Temperature control management method of electric oven

Abstract

The invention discloses a temperature control management method for an electric oven, and relates to the technical field of intelligent household appliance control, and the method comprises the steps: carrying out the offset correction of a pre-stored mode mapping table based on a calibration matrix, loading a target temperature interval and a three-dimensional temperature field partition parameter according to a cooking mode selected by a user, and triggering a dynamic learning mark; according to the dynamic learning mark, the furnace chamber temperature and the environment temperature change rate are collected in real time, the power compensation amount is calculated through a thermal inertia compensation model, and a partition power control matrix is generated in combination with the three-dimensional temperature field partition parameters; and distributing the power compensation amount and the partition power control matrix to the heating pipe according to a preset topology, dynamically adjusting power output, and implementing temperature early warning and no-load identification based on an acoustic emission spectrum entropy value. The temperature gradient change rate is calculated through the Fourier heat conduction law, the three-dimensional temperature field partition parameters are dynamically generated, and accurate control over the temperature field in the complex three-dimensional space is ensured so as to cope with environment changes and user demand changes.

Description

Technical Field

[0001] The invention relates to the technical field of intelligent household appliance control, in particular to a temperature control management method of an electric oven. Background Art

[0002] Early electric ovens mainly relied on simple mechanical thermostats to achieve temperature control, which resulted in large temperature fluctuations during the heating process. With the development of electronic technology and intelligent control theory, electric ovens began to use PID controllers to improve temperature control accuracy. The PID controller adjusts the temperature through three links: proportional, integral, and differential. It can reduce temperature fluctuations to a certain extent and provide a relatively stable temperature environment. The PID control method can maintain relatively constant heating conditions by continuously monitoring and adjusting the temperature, which is suitable for the basic needs of various cooking modes.

[0003] In recent years, with the application of artificial intelligence and machine learning technologies, the temperature control management of electric ovens has ushered in new development opportunities. However, the current technical solutions still face some challenges in practical applications. First of all, it is still a difficult problem to achieve accurate zoning and control of the temperature field in a complex three-dimensional space. Existing methods often ignore the influence of structural parameters such as baking tray material and size on temperature distribution, resulting in frequent local overheating or uneven cooling. Secondly, the existing technology also has shortcomings in energy-saving optimization. There is a lack of effective energy-saving strategies for no-load conditions, and it fails to make full use of temperature warning and anomaly detection mechanisms to reduce energy consumption and extend the service life of equipment. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a temperature control management method for an electric oven to solve the problems of uneven temperature distribution and insufficient no-load energy saving.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: In a first aspect, the present invention provides a temperature control management method for an electric oven, which includes loading furnace body structure parameters and performing zero-point calibration to generate a calibration matrix, and simultaneously initializing thermal inertia compensation parameters; offset-correcting a pre-stored mode mapping table based on the calibration matrix, loading a target temperature range and three-dimensional temperature field partition parameters according to the cooking mode selected by the user, and triggering a dynamic learning flag; according to the dynamic learning flag, collecting the furnace cavity temperature and the ambient temperature change rate in real time, calculating the power compensation amount through a thermal inertia compensation model, and generating a partition power control matrix in combination with the three-dimensional temperature field partition parameters; distributing the power compensation amount and the partition power control matrix to the heating tubes according to a preset topology, dynamically adjusting the power output, and implementing temperature warning and no-load identification based on the acoustic emission spectrum entropy value; iteratively optimizing the thermal inertia compensation parameters and the temperature field partition parameters according to the power adjustment data, the temperature warning state, and the no-load identification result, and simultaneously generating an energy-saving control strategy and a temperature anomaly protection strategy in the no-load state.

[0007] As a preferred solution of the temperature control management method for the electric oven of the present invention, wherein: the furnace body structure parameters include the baking tray size, the baking tray temperature distribution data, and the material thermal conductivity.

[0008] As a preferred solution of the temperature control management method for the electric oven of the present invention, wherein: the steps of loading the furnace body structure parameters and performing zero-point calibration to generate a calibration matrix, and simultaneously initializing the thermal inertia compensation parameters are as follows: Based on an ice-water mixture environment, define a reference value and generate a calibration matrix in combination with a spatial position weight factor; Initialize the thermal inertia compensation parameters according to the calibration matrix, and establish a mapping relationship between the thermal inertia compensation parameters and the three-dimensional temperature field partition.

[0009] As a preferred solution of the temperature control management method for the electric oven of the present invention, wherein: the steps of offset-correcting a pre-stored mode mapping table based on the calibration matrix, loading a target temperature range and three-dimensional temperature field partition parameters according to the cooking mode selected by the user, and triggering a dynamic learning flag are as follows: Define a dynamic reference temperature range through the mapping relationship between the thermal inertia compensation parameters and the three-dimensional temperature field partition, and generate a target temperature range according to the current furnace body structure; Based on the target temperature range and the material thermal conductivity, calculate the temperature gradient change rate according to Fourier's law of heat conduction, and dynamically generate three-dimensional temperature field partition parameters according to a gradient threshold; When the temperature gradient change rate exceeds the dynamic learning activation limit value, trigger the dynamic learning flag.

[0010] As a preferred solution of the temperature control management method of the electric oven described in the present invention, wherein: according to the dynamic learning flag, the furnace cavity temperature and the environmental temperature change rate are collected in real time, and the power compensation amount is calculated through the thermal inertia compensation model. The specific steps are as follows, When it is detected that the dynamic learning flag is activated, the furnace cavity temperature field distribution data and the environmental temperature change rate are collected in real time and spatially and temporally superimposed to generate a three-dimensional compensation input matrix containing spatio-temporal characteristics; The furnace cavity temperature field distribution data and the environmental temperature change rate are used as a training set, and supervised learning training is carried out based on the marked ideal compensation amount to generate a thermal inertia compensation model; The three-dimensional compensation input matrix is used as the input parameter of the thermal inertia compensation model, and the power compensation amount is calculated based on the gradient optimization algorithm.

