Dynamic temperature adjusting method and system for oven

Abstract

The invention relates to the technical field of oven temperature control, and discloses a dynamic temperature adjusting method and system for an oven, and the method comprises the steps: obtaining food types, food weight, initial set temperature and real-time temperature data; the baking stage temperature of each baking stage is calculated according to the food type, the food weight and the initial set temperature, wherein the baking stage temperature comprises the first stage temperature, the second stage temperature, the third stage temperature and the fourth stage temperature; the food type, the food weight and the baking stage temperature are input into a pre-trained decision tree model, baking stage time is obtained, and the baking stage time comprises the first stage time, the second stage time, the third stage time and the fourth stage time; and dynamically adjusting the baking temperature according to the baking stage temperature, the baking stage time and the real-time temperature data in combination with a fuzzy PID control algorithm. The method improves baking quality and energy utilization rate.

Description

Technical Field

[0001] The present invention relates to the technical field of oven temperature control, and in particular to a method and system for dynamically adjusting the temperature of an oven. Background Art

[0002] With the improvement of living standards, the functionality and intelligence of household appliances are also constantly improving. As a common kitchen appliance, the main function of the oven is to cook food by heating. Modern users have increasing requirements for baking quality. They not only pursue delicious food, but also expect to ensure food safety and achieve energy saving. Therefore, in order to meet the requirements of the oven to provide uniform and stable heat distribution and optimize the energy efficiency of the oven, developing an oven temperature adjustment method that can achieve precise and fast response has become an important direction of modern oven design.

[0003] Existing ovens use PID algorithms to regulate internal temperature stability. First, a target temperature is set as the expected value input into the control system. Next, the temperature sensor continuously monitors the actual temperature inside the oven and feeds this real-time data back to the controller. After receiving the signal from the sensor, the controller calculates the deviation between the current actual temperature and the set target temperature. Then, based on this deviation value, it combines the three parameters of proportional, integral and differential for calculation. The proportional part directly adjusts the output according to the current deviation; the integral part accumulates past deviations to take into account long-term errors; and the differential part predicts future trend changes and reacts in advance by evaluating the rate of change of the deviation. These calculation results jointly determine the working state of the heating element, that is, whether it is on or off and the power level. Based on the operating instructions obtained from the above calculations, the controller issues corresponding control commands to the heating device to adjust its working intensity, thereby affecting the temperature rise and fall in the oven. As the temperature changes, this process continues to repeat, and the temperature sensor continues to monitor the new temperature value and feeds it back to the controller, ensuring that the entire system is always in dynamic adjustment and maintaining a continuous and smooth temperature control process.

[0004] In the prior art, in the early stage of baking, the temperature inside the oven fluctuates greatly due to external factors, which may cause the temperature to be higher than the preset temperature, affecting the baking effect, especially for foods that take a long time to bake. In the middle and late stages of baking, the oven needs to increase the temperature multiple times to offset the impact of external factors on the temperature. However, as the baked food matures, the required baking temperature will continue to decrease. Continuously increasing the temperature of the oven not only wastes energy, but also creates a risk of overheating of the oven. Therefore, the prior art cannot adjust the baking temperature according to the type of food and baking time, resulting in low baking quality and low energy utilization. Summary of the invention

[0005] The present invention provides a method and system for dynamically adjusting the temperature of an oven, so as to adjust the baking temperature according to the type of food and the baking time, thereby improving the baking quality and energy utilization rate.

[0006] In a first aspect, in order to solve the above technical problems, the present invention provides a method for dynamic temperature adjustment of an oven, comprising:

[0007] Obtain food type, food weight, initial set temperature and real-time temperature data;

[0008] Calculating the baking stage temperature of each baking stage according to the food type, the food weight and the initial setting temperature, wherein the baking stage temperatures include a first stage temperature, a second stage temperature, a third stage temperature and a fourth stage temperature;

[0009] Inputting the food type, the food weight and the baking stage temperature into a pre-trained decision tree model to obtain the baking stage time, wherein the baking stage time includes the first stage time, the second stage time, the third stage time and the fourth stage time;

[0010] The baking temperature is dynamically adjusted according to the baking stage temperature, the baking stage time and the real-time temperature data in combination with a fuzzy PID control algorithm.

[0011] In an optional embodiment, the step of calculating the baking stage temperature of each baking stage according to the food type, the food weight and the initial set temperature includes:

[0012] The baking stage temperature is calculated by the following formula:

[0013] T1=T0+C·m·ΔT1

[0014]

[0015] T3=T2-c·log(m)·ΔT3

[0016] T4=T3-c·m 2 -ΔT4

[0017] Among them, T0 represents the initial set temperature, T1 represents the first stage temperature, T2 represents the second stage temperature, T3 represents the third stage temperature, T4 represents the fourth stage temperature, c represents the preset food type coefficient, m represents the food weight, ΔT1 represents the preset first stage basic temperature increment, ΔT2 represents the preset second stage basic temperature increment, ΔT3 represents the preset third stage basic temperature increment, and ΔT4 represents the preset fourth stage basic temperature increment.

