorithm is repeatedly performed, wherein the optimization step includes: taking the period when the temperature value of the heating chamber is detected to reach the second dynamic temperature value as the first period, and inputting the temperature value within the period into the original duty cycle prediction model to obtain the duty cycle of the heating device in the second period, and the second period is after the first period. The heating device is controlled to work according to the duty cycle of the second period, and the temperature value of the heating chamber in the second period is obtained through the temperature sensor.

[0146] Then, the reward value of the duty cycle of the heating device is determined according to the temperature value of the heating chamber in the second cycle and the second target temperature value, and the parameters of the original duty cycle prediction model are optimized according to the reward value and the SAC algorithm. In the process of repeatedly executing the optimization steps, the controller will accumulate the reward value of each execution of the optimization step. The controller will also detect the temperature value of the heating chamber in real time. If it is detected that the temperature value of the heating chamber is not within the preset temperature range, the training process will be terminated and restarted.

[0147] When the number of executions of the optimization step reaches the preset number, the cumulative reward value of the initial duty cycle prediction model is judged. If the cumulative reward value of the original duty cycle prediction model is below the preset reward value, it means that the training effect of the original duty cycle prediction model is poor and needs to be retrained; if the cumulative reward value of the original duty cycle prediction model is above the preset reward value, it means that the original duty cycle prediction model has completed the training for the current second target temperature. Then change the second target temperature value and continue the training of the original duty cycle prediction model until the total number of executions of the optimization step is above the preset cumulative number.

[0148] The following is an example of a control method for an oven provided in an embodiment of the present application. Fig.10 The figure is a schematic diagram of the overall flow of a method for controlling an oven provided in an embodiment of the present application.

[0149] As a possible example, when a user needs to use an oven, the user interacts with the oven through an operation panel to issue a cooking instruction. The oven obtains the cooking instruction input by the user, and the cooking instruction includes: cooking time and a first target temperature. The first dynamic temperature value is determined according to the first target temperature value.

[0150] The controller controls the heating device to start heating, and detects the temperature value of the heating chamber through the temperature sensor. After detecting that the temperature value of the heating chamber reaches the first dynamic temperature value, the step of adjusting the duty cycle of the heating device is performed, wherein the adjustment step includes: taking the temperature value in the cycle when the temperature value of the heating chamber reaches the first dynamic temperature as the temperature value in the current cycle, inputting the duty cycle prediction model to predict the duty cycle of the next cycle after the current cycle, and the controller controls the heating device to work according to the duty cycle of the next cycle. Then, it is determined whether the current cooking time reaches the cooking time indicated by the cooking instruction. If not, the step of adjusting the duty cycle of the heating device is repeated; if the current cooking time has reached the cooking time indicated by the cooking instruction, the oven is controlled to stop working and cooking is completed.

[0151] The present application also provides a hardware structure diagram of a controller, such as Fig.11 As shown, the controller 200 includes a processor 201, and optionally, further includes a memory 202 and a communication interface 203 connected to the processor 201. The processor 201, the memory 202 and the communication interface 203 are connected via a bus 204.

[0152] The processor 201 may be a central processing unit (CPU), a general-purpose processor network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a programmable logic device (PLD), or any combination thereof. The processor 201 may also be any other device having a processing function, such as a circuit, a device, or a software module. The processor 201 may also include multiple CPUs, and the processor 201 may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. The processor here may refer to one or more devices, circuits, or processing cores for processing data (such as computer program instructions).

[0153] The memory 202 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, and the present embodiment of the application does not impose any restrictions on this. The memory 202 may exist independently or be integrated with the processor 201. Among them, the memory 202 may contain a computer program code. The processor 201 is used to execute the computer program code stored in the memory 202, so as to realize the control method of the oven provided in the embodiment of the present application.

[0154] The communication interface 203 can be used to communicate with other devices or communication networks (such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc. The communication interface 203 can be a module, a circuit, a transceiver or any device that can achieve communication.

[0155] The bus 204 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus 204 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.11 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0156] Those skilled in the art will appreciate that in one or more of the above examples, the functions described in the present invention may be implemented in hardware, software, firmware, or any combination thereof. When implemented using software, the functions may be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any media that facilitates the transmission of a computer program from one place to another. The storage medium may be any available medium that a general or special-purpose computer can access.

[0157] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0158] In addition, each functional unit in each embodiment of the present invention can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a U disk, a mobile hard disk, a ROM, a RAM, a disk, or an optical disk.

[0159] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An oven, characterized in that: include: An inner pot, wherein a heating cavity is formed inside the inner pot, and the heating cavity is used to hold food; A heating device, disposed on the inner pot, for heating the inner pot; A temperature sensor is disposed inside the inner container and is used to detect the temperature value of the heating chamber; The controller connected to the heating device and the temperature sensor is configured as follows: Acquire a cooking instruction input by a user, and determine a first dynamic temperature value according to a first target temperature value included in the cooking instruction, wherein the first dynamic temperature is below the first target temperature value; Controlling the heating device to start working, and detecting the temperature value of the heating chamber through the temperature sensor; After detecting that the temperature value of the heating chamber reaches the first dynamic temperature value, performing a step of adjusting the duty cycle of the heating device, the step of adjusting comprising: inputting the temperature value of the heating chamber in a current cycle into a duty cycle prediction model, and outputting the duty cycle of the heating device in a next cycle after the current cycle; The duty cycle is the ratio of the duration of the heating device being in the working state within a cycle to the duration of the cycle; the heating device is controlled to work according to the duty cycle of the next cycle.