[0011] As a preferred solution of the temperature control management method of the electric oven described in the present invention, wherein: the generation of the partition power control matrix in combination with the three-dimensional temperature field partition parameters is as follows. The specific steps are as follows, According to the three-dimensional temperature field partition parameters, the furnace cavity is divided into multiple sub-regions with different thermal inertia response characteristics, and a dynamic heat conduction relationship is established for each sub-region; The dynamic heat conduction relationship of each sub-region is input into the pre-trained adaptive compensation mechanism, and a multi-dimensional power control matrix matching the temperature field partition is generated.

[0012] As a preferred solution of the temperature control management method of the electric oven described in the present invention, wherein: the distribution of the power compensation amount and the partition power control matrix to the heating tubes according to the preset topology, dynamically adjusting the power output, and implementing temperature warning and no-load identification based on the acoustic emission spectrum entropy value. The specific steps are as follows, The obtained power compensation amount and the partition power control matrix are mapped to the heating tube control unit according to the preset heating tube topology relationship, and the dynamic coupling parameters between adjacent tubes are generated; Based on the dynamic coupling parameters, the power output of each heating tube is adjusted in real time through a closed-loop controller, and the vibration signals of the heating tubes are synchronously collected and the spectrum entropy value is calculated; When the spectrum entropy value continuously exceeds the no-load determination threshold, it is considered that the current oven is in a no-load state, and a temperature anomaly warning is generated.

[0013] As a preferred solution of the temperature control management method of the electric oven described in the present invention, wherein: the iterative optimization of the thermal inertia compensation parameters and the temperature field partition parameters according to the power control data, the temperature warning state and the no-load identification result, and the synchronous generation of the energy-saving control strategy and the temperature anomaly protection strategy under the no-load state. The specific steps are as follows, Based on the power control data, combined with the dynamic adjustment factors in the temperature anomaly warning and the no-load identification result, an initial optimization parameter set of the thermal inertia compensation parameters and the temperature field partition parameters is generated; According to the initial optimization parameter set, the weight of the temperature field partition parameters is iteratively updated through the energy consumption balance logic, and an energy-saving control strategy and a temperature anomaly protection strategy are generated based on the no-load identification result; The generated energy-saving control strategy is allocated to the corresponding heating tubes according to the partition energy consumption threshold, and at the same time, the temperature anomaly protection strategy is associated with the regulation interfaces of each partition; After executing the energy-saving control strategy, the temperature control deviation and energy consumption data are collected in real time, and the furnace body structure parameters are updated through the feedback correction mechanism and iteratively optimized.

[0014] In a second aspect, the present invention provides a computer device, including a memory and a processor, where the memory stores a computer program, and: when the computer program is executed by the processor, any step of the temperature control management method of the electric oven as described in the first aspect of the present invention is implemented.

[0015] In a third aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, and: when the computer program is executed by the processor, any step of the temperature control management method of the electric oven as described in the first aspect of the present invention is implemented.

[0016] The beneficial effects of the present invention are as follows: By loading the target temperature range and three-dimensional temperature field partition parameters through the selected cooking mode by the user, a high degree of adaptability to different cooking requirements is achieved. Further, the Fourier heat conduction law is used to calculate the temperature gradient change rate, and the three-dimensional temperature field partition parameters are dynamically generated, ensuring the precise control of the temperature field in the complex three-dimensional space to cope with environmental changes and changes in user needs. It not only improves the accuracy of temperature control, but also enhances the flexibility and intelligence level of the device, enabling the electric oven to better adapt to various cooking scenarios and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 It is a flowchart of the temperature control management method of the electric oven.

[0019] Figure 2 It is a flowchart of the calibration matrix generation process of the temperature control management method of the electric oven.

[0020] Figure 3 It is a flowchart of the dynamic learning flag triggering of the temperature control management method of the electric oven.

[0021] Figure 4 It is a flow chart of power compensation distribution and heating tube control for the temperature control management method of an electric oven. Specific embodiments

[0022] To make the above objects, features and advantages of the present invention more obvious and understandable, the specific embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings of the specification.

[0023] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art can make similar generalizations without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0024] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure or characteristic that may be included in at least one implementation manner of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or alternative embodiments that exclude each other with other embodiments.

[0025] Refer to Figures 1 to 4 , which is an embodiment of the present invention. This embodiment provides a temperature control management method for an electric oven, including the following steps: S1: Load the furnace body structure parameters and perform zero calibration to generate a calibration matrix, and at the same time initialize the thermal inertia compensation parameters.

[0026] S1.1: The furnace body structure parameters include the baking tray size, the baking tray temperature distribution data, and the material thermal conductivity.

[0027] It should be noted that when collecting the furnace body structure parameters, the baking tray size, the baking tray temperature distribution data, and the material thermal conductivity are obtained by a combination of contact measurement and non-contact measurement. The baking tray size is directly measured using a laser rangefinder or a mechanical caliper, for example, recording the length, width, and thickness of the baking tray, and the example data is 300mm×200mm×5mm; an infrared thermal imager is used to scan the surface of the baking tray at a fixed time interval to obtain the baking tray temperature distribution data, and the example scanning interval is 5 seconds, and the temperature resolution reaches 0.5°C; the material thermal conductivity is measured by a standard thermal property tester, and the example test condition is a constant temperature environment of 25°C, and the measurement is carried out according to the ASTM D5470 standard. All measurement data are verified to form a complete set of furnace body structure parameters, including three core parameters: the baking tray size, the baking tray temperature distribution data, and the material thermal conductivity.

[0028] S1.2: Based on the ice-water mixture environment, define a reference value and generate a calibration matrix in combination with the spatial position weight factor.

[0029] The calibration matrix includes temperature deviation compensation coefficients and spatial weight factors.