[0018] In an optional implementation, the training process of the decision tree model includes:

[0019] Perform data cleaning and data standardization on the pre-stored historical food types, corresponding historical food weights, and historical baking stage temperatures to obtain pre-processed data;

[0020] Comprehensive feature extraction is performed based on the historical food types, the historical food weights, and the historical baking stage temperatures to obtain feature data;

[0021] Use the Gini index to evaluate the purity of each feature data, and select the feature with the lowest Gini index as the best split feature;

[0022] Splitting the data set of the parent node according to the optimal splitting feature to obtain multiple subsets, each subset corresponding to a new child node;

[0023] When the samples of the child node do not belong to the same category feature and the samples of the child node have features that can be used for further classification, and the number of samples contained in the child node is more than a preset threshold or does not reach a preset maximum tree depth, the child node continues to split;

[0024] When the samples of the child node belong to the same category feature or the samples of the child node do not have features that can be used for further classification or the number of samples contained in the child node is less than a preset threshold or reaches a preset maximum tree depth, the child node stops splitting, and the child node should be marked as a leaf node, and a classification result is given according to the category distribution of the samples of the child node;

[0025] When all child nodes stop splitting, the decision tree is pruned using a pruning optimization algorithm to obtain a trained decision tree model.

[0026] In an optional implementation, the use of the Gini index to evaluate the purity of each feature data and selecting the feature with the lowest Gini index as the best split feature includes:

[0027] The Gini index is calculated using the following formula:

[0028]

[0029] in, Represents feature category c i feature data set, D represents the feature data set, C represents the total number of feature categories, p(c i ) represents the feature category c i The probability in the feature data set, Gini(D) represents the Gini index of the feature data set.

[0030] In an optional embodiment, dynamically adjusting the baking temperature according to the baking stage temperature, the baking stage time and the real-time temperature data in combination with a fuzzy PID control algorithm comprises:

[0031] According to the first stage temperature control, the oven bakes at maximum power, the oven enters the first baking stage and starts recording the baking time;

[0032] When the real-time temperature data reaches the first stage temperature, a first correction temperature is calculated according to the real-time temperature data and the first stage temperature in combination with a fuzzy PID control algorithm;

[0033] Adjust the output power of the oven according to the real-time temperature data and the first corrected temperature, and control the real-time temperature data to reach the first corrected temperature;

[0034] When the real-time temperature data does not reach a preset error range centered on the first correction temperature and the baking time reaches the first stage time, the output power is adjusted according to the real-time temperature data and the first correction temperature and the first stage time is extended according to a preset delay step;

[0035] When the real-time temperature data reaches a preset error range centered on the first correction temperature and the baking time reaches the first stage time, the second baking stage is entered;

[0036] Calculate a second corrected temperature based on the real-time temperature data and the second stage temperature in combination with a fuzzy PID control algorithm;

[0037] According to the real-time temperature data and the second corrected temperature, the output power of the oven is adjusted to control the real-time temperature data to reach the second corrected temperature;

[0038] When the real-time temperature data does not reach a preset error range centered on the second corrected temperature and the baking time reaches the second stage time, the output power is adjusted according to the real-time temperature data and the second corrected temperature and the second stage time is extended according to a preset delay step;

[0039] When the real-time temperature data reaches a preset error range centered on the second corrected temperature and the baking time reaches the second stage time, the third baking stage is entered;

[0040] Calculate a third corrected temperature based on the real-time temperature data and the third stage temperature in combination with a fuzzy PID control algorithm;

[0041] Adjust the output power of the oven according to the real-time temperature data and the third corrected temperature, and control the real-time temperature data to reach the third corrected temperature;

[0042] When the real-time temperature data does not reach a preset error range centered on the third corrected temperature and the baking time reaches the third stage time, the output power is adjusted according to the real-time temperature data and the third corrected temperature and the third stage time is extended according to a preset delay step;

[0043] When the real-time temperature data reaches a preset error range centered on the third corrected temperature and the baking time reaches the third stage time, the fourth baking stage is entered;

[0044] Calculate a fourth corrected temperature based on the real-time temperature data and the fourth stage temperature in combination with a fuzzy PID control algorithm;

[0045] According to the real-time temperature data and the fourth corrected temperature, the output power of the oven is adjusted to control the real-time temperature data to reach the fourth corrected temperature;

[0046] When the real-time temperature data does not reach a preset error range centered on the fourth corrected temperature and the baking time reaches the fourth stage time, the output power is adjusted according to the real-time temperature data and the fourth corrected temperature and the fourth stage time is extended according to a preset delay step;

[0047] When the real-time temperature data reaches a preset error range centered on the fourth corrected temperature and the baking time reaches the fourth stage time, the baking ends.

[0048] In an optional implementation, the implementation process of the fuzzy PID control algorithm includes:

[0049] Calculate the error between the baking stage temperature and the real-time temperature data at the current moment to obtain a current temperature error;

[0050] Calculate the difference between the current temperature error and the historical temperature error stored at the previous moment to obtain the error change rate;

[0051] Calculating the degree of membership using a Gaussian membership function according to the current temperature error and the error change rate;

[0052] Performing fuzzy reasoning using a weighted average method according to the membership degree and predefined fuzzy rules to obtain a fuzzy output;

[0053] Adjusting PID parameters according to the fuzzy output to obtain proportional correction parameters, integral correction parameters and differential correction parameters;

[0054] Calculating an error correction coefficient according to the current temperature error, the proportional correction parameter, the integral correction parameter and the differential correction parameter;

[0055] Calculate the stage correction temperature according to the error correction coefficient and the real-time temperature data, wherein the correction stage temperature includes a first correction temperature, a second correction temperature, a third correction temperature and a fourth correction temperature;