2. The oven according to claim 1, characterized in that: The controller, after being configured to perform the step of adjusting the duty cycle of the heating device, is further configured to: When the current cooking time of the oven does not reach the cooking time indicated by the cooking instruction, the step of adjusting the duty cycle of the heating device is repeated until the current cooking time of the oven reaches the cooking time indicated by the cooking instruction, and then the oven is controlled to stop working.

3. The oven according to claim 1, characterized in that: The duty cycle prediction model is obtained by: The controller determines a second dynamic temperature value according to a second target temperature value input by a user, wherein the second dynamic temperature value is below the second target temperature value; Controlling the heating device to start working, and detecting the temperature value of the heating chamber through the temperature sensor; After detecting that the temperature value of the heating chamber reaches the second dynamic temperature value, repeatedly performing the optimization step of the original duty cycle prediction model based on the neural network algorithm, and when detecting that the preset condition is met, stopping the optimization step, and using the original duty cycle prediction model when the preset condition is met as the optimized duty cycle prediction model; The optimization step includes: inputting the temperature value of the heating chamber in the first cycle into the original duty cycle prediction model, outputting the duty cycle of the heating device in the second cycle, the second cycle being after the first cycle; controlling the heating device to work according to the duty cycle of the second cycle, and obtaining the temperature value of the heating chamber in the second cycle through the temperature sensor; optimizing the parameters of the original duty cycle prediction model according to the temperature value of the heating chamber in the second cycle, the second target temperature value and the flexible action evaluation SAC algorithm; The preset conditions include: the number of executions of the optimization step reaches a preset number, and the cumulative reward value of the original duty cycle prediction model is above a preset reward value, and the reward value of the original duty cycle prediction model is obtained based on the temperature value of the heating chamber and the second target temperature value.

4. The oven according to claim 3, characterized in that: The controller is configured to optimize the parameters of the original duty cycle prediction model according to the temperature value of the heating chamber in the second cycle, the second target temperature value and the SAC algorithm, and is specifically configured as follows: determining a reward value of a duty cycle of the heating device in the second period according to a temperature value of the heating chamber in the second period and the second target temperature value; The parameters of the original duty cycle prediction model are optimized according to the reward value of the duty cycle of the heating device in the second cycle and the SAC algorithm.

5. A method for controlling an oven, characterized in that: The method comprises: Acquire a cooking instruction input by a user, and determine a first dynamic temperature value according to a first target temperature value included in the cooking instruction, wherein the first dynamic temperature is below the first target temperature value; Control the heating device to start working and detect the temperature value of the heating chamber; After detecting that the temperature value of the heating chamber reaches the first dynamic temperature value, performing a step of adjusting the duty cycle of the heating device, the step of adjusting comprises: inputting the temperature value of the heating chamber in the current cycle into a duty cycle prediction model, and outputting the duty cycle of the heating device in the next cycle after the current cycle; the duty cycle is the ratio of the duration of the heating device being in the working state in one cycle to the duration of the cycle; The heating device is controlled to operate according to the duty cycle of the next cycle.

6. The method according to claim 5, characterized in that After the step of adjusting the duty cycle of the heating device, the method further comprises: When the current cooking time of the oven does not reach the cooking time indicated by the cooking instruction, the step of adjusting the duty cycle of the heating device is repeated until the current cooking time of the oven reaches the cooking time indicated by the cooking instruction, and then the oven is controlled to stop working.

7. The method according to claim 5, characterized in that The duty cycle prediction model is obtained by: Determining a second dynamic temperature value according to a second target temperature value input by a user, wherein the second dynamic temperature value is below the second target temperature value; Controlling the heating device to start working and detecting the temperature value of the heating chamber; After detecting that the temperature value of the heating chamber reaches the second dynamic temperature value, repeatedly performing the optimization step of the original duty cycle prediction model based on the neural network algorithm, and when detecting that the preset condition is met, stopping the optimization step, and using the original duty cycle prediction model when the preset condition is met as the optimized duty cycle prediction model; The optimization step includes: inputting the temperature value of the heating chamber in the first cycle into the original duty cycle prediction model, outputting the duty cycle of the heating device in the second cycle, the second cycle being after the first cycle; controlling the heating device to work according to the duty cycle of the second cycle, and obtaining the temperature value of the heating chamber in the second cycle; optimizing the parameters of the original duty cycle prediction model according to the temperature value of the heating chamber in the second cycle, the second target temperature value and the SAC algorithm; The preset conditions include: the number of executions of the optimization step reaches a preset number, and the cumulative reward value of the original duty cycle prediction model is above a preset reward value, and the reward value of the original duty cycle prediction model is obtained based on the temperature value of the heating chamber and the second target temperature value.

8. The method according to claim 7, characterized in that The optimizing the parameters of the original duty cycle prediction model according to the temperature value of the heating chamber in the second cycle, the second target temperature value and the SAC algorithm comprises: determining a reward value of a duty cycle of the heating device in the second period according to a temperature value of the heating chamber in the second period and the second target temperature value; The parameters of the original duty cycle prediction model are optimized according to the reward value of the duty cycle of the heating device in the second cycle and the SAC algorithm.

Images