[0030] The specific process includes that the ice-water mixture environment refers to the solid-liquid coexistence phase equilibrium state formed by distilled water and high-purity ice in a closed container, and its function is to provide a standard 0°C reference benchmark for temperature measurement; in the ice-water mixture environment, the temperature sensor array to be calibrated is completely immersed and kept in thermal equilibrium for 30 minutes, and the steady-state response values output by each sensor are recorded as reference values. The spatial position weight factor is calculated according to the coordinate positions of the sensors in the three-dimensional temperature field. When generating the calibration matrix, the temperature deviation compensation coefficient of each sensor is multiplied by the corresponding spatial position weight factor after normalization. For example, a deviation coefficient of -0.12°C and a weight factor of 0.8 result in a calibration parameter of -0.096°C; the finally formed calibration matrix contains a data structure of N×4, and each row records the sensor number, three-dimensional coordinates, temperature deviation compensation coefficient, and spatial weight factor, which are used for real-time compensation of subsequent temperature measurements.

[0031] S1.3: Initialize the thermal inertia compensation parameters according to the calibration matrix, and establish the mapping relationship between the thermal inertia compensation parameters and the partitions of the three-dimensional temperature field.

[0032] The thermal inertia compensation parameters include a dynamic learning rate and an inertia delay time.

[0033] The specific process includes that when initializing the thermal inertia compensation parameters, the temperature deviation compensation coefficients and spatial weight factors in the calibration matrix are used as basic input parameters. The temperature deviation compensation coefficients are normalized according to the spatial weight factors and then converted into initial compensation values. The initial compensation values are allocated according to the corresponding relationship of the spatial coordinates of the partitions of the three-dimensional temperature field to establish a direct mapping between the thermal inertia compensation parameters and the partitions of the three-dimensional temperature field. For example, a region with partition coordinates (x1, y1, z1) corresponds to a specific combination of thermal inertia compensation parameters; the thermal inertia compensation parameters include two core parameters, namely the dynamic learning rate and the inertia delay time. Among them, the dynamic learning rate is automatically adjusted according to the temperature change gradient within the partition. For example, when the temperature gradient increases by 1°C / cm, the dynamic learning rate increases by 0.01. The inertia delay time is jointly determined by the thermal conductivity coefficient of the partition material and the spatial weight factor. For example, the inertia delay time for the aluminum alloy partition is 2 seconds, while that for the stainless steel partition is 3 seconds. The entire process strictly initializes the parameters based on the reference data provided by the calibration matrix to ensure that the thermal inertia compensation parameters are fully matched with the physical characteristics of the partitions of the three-dimensional temperature field.

[0034] S2: Perform offset correction on the pre-stored pattern mapping table based on the calibration matrix, load the target temperature range and three-dimensional temperature field partition parameters according to the cooking mode selected by the user, and trigger the dynamic learning flag.

[0035] S2.1: Define a dynamic reference temperature range based on the mapping relationship between the thermal inertia compensation parameters and the three-dimensional temperature field partitions, and generate a target temperature range according to the current furnace structure.

[0036] The specific process includes, when defining the dynamic reference temperature range, establishing the mapping relationship between the thermal inertia compensation parameters and the three-dimensional temperature field partitions by taking the spatial coordinates (x, y, z) of each temperature field partition as input parameters, and the dynamic learning rate and inertia delay time as output parameters. The upper and lower limits of the reference temperature range are dynamically adjusted according to the compensation parameters in the mapping relationship. During the process of dynamically adjusting the reference temperature range, first determine the basic adjustment amount based on the measured temperature deviation of each partition. After the basic adjustment amount is corrected by the temperature deviation compensation coefficient specific to the partition, it is combined with the spatial weight factor of the corresponding partition to form the final temperature range adjustment value. After the adjustment is executed, continuously monitor the actual temperature change situation, and compare and verify the actual temperature change situation with the predicted change trend based on the thermal inertia characteristics of the partition.

[0037] Furthermore, when generating the target temperature range, the baking tray size, material thermal conductivity, and heating tube distribution parameters of the current furnace structure are used as input conditions. The dynamic reference temperature range is coupled with the furnace structure parameters. First, perform area weighting on the reference range of each partition according to the baking tray size, and then adjust the range according to the material thermal conductivity. For example, the range of the aluminum alloy partition is narrowed to ±3°C due to its high thermal conductivity. The finally generated target temperature range is 182 - 188°C in the center area of the baking tray and 175 - 181°C in the edge area, accurately reflecting the thermal distribution characteristics of the furnace structure.

[0038] S2.2: Calculate the temperature gradient change rate based on the target temperature range and the material thermal conductivity, and dynamically generate the three-dimensional temperature field partition parameters according to the gradient threshold. The expression is: ; Where, represents the temperature gradient change rate, represents the material thermal conductivity, represents the three-dimensional space weight coefficient, represents the horizontal coordinate in the three-dimensional coordinate system of the baking tray, represents the longitudinal coordinate in the three-dimensional coordinate system of the baking tray, represents the vertical coordinate in the three-dimensional coordinate system of the baking tray, represents the maximum temperature difference of the target range, represents the characteristic length of the baking tray, represents the hyperbolic tangent function, represents the response sharpness coefficient, represents the original temperature gradient calculated in real time, Represents the critical temperature value at which the thermal response characteristics change significantly. Represents the time decay coefficient. Represents the time variable.

[0039] The specific process includes, when calculating the temperature gradient change rate, based on the temperature distribution range provided by the target temperature interval and the heat conduction characteristics characterized by the material thermal conductivity, applying Fourier's law of heat conduction to establish the spatio-temporal evolution relationship of the temperature field. By solving the second-order partial derivatives of the temperature field in the three-dimensional coordinate system of the baking tray, the temperature gradient change characteristics of each spatial point are obtained, where the temperature gradient components of the horizontal coordinate, vertical coordinate, and vertical coordinate are weighted and synthesized according to the spatial weight coefficient to form the temperature gradient change rate reflecting the actual heat conduction characteristics.

[0040] Furthermore, the gradient threshold is set according to the safe operating temperature range of the baking tray material and the thermal stress distribution characteristics, and is used to identify the key areas in the temperature field that need to be partitioned and regulated. When the originally calculated temperature gradient exceeds the gradient threshold in real time, a dynamic generation mechanism for three-dimensional temperature field partition parameters is triggered. Combining the smooth transition characteristics of the hyperbolic tangent function and the dynamic adjustment effect of the time decay coefficient, three-dimensional temperature field partition parameters matching the current thermal state are generated. The role of the gradient threshold is to ensure that the temperature field partition can respond to thermal anomalies in a timely manner and avoid frequent partition adjustments caused by instantaneous fluctuations. In the example, the gradient threshold for the stainless steel baking tray is set to 15 °C / cm, and for the aluminum alloy baking tray is 20 °C / cm.