[0056] Among them, the membership degree is calculated by:

[0057]

[0058] The fuzzy output is calculated by the following formula:

[0059]

[0060] Adjust the PID parameters by the following formula:

[0061] K′ p =K p +ΔK p

[0062] K′ i =K i +ΔK i

[0063] K′ d =K d +ΔK d

[0064] The error correction factor is calculated using the following formula:

[0065]

[0066] The stage corrected temperature is calculated by the following formula:

[0067] T corrected =T target +C e

[0068] Among them, μ NB (E(t)) represents the negative large temperature error membership, μ ZO (E(t)) represents the zero temperature error membership, μ PB (E(t)) represents the positive temperature error membership, E(t) represents the current temperature error, c E Represents the preset temperature error center coefficient, σ E Represents the pre-stored temperature error standard deviation, μ NB (ΔE(t)) represents the negative large change rate membership, μ ZO (ΔE(t)) represents the zero-rate membership, μ PB (ΔE(t)) represents the positive change rate membership, ΔE(t) represents the error change rate, c ΔE Represents the preset error change rate center coefficient, σΔE Indicates the standard deviation of the pre-stored error change rate, ΔK p Indicates the proportional integrated fuzzy output, ΔK i Indicates the integral comprehensive fuzzy output, ΔK d represents the differential integrated fuzzy output, w i represents the weight corresponding to the i-th fuzzy rule, x pi represents the proportional fuzzy output under the i-th fuzzy rule, x ii represents the integral fuzzy output under the i-th fuzzy rule, x di represents the differential fuzzy output under the i-th fuzzy rule, K′ p Represents the proportional correction coefficient, K′ i Indicates the integral correction coefficient, K′ d Denotes the differential correction coefficient, K p Represents the proportionality coefficient, K i Indicates the integral coefficient, K d represents the differential coefficient, τ represents the preset time step, C e represents the error correction factor, T target Indicates the baking stage temperature, T corrected Indicates the correction stage temperature.

[0069] In an optional embodiment, adjusting the output power of the oven according to the real-time temperature data and the first corrected temperature to control the real-time temperature data to reach the first corrected temperature includes:

[0070] Calculate the oven's output power using the following formula:

[0071] E′(t)=T corrected -T real

[0072]

[0073] Among them, P(t) represents the adjusted output power, P0 represents the output power at the current moment, and P N represents the rated power, E′(t) represents the correction error, T corrected Indicates the correction stage temperature, T real Indicates real-time temperature, K′ p Represents the proportional correction coefficient, K′ i Indicates the integral correction coefficient, K′ d represents the differential correction coefficient, and τ represents the preset time step.

[0074] In a second aspect, the present invention provides a dynamic temperature adjustment system for an oven, comprising:

[0075] A data acquisition module is used to obtain food type, food weight, initial set temperature and real-time temperature data;

[0076] a stage temperature calculation module, used for calculating the baking stage temperature of each baking stage according to the food type, the food weight and the initial set temperature, wherein the baking stage temperature includes a first stage temperature, a second stage temperature, a third stage temperature and a fourth stage temperature;

[0077] a stage time calculation module, for inputting the food type, the food weight and the baking stage temperature into a pre-trained decision tree model to obtain the baking stage time, wherein the baking stage time includes the first stage time, the second stage time, the third stage time and the fourth stage time;

[0078] The dynamic temperature adjustment module is used to dynamically adjust the baking temperature according to the baking stage temperature, the baking stage time and the real-time temperature data in combination with a fuzzy PID control algorithm.

[0079] In a third aspect, the present invention further provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements any one of the above-mentioned methods for dynamic temperature adjustment of an oven when executing the computer program.

[0080] In a fourth aspect, the present invention further provides a computer-readable storage medium, the computer-readable storage medium comprising a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned methods for dynamic temperature adjustment of an oven.

[0081] Compared with the prior art, the present invention has the following beneficial effects:

[0082] The invention discloses a dynamic temperature adjustment method for an oven, comprising obtaining food type, food weight, initial setting temperature and real-time temperature data; calculating the baking stage temperature of each baking stage according to the food type, food weight and initial setting temperature, wherein the baking stage temperature includes the first stage temperature, the second stage temperature, the third stage temperature and the fourth stage temperature; inputting the food type, the food weight and the baking stage temperature into a pre-trained decision tree model to obtain the baking stage time, wherein the baking stage time includes the first stage time, the second stage time, the third stage time and the fourth stage time; and dynamically adjusting the baking temperature according to the baking stage temperature, the baking stage time and the real-time temperature data in combination with a fuzzy PID control algorithm. The invention automatically calculates and adjusts the temperature and time of the four stages in the baking process according to the food type, food weight and initial setting temperature. The system uses the pre-trained decision tree model to determine the time of each baking stage, and dynamically adjusts the baking temperature in combination with the real-time temperature data and the fuzzy PID control algorithm, so as to adjust the baking temperature according to the food type and baking time, and improve the baking quality and energy utilization rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] Figure 1 is a schematic flow chart of a dynamic temperature adjustment method for an oven provided by a first embodiment of the present invention;

[0084] Figure 2 It is a structural schematic diagram of a dynamic temperature adjustment system of an oven provided in a second embodiment of the present invention. DETAILED DESCRIPTION

[0085] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0086] Reference Figure 1 The first embodiment of the present invention provides a method for dynamic temperature adjustment of an oven, comprising the following steps:

[0087] S11, obtain food type, food weight, initial set temperature and real-time temperature data

[0088] S12, calculating the baking stage temperature of each baking stage according to the food type, the food weight and the initial setting temperature, wherein the baking stage temperature includes a first stage temperature, a second stage temperature, a third stage temperature and a fourth stage temperature

[0089] S13, inputting the food type, the food weight and the baking stage temperature into a pre-trained decision tree model to obtain baking stage time, wherein the baking stage time includes a first stage time, a second stage time, a third stage time and a fourth stage time;

[0090] S14, dynamically adjusting the baking temperature according to the baking stage temperature, the baking stage time and the real-time temperature data in combination with a fuzzy PID control algorithm.

[0091] In step S11, food type, food weight, initial setting temperature and real-time temperature data are obtained.

[0092] The food type information is entered by the user through the oven's interactive interface, such as selecting a preset food type option or manually entering a specific food name. The food weight is directly measured by a high-precision electronic scale built into the bottom or inside the oven. When the food is placed in the oven, the electronic scale immediately detects and records the weight of the food. The initial set temperature comes from the user's instructions and is also set through the oven's control panel or touch screen, reflecting the user's desired starting baking temperature. At the same time, the system continues to collect real-time temperature data from temperature sensors installed in multiple locations inside the oven.

[0093] In step S12, the baking stage temperature of each baking stage is calculated according to the food type, the food weight and the initial setting temperature, wherein the baking stage temperatures include a first stage temperature, a second stage temperature, a third stage temperature and a fourth stage temperature.

[0094] In a specific embodiment, the step of calculating the baking stage temperature of each baking stage according to the food type, the food weight and the initial set temperature includes:

[0095] The baking stage temperature is calculated by the following formula:

[0096] T1=T0+c·m·ΔT1

[0097]

[0098] T3=T2-c·log(m)·ΔT3

[0099] T4=T3-c·m 2 ΔT4

[0100] Among them, T0 represents the initial set temperature, T1 represents the first stage temperature, T2 represents the second stage temperature, T3 represents the third stage temperature, T4 represents the fourth stage temperature, c represents the preset food type coefficient, m represents the food weight, ΔT1 represents the preset first stage basic temperature increment, ΔT2 represents the preset second stage basic temperature increment, ΔT3 represents the preset third stage basic temperature increment, and ΔT4 represents the preset fourth stage basic temperature increment.

[0101] Specifically, for a given food type, food weight, and initial set temperature, the system will use the following formula to determine the temperature for the four baking stages:

[0102] T1=T0+c·m·ΔT1

[0103]

[0104] T3=T2-c·log(m)·ΔT3

[0105] T4=T3-c·m 2 ΔT4

[0106] Among them, T0 represents the initial set temperature, T1 represents the first stage temperature, T2 represents the second stage temperature, T3 represents the third stage temperature, T4 represents the fourth stage temperature, c represents the preset food type coefficient, which reflects the temperature change requirements of different types of food during the baking process, m represents the food weight, ΔT1 represents the preset first stage basic temperature increment, ΔT2 represents the preset second stage basic temperature increment, ΔT3 represents the preset third stage basic temperature increment, and ΔT4 represents the preset fourth stage basic temperature increment.

[0107] The calculation starts with determining the first stage temperature T1 based on the initial set temperature T0 and the food weight m. Here, the product of the food type coefficient c and the food weight m is multiplied by the first stage basic temperature increment ΔT1 and added to the initial set temperature T0 to obtain the first stage temperature T1. This step ensures that the appropriate temperature can be quickly reached at the beginning of baking, laying a good foundation for subsequent baking.

[0108] Next, in order to enter the second stage, the system uses the first stage temperature T1 plus the increment calculated by the food type coefficient c, the square root of the food weight m, and the second stage basic temperature increment ΔT2 to determine the second stage temperature T2. The square root method takes into account that as the baking process progresses, the temperature rise rate should gradually slow down to avoid overheating and affecting food quality.

[0109] When transitioning to the third stage, the system subtracts a term consisting of the food type coefficient c, the natural logarithm of the food weight m, and the third stage basic temperature increment ΔT3 from the second stage temperature T2 to obtain the third stage temperature T3. The logarithmic function is introduced to reflect the trend of more precise and gradually lower temperature adjustment in the later stage of baking, to meet the needs when the food is close to completion.

[0110] Finally, when determining the fourth stage temperature T4, the system subtracts an amount determined by the food type coefficient c, the square of the food weight m, and the fourth stage basic temperature increment ΔT4 from the third stage temperature T3. This design allows for more precise temperature control at the end of baking, ensuring that the final product comes out of the oven perfectly.

[0111] The design of the entire algorithm not only takes into account the properties of the food itself (such as type and weight), but also combines the characteristics of different baking stages to achieve the goal of dynamically adjusting the baking temperature. This helps to improve the quality of baking while maximizing energy consumption.

[0112] In step S13, the food type, the food weight and the baking stage temperature are input into a pre-trained decision tree model to obtain the baking stage time, wherein the baking stage time includes the first stage time, the second stage time, the third stage time and the fourth stage time.