[0041] S2.3: When the temperature gradient change rate exceeds the dynamic learning activation limit value, trigger the dynamic learning flag.

[0042] The specific process includes, the dynamic learning activation limit value is comprehensively determined according to the safe operating temperature range of the baking tray material, the thermal stress distribution characteristics, and the temperature gradient statistical value in the historical operation data, and is used to distinguish the normal heat conduction state from the abnormal state that requires dynamic adjustment. When the temperature gradient change rate calculated in real time exceeds the dynamic learning activation limit value, the dynamic learning flag is immediately activated, triggering the update mechanism of the thermal inertia compensation parameter. The role of the dynamic learning activation limit value is to establish a critical criterion for temperature field regulation. In the example, the dynamic learning activation limit value for the stainless steel baking tray is 15 °C / cm, and this value is derived from the correlation analysis of the material yield strength and the coefficient of thermal expansion, ensuring that the dynamic learning process is started before the temperature gradient reaches the critical value that may affect the structural stability of the baking tray. The activation state of the dynamic learning flag is continuously maintained until the temperature gradient change rate drops below the dynamic learning activation limit value and operates stably for more than the set duration. The entire process uses a hardware comparison circuit to monitor the numerical relationship between the temperature gradient change rate and the dynamic learning activation limit value in real time, ensuring the real-time and reliability of the trigger of the dynamic learning flag.

[0043] S3: According to the dynamic learning flag, collect the furnace cavity temperature and the environmental temperature change rate in real time, calculate the power compensation amount through the thermal inertia compensation model, and generate a partitioned power control matrix in combination with the three-dimensional temperature field partition parameters.

[0044] S3.1: When it is detected that the dynamic learning flag is activated, collect the furnace cavity temperature field distribution data and the environmental temperature change rate in real time and perform space-time superposition to generate a three-dimensional compensation input matrix containing space-time characteristics.

[0045] Specifically, when it is detected that the dynamic learning flag is activated, immediately start the temperature sensor array to collect the furnace cavity temperature field distribution data at a fixed sampling frequency. The temperature sensor array is distributed along the X, Y, and Z axes of the baking tray three-dimensional coordinate system. Each sensor node records the temperature value of the corresponding spatial coordinate point. The environmental temperature change rate data is accurately synchronized with the temperature field distribution data through timestamps; after the collected environmental temperature change rate data undergoes space-time alignment processing, the temperature value of each spatial coordinate point is linearly superimposed with the environmental temperature change rate at the corresponding time point. All composite data units are arranged and combined according to the grid structure of the baking tray three-dimensional coordinate system, and finally a three-dimensional compensation input matrix with complete space-time characteristics is generated. Each element in the three-dimensional compensation input matrix contains information in three dimensions: spatial coordinates, temperature value, and environmental temperature change rate.

[0046] Furthermore, when generating the three-dimensional compensation input matrix containing space-time characteristics, map the collected furnace cavity temperature field distribution data to the three-dimensional grid nodes according to the spatial coordinate positions, and the environmental temperature change rate data is superimposed with the temperature values of each spatial node as a time dimension variable. In the example, the data of each grid node contains the temperature values in three spatial dimensions: horizontal coordinate, vertical coordinate, and vertical coordinate, as well as the environmental temperature change rate at the corresponding time point, forming a four-dimensional data set. After processing the missing data points through the space-time interpolation algorithm, the finally generated three-dimensional compensation input matrix completely retains the space-time evolution characteristics of the temperature field distribution.

[0047] S3.2: Use the furnace cavity temperature field distribution data and the environmental temperature change rate as the training set, and perform supervised learning training based on the labeled ideal compensation amount to generate a thermal inertia compensation model.

[0048] The specific process includes that the temperature sensor array collects the temperature field distribution data of the furnace cavity at a fixed sampling period. The example sampling period is 200 ms. At the same time, the ambient temperature sensor records the ambient temperature change rate based on the same time reference. After the collected original data is subjected to spatio-temporal alignment and normalization processing, the temperature field distribution data of the furnace cavity at each sampling moment and the ambient temperature change rate are combined into training samples. For example, a 300 mm × 200 mm baking tray area is divided into 15 × 10 grid points, and the temperature value of each grid point and the ambient temperature change rate at the corresponding moment together form a 150-dimensional feature vector. The labeled ideal compensation amount is derived from the compensation power required for each grid point under the standard working conditions determined by experiments, forming label data that corresponds one-to-one with the feature vector.

[0049] Specifically, when performing supervised learning training, the gradient descent method is used to optimize the parameters of the thermal inertia compensation model. Each iteration optimizes the mean square error between the predicted compensation amount output by the thermal inertia compensation model and the labeled ideal compensation amount. The structure of the thermal inertia compensation model includes a three-layer fully connected network. The input layer processes the 150-dimensional feature vector. The hidden layer is set with 64 neurons and uses the ReLU activation function. The output layer generates a compensation amount prediction value that matches the input dimension. During the training process, the learning rate is dynamically adjusted. For example, the initial learning rate is set to 0.001 and decays by 50% every 10 epochs until the prediction error on the validation set is less than 5 W / m², at which point the training is completed, and finally a thermal inertia compensation model that can output an accurate compensation amount based on the real-time input temperature field distribution data of the furnace cavity and the ambient temperature change rate is obtained.