[0113] In a specific embodiment, the training process of the decision tree model includes:

[0114] Perform data cleaning and data standardization on the pre-stored historical food types, corresponding historical food weights, and historical baking stage temperatures to obtain pre-processed data;

[0115] Comprehensive feature extraction is performed based on the historical food types, the historical food weights, and the historical baking stage temperatures to obtain feature data;

[0116] Use the Gini index to evaluate the purity of each feature data, and select the feature with the lowest Gini index as the best split feature;

[0117] Splitting the data set of the parent node according to the optimal splitting feature to obtain multiple subsets, each subset corresponding to a new child node;

[0118] When the samples of the child node do not belong to the same category feature and the samples of the child node have features that can be used for further classification, and the number of samples contained in the child node is more than a preset threshold or does not reach a preset maximum tree depth, the child node continues to split;

[0119] When the samples of the child node belong to the same category feature or the samples of the child node do not have features that can be used for further classification or the number of samples contained in the child node is less than a preset threshold or reaches a preset maximum tree depth, the child node stops splitting, and the child node should be marked as a leaf node, and a classification result is given according to the category distribution of the samples of the child node;

[0120] When all child nodes stop splitting, the decision tree is pruned using a pruning optimization algorithm to obtain a trained decision tree model.

[0121] In a specific implementation, the use of the Gini index to evaluate the purity of each feature data and selecting the feature with the lowest Gini index as the best split feature includes:

[0122] The Gini index is calculated using the following formula:

[0123]

[0124] in, Represents feature category c i feature data set, D represents the feature data set, C represents the total number of feature categories, p(c i ) represents the feature category c i The probability in the feature data set, Gini(D) represents the Gini index of the feature data set.

[0125] Specifically, the training of the decision tree model is based on historical data, which contains the food types, corresponding food weights, and temperature information of each baking stage recorded in the previous baking process. First, these pre-stored historical data are cleaned and standardized to remove noise or outliers and adjust the value range for subsequent analysis, so as to obtain high-quality pre-processed data. Then, comprehensive feature extraction is performed based on the historical food types, food weights, and baking stage temperatures to generate feature data that can be used for training. This process aims to identify the key attributes that most affect baking time.

[0126] In order to build a decision tree, the Gini index is used as a metric to evaluate the purity of each feature data, that is, the effectiveness of the feature for classification. The lower the Gini index, the stronger the ability of the feature to split the data set, and the more suitable it is as a basis for splitting. Specifically, the formula for calculating the Gini index is as follows:

[0127]

[0128] here, Represents feature category c i feature data set, D represents the feature data set, C represents the total number of feature categories, p(ci ) represents the feature category c i The probability in the feature data set, Gini(D) represents the Gini index of the feature data set. After calculating the Gini index of each feature through the above formula, the feature with the lowest Gini index is selected as the best split feature to decide how to divide the data set of the parent node to form multiple subsets, each of which corresponds to a new child node.

[0129] As the splitting process continues, when the samples of a child node no longer all belong to the same category or there are features that can be used for further classification, and the number of samples contained in the child node exceeds the preset threshold and does not reach the set maximum tree depth, the child node will continue to split. On the contrary, if the samples of the child node all belong to the same category, there are no features that can be used for further classification, the number of samples is lower than the threshold, or the maximum tree depth is reached, the splitting stops and the node is marked as a leaf node. The leaf node gives the final classification result based on the category distribution of the samples it contains, that is, the baking phase time.

[0130] Once all possible split operations are completed, the decision tree will go through a pruning optimization process. Pruning is to prevent overfitting, that is, the model is too complex to overfit the training data but has poor generalization ability to external data. The pruning algorithm removes those branches that contribute little or even no help to improve the prediction accuracy, simplifies the decision tree structure, and enhances the robustness and accuracy of the model. After this series of operations, a trained decision tree model is finally obtained. The model can effectively output the corresponding baking stage time when receiving new food types, weights, and baking stage temperatures, thereby guiding the oven to achieve more accurate dynamic temperature regulation.

[0131] In step S14, the baking temperature is dynamically adjusted according to the baking stage temperature, the baking stage time and the real-time temperature data in combination with a fuzzy PID control algorithm.

[0132] In a specific embodiment, dynamically adjusting the baking temperature according to the baking stage temperature, the baking stage time and the real-time temperature data in combination with a fuzzy PID control algorithm comprises:

[0133] According to the first stage temperature control, the oven bakes at maximum power, the oven enters the first baking stage and starts recording the baking time;

[0134] When the real-time temperature data reaches the first stage temperature, a first correction temperature is calculated according to the real-time temperature data and the first stage temperature in combination with a fuzzy PID control algorithm;

[0135] Adjust the output power of the oven according to the real-time temperature data and the first corrected temperature, and control the real-time temperature data to reach the first corrected temperature;

[0136] When the real-time temperature data does not reach a preset error range centered on the first correction temperature and the baking time reaches the first stage time, the output power is adjusted according to the real-time temperature data and the first correction temperature and the first stage time is extended according to a preset delay step;

[0137] When the real-time temperature data reaches a preset error range centered on the first correction temperature and the baking time reaches the first stage time, the second baking stage is entered;

[0138] Calculate a second corrected temperature based on the real-time temperature data and the second stage temperature in combination with a fuzzy PID control algorithm;

[0139] According to the real-time temperature data and the second corrected temperature, the output power of the oven is adjusted to control the real-time temperature data to reach the second corrected temperature;

[0140] When the real-time temperature data does not reach a preset error range centered on the second corrected temperature and the baking time reaches the second stage time, the output power is adjusted according to the real-time temperature data and the second corrected temperature and the second stage time is extended according to a preset delay step;

[0141] When the real-time temperature data reaches a preset error range centered on the second corrected temperature and the baking time reaches the second stage time, the third baking stage is entered;

[0142] Calculate a third corrected temperature based on the real-time temperature data and the third stage temperature in combination with a fuzzy PID control algorithm;

[0143] Adjust the output power of the oven according to the real-time temperature data and the third corrected temperature, and control the real-time temperature data to reach the third corrected temperature;

[0144] When the real-time temperature data does not reach a preset error range centered on the third corrected temperature and the baking time reaches the third stage time, the output power is adjusted according to the real-time temperature data and the third corrected temperature and the third stage time is extended according to a preset delay step;

[0145] When the real-time temperature data reaches a preset error range centered on the third corrected temperature and the baking time reaches the third stage time, the fourth baking stage is entered;

[0146] Calculate a fourth corrected temperature based on the real-time temperature data and the fourth stage temperature in combination with a fuzzy PID control algorithm;

[0147] According to the real-time temperature data and the fourth corrected temperature, the output power of the oven is adjusted to control the real-time temperature data to reach the fourth corrected temperature;

[0148] When the real-time temperature data does not reach a preset error range centered on the fourth corrected temperature and the baking time reaches the fourth stage time, the output power is adjusted according to the real-time temperature data and the fourth corrected temperature and the fourth stage time is extended according to a preset delay step;

[0149] When the real-time temperature data reaches a preset error range centered on the fourth corrected temperature and the baking time reaches the fourth stage time, the baking ends.

[0150] In a specific implementation, the implementation process of the fuzzy PID control algorithm includes:

[0151] Calculate the error between the baking stage temperature and the real-time temperature data at the current moment to obtain a current temperature error;

[0152] Calculate the difference between the current temperature error and the historical temperature error stored at the previous moment to obtain the error change rate;

[0153] Calculating the degree of membership using a Gaussian membership function according to the current temperature error and the error change rate;

[0154] Performing fuzzy reasoning using a weighted average method according to the membership degree and predefined fuzzy rules to obtain a fuzzy output;

[0155] Adjusting PID parameters according to the fuzzy output to obtain proportional correction parameters, integral correction parameters and differential correction parameters;

[0156] Calculating an error correction coefficient according to the current temperature error, the proportional correction parameter, the integral correction parameter and the differential correction parameter;

[0157] Calculate the stage correction temperature according to the error correction coefficient and the real-time temperature data, wherein the correction stage temperature includes a first correction temperature, a second correction temperature, a third correction temperature and a fourth correction temperature;

[0158] Among them, the membership degree is calculated by:

[0159]

[0160] The fuzzy output is calculated by the following formula:

[0161]

[0162] Adjust the PID parameters by the following formula:

[0163] K′ p =K p +ΔK p

[0164] K′ i =K i +ΔK i

[0165] K′ d =K d +ΔK d

[0166] The error correction factor is calculated using the following formula:

[0167]

[0168] The stage corrected temperature is calculated by the following formula:

[0169] T corrected =T target +C e

[0170] Among them, μ NB (E(t)) represents the negative large temperature error membership, μ ZO (E(t)) represents the zero temperature error membership, μ PB (E(t)) represents the positive temperature error membership, E(t) represents the current temperature error, c E Represents the preset temperature error center coefficient, σ E Represents the pre-stored temperature error standard deviation, μ NB (ΔE(t)) represents the negative large change rate membership, μ ZO (ΔE(t)) represents the zero-rate membership, μ PB (ΔE(t)) represents the positive change rate membership, ΔE(t) represents the error change rate, c ΔE Represents the preset error change rate center coefficient, σ ΔE Indicates the standard deviation of the pre-stored error change rate, ΔK p Indicates the proportional integrated fuzzy output, ΔK i Indicates the integral comprehensive fuzzy output, ΔK d represents the differential integrated fuzzy output, w i represents the weight corresponding to the i-th fuzzy rule, x pi represents the proportional fuzzy output under the i-th fuzzy rule, x ii represents the integral fuzzy output under the i-th fuzzy rule, x di represents the differential fuzzy output under the i-th fuzzy rule, K′ p Represents the proportional correction coefficient, K′i Indicates the integral correction coefficient, K′ d Denotes the differential correction coefficient, K p Represents the proportionality coefficient, K i Indicates the integral coefficient, K d represents the differential coefficient, τ represents the preset time step, C e represents the error correction factor, T target Indicates the baking stage temperature, T corrected Indicates the correction stage temperature.

[0171] In a specific implementation, the step of adjusting the output power of the oven according to the real-time temperature data and the first corrected temperature to control the real-time temperature data to reach the first corrected temperature includes:

[0172] Calculate the oven's output power using the following formula:

[0173] E′(t)=T corrected -T real

[0174]

[0175] Among them, P(t) represents the adjusted output power, P0 represents the output power at the current moment, and P N represents the rated power, E′(t) represents the correction error, T corrected Indicates the correction stage temperature, T real Indicates real-time temperature, K′ p Represents the proportional correction coefficient, K′ i Indicates the integral correction coefficient, K′ d represents the differential correction coefficient, and τ represents the preset time step.