[0050] S3.3: Use the three-dimensional compensation input matrix as the input parameter of the thermal inertia compensation model, and calculate the power compensation amount based on the gradient optimization algorithm. The expression is: ; Among them, represents the power compensation amount, represents the non-linear mapping function, represents the integral domain of the three-dimensional temperature field and the time variable, represents the three-dimensional dynamic feature matrix containing the spatial distribution of the furnace cavity temperature field and its spatio-temporal gradient, represents the compensation weight coefficient in the horizontal direction of the spatial coordinate axis, represents the compensation weight coefficient in the vertical direction of the spatial coordinate axis, represents the spatio-temporal convolution operator, represents the column vector of the temperature field distribution, represents the heat conduction stiffness matrix, represents the heat conduction stiffness matrix and the product of the column vector of the temperature field distribution , represents the natural exponential function, represents the attenuation intensity coefficient, Denote the partial differential of the temperature field feature matrix Denote the time differential term Denote the Frobenius norm

[0051] The specific process includes that when taking the three-dimensional compensation input matrix as the input parameter of the thermal inertia compensation model, first perform standardization processing on the input data to normalize the spatial distribution value of the temperature field to the range of 0-1; the thermal inertia compensation model processes the three-dimensional dynamic feature matrix through a spatio-temporal convolution operator, and the reference response function of the spatio-temporal convolution kernel adopts a Gaussian decay form. During the calculation process, the compensation weight coefficient in the spatial coordinate direction and the compensation weight coefficient in the spatial coordinate direction respectively perform Hadamard product operations with the partial differential of the temperature field feature matrix, and the time differential term calculates the data change rate of adjacent time steps through the central difference method; the intelligent convolution kernel dynamically adjusts the convolution weights according to the training parameter set. The calculation process of the power compensation amount includes three main steps: first, discretize the integration domain of the three-dimensional temperature field and the time variable, secondly, transform the spatio-temporal features through a non-linear mapping function, and finally use the Frobenius norm to constrain the energy range of the output result; the gradient optimization algorithm uses the adaptive moment estimation method to update the parameters. For example, the initial learning rate is set to 0.001. Calculate the mean square error between the power compensation amount and the target value during each iteration and backpropagate to update the parameters of the intelligent convolution kernel until the loss function converges.

[0052] S3.4: According to the three-dimensional temperature field partition parameters, divide the furnace cavity into multiple sub-regions with different thermal inertia response characteristics, and establish a dynamic heat conduction relationship for each sub-region.

[0053] Specifically, when dividing the sub-regions with different thermal inertia response characteristics, determine the regional boundaries based on the spatial temperature gradient distribution and the difference in material thermal conductivity in the three-dimensional temperature field partition parameters. The geometric size of each sub-region is determined by the spatial sampling density of the temperature field. For example, on a baking tray of 300mm×300mm, when using a sampling grid of 15×15, each sub-region corresponds to an actual physical area of 20mm×20mm; after the division, assign an independent thermal inertia response characteristic identifier to each sub-region, including the reference temperature value, the maximum temperature fluctuation range, and the material characteristic parameters of each sub-region.

[0054] Furthermore, the heat conduction relationship refers to the quantitative relationship that describes the law of heat energy transfer between adjacent sub-regions, including conduction intensity, directionality, and time response characteristics. A heat flow transfer path is established based on the physical adjacency relationship and temperature gradient direction between sub-regions. The dynamic heat conduction equation for each sub-region contains three terms: the self-thermal inertia term of this region is represented by the product of the temperature change rate and heat capacity, the neighborhood conduction term is calculated using Fourier's law, and the environmental coupling term considers boundary heat exchange. In the example, the self-thermal inertia term coefficient of a 20mm×20mm aluminum alloy sub-region is 2.3 J / (℃·s), and the conduction coefficient with the adjacent stainless steel region is 0.8 W / (m·K). The parameters of the dynamic heat conduction relationship are identified online through the temperature field data collected in real time, and the conduction coefficient is updated every 60 seconds using the recursive least squares method to ensure that the heat conduction relationship is synchronized with the actual working conditions.

[0055] S3.5: Input the dynamic heat conduction relationship of each sub-region into the pre-trained adaptive compensation mechanism and generate a partition power control matrix that matches the temperature field partition.

[0056] The specific process includes that when inputting the dynamic heat conduction relationship of the sub-region, the pre-trained adaptive compensation mechanism first analyzes the self-thermal inertia term coefficient, neighborhood conduction coefficient, and environmental coupling parameters of each sub-region. In the example, the 2.3 J / (℃·s) self-thermal inertia term coefficient of the aluminum alloy sub-region and the 0.8 W / (m·K) neighborhood conduction coefficient are combined into a feature vector. After the feature vector is normalized, it forms a compensation input tensor together with the spatial coordinate information of the temperature field partition. The pre-trained adaptive compensation mechanism processes the compensation input tensor through a three-layer fully connected network. The first layer maps the feature dimension from 5 dimensions to 16 dimensions, the second layer uses the LeakyReLU activation function for non-linear transformation, and the third layer outputs the preliminary compensation coefficients of each sub-region.

[0057] Furthermore, when pre-training the adaptive compensation mechanism, supervised learning training is carried out using the historical working condition data set. The historical working condition data set contains the corresponding relationship between the sub-region heat conduction parameters and the optimal compensation coefficients under 100 different heating curves. The training process uses the stochastic gradient descent method with momentum, the initial learning rate is set to 0.01 and decays by 30% every 20 epochs, and the loss function calculates the mean square error between the predicted compensation coefficient and the measured optimal value. Through the Hadamard product matrix multiplication operation method, the three-dimensional compensation coefficient matrix generated by the adaptive compensation mechanism is multiplied element by element with the spatial weight matrix of the temperature field partition, and finally a multi-dimensional partition power control matrix with spatial difference characteristics is output. The control coefficients of all sub-regions are reorganized according to the original spatial arrangement of the temperature field partition to form a two-dimensional power control matrix that completely corresponds to the partition geometric structure, and at the same time, the time dimension change rate is added to form a multi-dimensional partition power control matrix.

[0058] S4: Allocate the power compensation amount and the partition power control matrix to the heating tubes according to the preset topology, dynamically adjust the power output, and implement temperature early warning and no-load identification based on the acoustic emission spectrum entropy value.

[0059] S4.1: Map the obtained power compensation amount and the partition power control matrix to the heating tube control unit according to the preset heating tube topology relationship, and generate the dynamic coupling parameters between adjacent tubes.

[0060] The specific process includes forming a spatial position correspondence table of the heating tube topology relationship through the geometric matching relationship between the pre-established physical layout coordinates of the heating tubes and the temperature field partition grid. The physical layout coordinates of the heating tubes are the spatial coordinate data of the installation positions of the heating tubes measured by a laser three-dimensional scanner, and are established based on the installation positioning reference points in the mechanical design drawings of the oven. Through the spatial position correspondence table of the heating tube topology relationship, each element index of the partition power control matrix is matched one by one with the spatial position of the heating tube topology relationship to establish a mapping relationship. The power compensation amount is allocated by area weighting of the area covered by the heating tubes. The final control instruction received by the heating tube control unit is linearly superimposed by three parts: the basic power setting value, the partition power control matrix allocation value, and the power compensation amount. For example, the basic value of 500W + the matrix allocation value of 80W + the compensation amount of 45W = 625W output power.

[0061] Furthermore, when generating the dynamic coupling parameters between adjacent tubes, determine the inter-tube thermal influence coefficient according to the adjacency matrix in the heating tube topology relationship. The adjacency matrix is generated by the preset heating tube spacing threshold and heat radiation range parameters. The dynamic coupling parameters include two components: the transient heat conductivity and the temperature gradient compensation factor. The transient heat conductivity is determined by the temperature difference between the surfaces of adjacent tubes collected in real time. The temperature gradient compensation factor is adjusted based on the difference in the power change rate of adjacent tubes. For example, when the power increase rate of the left heating tube is 2W / s and that of the right side is 1.5W / s, a compensation factor of 0.25 is generated; all coupling parameters are stored in a symmetric matrix according to the heating tube topology relationship for power coordination in the next cycle.

[0062] S4.2: Based on the dynamic coupling parameters, adjust the power output of each heating tube in real time through a closed-loop controller, synchronously collect the vibration signals of the heating tubes and calculate the spectrum entropy value. The expression is: ; where represents the spectrum entropy value at time, represents the total number of frequency bands divided, represents the frequency band index currently being calculated, represents the dynamic weight factor of the th frequency band at time, The normalized power spectral density of the ith frequency band, where is an index variable for the summation operation over frequency bands, and is the dynamic weight factor of the

[0063] ith

[0064] frequency band at time

[0065] Specifically, when adjusting the power output of the heating tubes based on the dynamic coupling parameters, the closed-loop controller first reads the coupling parameters in the stored symmetric matrix, such as the transient thermal conductivity of 0.8 W / (m·K) and the temperature gradient compensation factor of 0.25; according to the current operating states of each heating tube and the coupling relationship between adjacent tubes, the incremental PID algorithm is used to adjust the power output. For example, when it is detected that the temperature of the left heating tube rises too fast, its power set value is reduced by 15 W based on the compensation factor of 0.25; during the adjustment process, the dynamic coupling parameters are updated every 200 ms to ensure that the power output is synchronized with the real-time working conditions.

[0066] The specific process includes that the no-load determination threshold is determined based on the statistical analysis of the historical spectrum entropy value dataset collected under the standard load condition of the oven. The temperature sensor array acquires the vibration spectrum data of each partition in real time at a sampling frequency of 10 Hz, calculates the normalized power spectral density of 16 frequency bands after 512-point FFT transformation, and then obtains the current spectrum entropy value. When the spectrum entropy values of 5 consecutive sampling periods (corresponding to 0.5 seconds) all exceed the no-load determination threshold of 3.2, it is determined that the oven is in the no-load state. The role of the no-load determination threshold is to accurately distinguish the normal load condition from the no-load abnormal state and avoid misjudgment caused by temporary disturbances. After confirming the no-load state, a temperature anomaly warning signal including the coordinates of the abnormal partition and the entropy deviation degree is immediately generated. For example, the spectrum entropy value of the (x5, y7) partition is recorded as 3.5 and marked as a secondary warning, and at the same time, the power protection mechanism is triggered to limit the power output of the corresponding heating tube within a safe range.

[0067] S5: Iteratively optimize the thermal inertia compensation parameters and the temperature field partition parameters according to the power control data, temperature anomaly warning, and no-load identification results, and simultaneously generate an energy-saving control strategy and a temperature anomaly protection strategy under the no-load state.

[0068] S5.1: Based on the power control data, combined with the dynamic adjustment factors in the temperature anomaly warning and no-load identification results, generate an initial optimization parameter set for the thermal inertia compensation parameters and the temperature field partition parameters.

[0069] The specific process includes that based on the power control data (referring to the historical dataset recording the working state of the heating tube, including parameters such as voltage, current, power setting value, and actual output power. For example, the power output curve of the heating tube with the acquisition number H05 in the last 100 control cycles is collected), combined with the dynamic adjustment factors in the temperature anomaly warning and no-load identification results (referring to the weight coefficients that can correct the parameters in real time according to the change of the working condition, which are jointly determined by the spectrum entropy deviation degree and the load state coefficient. For example, the spectrum entropy deviation degree of 1.2 corresponds to a correction weight of 0.9), generate an initial optimization parameter set for the thermal inertia compensation parameters and the temperature field partition parameters.

[0070] Specifically, first extract the steady-state power value and transient adjustment amount in the power control data as the reference parameters. The spectrum entropy deviation degree provided by the temperature anomaly warning and the load state coefficient in the no-load identification result jointly constitute the dynamic adjustment factor. For example, when the spectrum entropy deviation degree reaches 1.2 and the load state coefficient is lower than 0.7, a dynamic attenuation coefficient of 0.85 is generated. The optimization process of the thermal inertia compensation parameters performs weighted fusion on the reference power parameters and the dynamic adjustment factor. The optimization of the temperature field partition parameters performs regional recalibration based on the spatial distribution characteristics in the power control data and the dynamic adjustment factor. The finally generated initial optimization parameter set includes 32-dimensional thermal inertia compensation parameters and 225-dimensional temperature field partition parameters, and all parameters are normalized and stored in the parameter matrix for calling in the control cycle.

[0071] S5.2: According to the initial optimization parameter set, iteratively update the weight of the temperature field partition parameters through the energy consumption balance logic, and generate an energy-saving control strategy and a temperature anomaly protection strategy based on the no-load recognition result.