[0176] Specifically, when baking starts, the oven sets the maximum power according to the first stage temperature to start the baking process, enters the first baking stage and starts timing. During this period, the temperature sensor installed inside the oven continuously monitors the actual temperature and feeds the data back to the control system. When the real-time temperature reaches the first stage temperature, the system uses the fuzzy PID control algorithm to calculate a more accurate first correction temperature. This correction value is based on the difference between the current real-time temperature and the expected first stage temperature.

[0177] Next, the system adjusts the output power of the oven to stabilize the real-time temperature at the first correction temperature. If the real-time temperature fails to remain within the preset error range centered on the first correction temperature during the specified first stage time, the control system first recalculates the current temperature error, readjusts the PID parameters, calculates the corresponding output power for adjustment, and extends the first stage time according to the preset delay step until the conditions are met. Once the real-time temperature is maintained within the preset error range and reaches the predetermined time of the first stage, the system automatically switches to the second baking stage and repeats the above process to determine the second correction temperature.

[0178] The same logic applies to the third and fourth baking stages. For each stage, the system uses the fuzzy PID control algorithm to calculate the corrected temperature of the stage based on the real-time temperature data and the corresponding baking stage temperature, and adjusts the output power to ensure that the temperature is stable near the corrected target value. When all four stages are completed, the baking is over.

[0179] The core of the fuzzy PID control algorithm is that it can handle nonlinear and uncertainty problems, providing more flexible and accurate temperature control. Specifically, the algorithm first calculates the error between the baking stage temperature and the current real-time temperature data, that is, the current temperature error E(t), and then calculates the difference between the current temperature error and the historical temperature error at the previous moment to obtain the error change rate ΔE(t).

[0180] Subsequently, the membership degree is calculated using the Gaussian membership function for the current temperature error E(t) and the error change rate ΔE(t), and the formula is as follows:

[0181]

[0182]

[0183] Based on these memberships, the system uses the weighted average method to perform fuzzy reasoning according to predefined fuzzy rules and obtain fuzzy output. For example, if the current temperature error is close to μ ZO (E(t)), that is, the actual temperature is very close to the target temperature, but the error rate of change is close to μ NB (ΔE(t)), indicating that although the temperature is close to the target, the rising speed is too fast, so the proportional fuzzy output, integral fuzzy output and differential fuzzy output under the corresponding fuzzy rules are matched. The proportional comprehensive fuzzy output ΔK is obtained by weighted average of all proportional fuzzy outputs, integral fuzzy outputs and differential fuzzy outputs obtained by fuzzy rule matching. p , integral comprehensive fuzzy output ΔK i Sum differential comprehensive fuzzy output ΔK d , calculated by the following formula:

[0184]

[0185] Next, adjust the PID parameters according to the fuzzy output to obtain a new proportional correction coefficient K′ p , integral correction coefficient K′ i , and the differential correction coefficient K′ d , which is calculated as:

[0186] K′ p =K p +ΔK p

[0187] K′ i =K i +ΔK i

[0188] K′ d =K d +ΔK d

[0189] Finally, the system determines the new PID parameter K′ based on the current temperature error E(t). p , K′ i , K′ d , and the preset time step τ to calculate the error correction coefficient C e :

[0190]

[0191] This error correction coefficient is used to update the real-time temperature to the correction stage temperature T corrected , the formula is:

[0192] T corrected =T target +C e

[0193] In order to ensure that the real-time temperature can reach the correction stage temperature T corrected , the system further calculates the adjusted output power P(t), the formula is as follows:

[0194] E′(t)=T corrected -T real

[0195]

[0196] In this way, the system can continuously optimize the temperature control strategy during the baking process to ensure that each step meets the optimal baking conditions and ultimately achieve high-quality baking results.

[0197] The following describes the working process of the present invention using a relatively common scenario as an example. Figure 1, a method for dynamic temperature regulation of an oven, comprising the following steps:

[0198] The goal of this baking is to make a batch of high-quality chocolate cakes. The food type is chocolate cake, the initial set temperature is 180 degrees Celsius, and the food weight is 2 kilograms.

[0199] When the user selects chocolate cake as the baking object and enters the corresponding weight, the system automatically starts the baking program. First, the oven enters the first stage, when the oven heats at maximum power, with the goal of quickly raising the internal temperature to the calculated first-stage temperature of 200 degrees Celsius. As the temperature gradually rises, the real-time temperature sensor continuously feeds back data to the control system. When the temperature reaches 200 degrees Celsius, the system calculates the corrected temperature of 205 degrees Celsius in combination with the fuzzy PID control algorithm, and adjusts the output power to ensure that the temperature stabilizes at this level. Although the temperature was not completely stable within the initially expected time, a stable baking environment was eventually achieved by appropriately increasing the heating time.

[0200] Next, the oven smoothly transitioned to the second stage, where the temperature needed to be adjusted to 195 degrees Celsius. The system again used the fuzzy PID control algorithm to calculate the corrected temperature of 197 degrees Celsius and adjusted the heating power accordingly. In this stage, the temperature control showed extremely high accuracy, and the real-time temperature remained within the expected range, ensuring that the cake was evenly heated.

[0201] Then, in the third stage, the temperature is further reduced to 185 degrees Celsius, and the correction temperature is set to 187 degrees Celsius. The key to this stage is to prevent overheating from affecting the quality of the cake. The system successfully maintains this temperature, ensuring the formation of the cake's internal structure and good surface color.