[0072] The specific process includes: according to the initial optimization parameter set, iteratively update the weight of the temperature field partition parameters through the energy consumption balance logic, and generate an energy-saving control strategy (referring to a control scheme for optimizing energy consumption by reducing the power output in stages) and a temperature anomaly protection strategy (referring to a safety measure for preventing equipment damage by restricting the power change rate) based on the no-load recognition result. Specifically, when iteratively updating the weight of the temperature field partition parameters, the energy consumption balance logic first analyzes the energy consumption distribution characteristics of the 225-dimensional temperature field partition parameters in the initial optimization parameter set. For example, when it is detected that the energy consumption ratio in the central region exceeds 60%, the balance adjustment is triggered; the gradient descent method is used in the update process, and the weight of the high-energy consumption region is gradually reduced by 5% as the step size while the weight of the low-energy consumption region is increased. After each iteration, the overall energy consumption standard deviation is recalculated. When the standard deviation is less than the preset threshold of 5 W / m², the iteration stops, and finally, the balanced weight matrix of the temperature field partition parameters is output.

[0073] Furthermore, when generating the energy-saving control strategy and the temperature anomaly protection strategy based on the no-load recognition result, when the load status coefficient in the no-load recognition result is lower than 0.3, the energy-saving control strategy (referring to a control scheme for optimizing energy consumption by reducing the power output in stages) is activated. The energy-saving control strategy down-regulates the set value of the heating tube reference power in stages according to the no-load degree. The temperature anomaly protection strategy (referring to a safety measure for preventing equipment damage by restricting the power change rate) generates a protection level by comprehensively considering the deviation degree of the spectral entropy value and the load status coefficient. For example, when the deviation degree of the spectral entropy value is 1.5 and the load status coefficient is 0.4, the secondary protection is activated, and the power gradient of the adjacent heating tubes in the affected partition is restricted within 2 W / s; the parameters of both strategies are stored in matrix form. The energy-saving control strategy includes 5-level power adjustment coefficients (corresponding to power reduction ratios of 10%, 20%, 30%, 40%, and 50% in sequence), and the temperature anomaly protection strategy includes 3-level protection intensity parameters (restricting the power gradient to 3 W / s, 2 W / s, and 1 W / s respectively).

[0074] S5.3: Allocate the generated energy-saving control strategy to the corresponding heating tubes according to the partition energy consumption threshold, and at the same time associate the temperature anomaly protection strategy with the regulation interfaces of each partition.

[0075] The specific process includes that when allocating the energy-saving control strategy, the partition energy consumption threshold is preset based on the historical energy consumption peak and steady-state operating range of each partition in the initial optimization parameter set. The 5-level power adjustment coefficient in the energy-saving control strategy is matched and allocated according to the proportional relationship between the current energy consumption of the partition and the threshold. For example, when the real-time energy consumption of a certain partition reaches 120% of the threshold, the third-level adjustment coefficient of 0.7 is automatically applied to reduce the power to 70% of the original value. The allocation process is completed through the mapping table in the heating pipe topology relationship. Each heating pipe receives the energy-saving control parameters corresponding to its controlled partition. For example, the second-level adjustment coefficient of 0.85 is applied to the three partitions responsible for the heating pipe numbered H09.

[0076] Furthermore, when associating the temperature anomaly protection strategy, the regulation interfaces of each partition establish a binding relationship with the protection strategy according to the preset anomaly response priority. The preset anomaly response priority is obtained by analyzing the historical data distribution law of the temperature fluctuation characteristics of each partition, and the partitions exceeding the normal fluctuation range are marked as high-priority interfaces. The corresponding protection strategy level is automatically matched according to the preset priority, and the protection control parameters and thermal compensation parameters are synchronously sent to each partition control unit through the real-time communication protocol to form a priority-driven dynamic protection mechanism. The 3-level protection intensity parameters in the temperature anomaly protection strategy are dynamically associated according to the partition interface priority, and the association process is updated in real time to the parameter register of the heating pipe control unit.

[0077] S5.4: After executing the energy-saving control strategy, the temperature control deviation and energy consumption data are collected in real time, and the furnace body structure parameters are updated through the feedback correction mechanism and iteratively optimized.

[0078] The specific process includes that the feedback correction mechanism is a closed-loop control method that dynamically adjusts parameters according to the difference between the actual output and the expected target to update the furnace body structure parameters and perform iterative optimization. Specifically, after executing the energy-saving control strategy, the temperature sensor array collects the temperature control deviation data of each partition in real time at a sampling frequency of 2Hz, and the electric energy metering unit synchronously records the energy consumption data of each heating pipe. The feedback correction mechanism (a closed-loop control method that dynamically adjusts parameters according to the difference between the actual output and the expected target) first calculates the correlation coefficient between the temperature control deviation and the energy consumption change. The heat conduction coefficient and radiation efficiency parameters in the furnace body structure parameters are incrementally updated according to the correction weight. The iterative optimization process uses the moving window average method, and the parameter optimization amount is recalculated every 5 control cycles. The updated furnace body structure parameters are immediately applied to the strategy calculation of the next control cycle to form a closed-loop optimization.

[0079] This embodiment also provides a computer device applicable to the temperature control management method of an electric oven, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the temperature control management method of the electric oven as proposed in the above embodiment.

[0080] The computer device may be a terminal, which includes a processor, a memory, a communication interface, a display screen, and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0081] This embodiment also provides a storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the temperature control management method of the electric oven as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (abbreviated as SRAM), electrically erasable programmable read-only memory (abbreviated as EEPROM), erasable programmable read-only memory (abbreviated as EPROM), programmable read-only memory (abbreviated as PROM), read-only memory (abbreviated as ROM), magnetic memory, flash memory, a magnetic disk, or an optical disc.

[0082] In summary, in the present invention, by loading the target temperature range and three-dimensional temperature field partition parameters according to the cooking mode selected by the user, a high degree of adaptability to different cooking requirements is achieved. Further, by using Fourier's law of heat conduction to calculate the temperature gradient change rate and dynamically generate three-dimensional temperature field partition parameters, precise control of the temperature field in a complex three-dimensional space is ensured to cope with environmental changes and changes in user needs. This not only improves the accuracy of temperature control but also enhances the flexibility and intelligence level of the device, enabling the electric oven to better adapt to various cooking scenarios and improving the user experience.

[0083] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A temperature control management method for an electric oven, characterized in that: including, loading the furnace body structure parameters and performing zero calibration to generate a calibration matrix, and initializing the thermal inertia compensation parameters at the same time; performing offset correction on the pre-stored mode mapping table based on the calibration matrix, loading the target temperature range and three-dimensional temperature field partition parameters according to the selected cooking mode by the user, and triggering the dynamic learning flag; according to the dynamic learning flag, collecting the furnace cavity temperature and the ambient temperature change rate in real time, calculating the power compensation amount through the thermal inertia compensation model, and generating a partition power control matrix in combination with the three-dimensional temperature field partition parameters; allocating the power compensation amount and the partition power control matrix to the heating tubes according to the preset topology, dynamically adjusting the power output, and implementing temperature warning and no-load identification based on the acoustic emission spectrum entropy value; iteratively optimizing the thermal inertia compensation parameters and the temperature field partition parameters according to the power control data, temperature anomaly warning and no-load identification results, and synchronously generating an energy-saving control strategy and a temperature anomaly protection strategy in the no-load state.

2. The temperature control management method of the electric oven according to claim 1, characterized in that: The furnace body structure parameters include the baking tray size, the baking tray temperature distribution data, and the material thermal conductivity.

3. The temperature control management method of the electric oven according to claim 2, characterized in that: The step of loading the furnace body structure parameters and performing zero calibration to generate a calibration matrix, and initializing the thermal inertia compensation parameters at the same time is as follows. Based on the ice-water mixture environment, defining a reference value and generating a calibration matrix in combination with the spatial position weight factor; Initializing the thermal inertia compensation parameters according to the calibration matrix, and establishing a mapping relationship between the thermal inertia compensation parameters and the three-dimensional temperature field partition.

4. The temperature control management method of the electric oven according to claim 3, characterized in that: The step of performing offset correction on the pre-stored mode mapping table based on the calibration matrix, loading the target temperature range and the three-dimensional temperature field partition parameters according to the selected cooking mode by the user, and triggering the dynamic learning flag is as follows. Defining a dynamic reference temperature range through the mapping relationship between the thermal inertia compensation parameters and the three-dimensional temperature field partition, and generating a target temperature range according to the current furnace body structure; Based on the target temperature range and the material thermal conductivity, calculating the temperature gradient change rate according to Fourier's law of heat conduction, and dynamically generating three-dimensional temperature field partition parameters according to the gradient threshold; When the temperature gradient change rate exceeds the dynamic learning activation limit value, triggering the dynamic learning flag.

5. The temperature control management method of the electric oven according to claim 4, characterized in that: The step of collecting the furnace cavity temperature and the ambient temperature change rate in real time according to the dynamic learning flag, and calculating the power compensation amount through the thermal inertia compensation model is as follows. When it is detected that the dynamic learning flag is activated, collecting the furnace cavity temperature field distribution data and the ambient temperature change rate in real time and performing space-time superposition to generate a three-dimensional compensation input matrix containing space-time characteristics; Taking the furnace cavity temperature field distribution data and the ambient temperature change rate as the training set, and performing supervised learning training based on the marked ideal compensation amount to generate a thermal inertia compensation model; Taking the three-dimensional compensation input matrix as the input parameter of the thermal inertia compensation model, and calculating the power compensation amount based on the gradient optimization algorithm.

6. The temperature control management method of the electric oven according to claim 5, characterized in that: The step of generating a partition power control matrix in combination with the three-dimensional temperature field partition parameters is as follows. According to the three-dimensional temperature field partition parameters, dividing the furnace cavity into multiple sub-regions with different thermal inertia response characteristics, and establishing a dynamic heat conduction relationship for each sub-region; Inputting the dynamic heat conduction relationship of each sub-region into the pre-trained adaptive compensation mechanism, and generating a partition power control matrix matching the temperature field partition.

7. The temperature control management method of the electric oven according to claim 6, characterized in that: The steps of allocating the power compensation amount and the partition power control matrix to the heating tubes according to a preset topology, dynamically adjusting the power output, and implementing temperature early warning and no-load identification based on the acoustic emission spectrum entropy value are as follows: Map the obtained power compensation amount and the partition power control matrix to the heating tube control unit according to the preset heating tube topology relationship, and generate dynamic coupling parameters between adjacent tubes; Based on the dynamic coupling parameters, adjust the power output of each heating tube in real time through a closed-loop controller, synchronously collect the vibration signals of the heating tubes, and calculate the spectrum entropy value; When the spectrum entropy value continuously exceeds the no-load determination threshold, it is considered that the current oven is in a no-load state, and a temperature anomaly early warning is generated.

8. The temperature control management method of the electric oven according to claim 7, characterized in that: The steps of iteratively optimizing the thermal inertia compensation parameters and the temperature field partition parameters according to the power control data, the temperature early warning state, and the no-load identification result, and synchronously generating an energy-saving control strategy and a temperature anomaly protection strategy under the no-load state are as follows: Based on the power control data, combined with the dynamic adjustment factors in the temperature anomaly early warning and the no-load identification result, generate an initial optimization parameter set for the thermal inertia compensation parameters and the temperature field partition parameters; According to the initial optimization parameter set, iteratively update the weight of the temperature field partition parameters through the energy consumption balance logic, and generate an energy-saving control strategy and a temperature anomaly protection strategy based on the no-load identification result; Allocate the generated energy-saving control strategy to the corresponding heating tubes according to the partition energy consumption threshold, and at the same time associate the temperature anomaly protection strategy with the regulation interfaces of each partition; After executing the energy-saving control strategy, collect the temperature control deviation and energy consumption data in real time, and update the furnace body structure parameters through a feedback correction mechanism and perform iterative optimization.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the temperature control management method of the electric oven according to any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the temperature control management method of the electric oven according to any one of claims 1 to 8.

Images