[0202] Finally, in the fourth stage, the temperature drops to 175 degrees Celsius, with a correction temperature of 177 degrees Celsius. This stage is designed to complete the final baking of the cake while avoiding over-drying. By precisely controlling the temperature, the system ensures that the cake has the ideal moistness and taste when it comes out of the oven.

[0203] During the entire baking process, the system not only automatically calculated and adjusted the temperature and time of the baking stage according to the type and weight of the food, but also determined the specific duration of each stage through the decision tree model. Thanks to the application of the fuzzy PID control algorithm, the temperature was always kept within the optimal range without large fluctuations or deviations. In the end, at the end of baking, the chocolate cake presented a perfect appearance and taste, proving the effectiveness of this dynamic temperature regulation method. This method not only improves the quality of baking, but also significantly improves energy utilization. Reference Figure 2 The second embodiment of the present invention provides a dynamic temperature adjustment system for an oven, comprising:

[0204] A data acquisition module is used to obtain food type, food weight, initial set temperature and real-time temperature data;

[0205] a stage temperature calculation module, used for calculating the baking stage temperature of each baking stage according to the food type, the food weight and the initial set temperature, wherein the baking stage temperature includes a first stage temperature, a second stage temperature, a third stage temperature and a fourth stage temperature;

[0206] a stage time calculation module, for inputting the food type, the food weight and the baking stage temperature into a pre-trained decision tree model to obtain the baking stage time, wherein the baking stage time includes the first stage time, the second stage time, the third stage time and the fourth stage time;

[0207] The dynamic temperature adjustment module is used to dynamically adjust the baking temperature according to the baking stage temperature, the baking stage time and the real-time temperature data in combination with a fuzzy PID control algorithm. It should be noted that the dynamic temperature adjustment device for an oven provided in an embodiment of the present invention is used to execute all the process steps of the dynamic temperature adjustment method for an oven in the above embodiment, and the working principles and beneficial effects of the two correspond one to one, so they are not repeated here.

[0208] The embodiment of the present invention further provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a dynamic temperature adjustment program for an oven. When the processor executes the computer program, the steps of the above-mentioned dynamic temperature adjustment method for an oven are implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are realized, such as the dynamic temperature adjustment module of the oven.

[0209] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the electronic device.

[0210] The electronic device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. The electronic device may include more or fewer components than the above components, or may combine certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0211] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device.

[0212] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the electronic device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0213] Wherein, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-0nly Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media does not include electrical carrier signals and telecommunication signals.

[0214] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0215] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for dynamic temperature regulation of an oven, characterized in that: Executed by the controller, including: Obtain food type, food weight, initial set temperature and real-time temperature data; Calculating the baking stage temperature of each baking stage according to the food type, the food weight and the initial setting temperature, wherein the baking stage temperatures include a first stage temperature, a second stage temperature, a third stage temperature and a fourth stage temperature; Inputting the food type, the food weight and the baking stage temperature into a pre-trained decision tree model to obtain the baking stage time, wherein the baking stage time includes the first stage time, the second stage time, the third stage time and the fourth stage time; The baking temperature is dynamically adjusted according to the baking stage temperature, the baking stage time and the real-time temperature data in combination with a fuzzy PID control algorithm.

2. The method for dynamic temperature regulation of an oven according to claim 1, characterized in that: The step of calculating the baking stage temperature of each baking stage according to the food type, the food weight and the initial set temperature comprises: The baking stage temperature is calculated by the following formula: T1=T0+c·m·ΔT1 T3=T2-c·log(m)·ΔT3 T4=T3-c·m 2 ·ΔT4 Among them, T0 represents the initial set temperature, T1 represents the first stage temperature, T2 represents the second stage temperature, T3 represents the third stage temperature, T4 represents the fourth stage temperature, c represents the preset food type coefficient, m represents the food weight, ΔT1 represents the preset first stage basic temperature increment, ΔT2 represents the preset second stage basic temperature increment, ΔT3 represents the preset third stage basic temperature increment, and ΔT4 represents the preset fourth stage basic temperature increment.

3. The method for dynamic temperature regulation of an oven according to claim 1, characterized in that: The training process of the decision tree model includes: Perform data cleaning and data standardization on the pre-stored historical food types, corresponding historical food weights, and historical baking stage temperatures to obtain pre-processed data; Comprehensive feature extraction is performed based on the historical food types, the historical food weights, and the historical baking stage temperatures to obtain feature data; Use the Gini index to evaluate the purity of each feature data, and select the feature with the lowest Gini index as the best split feature; Splitting the data set of the parent node according to the optimal splitting feature to obtain multiple subsets, each subset corresponding to a new child node; When the samples of the child node do not belong to the same category feature and the samples of the child node have features that can be used for further classification, and the number of samples contained in the child node is more than a preset threshold or does not reach a preset maximum tree depth, the child node continues to split; When the samples of the child node belong to the same category feature or the samples of the child node do not have features that can be used for further classification or the number of samples contained in the child node is less than a preset threshold or reaches a preset maximum tree depth, the child node stops splitting, and the child node should be marked as a leaf node, and a classification result is given according to the category distribution of the samples of the child node; When all child nodes stop splitting, the decision tree is pruned using a pruning optimization algorithm to obtain a trained decision tree model.

4. The method for dynamic temperature regulation of an oven according to claim 3, characterized in that: The Gini index is used to evaluate the purity of each feature data, and the feature with the lowest Gini index is selected as the best split feature, including: The Gini index is calculated using the following formula: in, Represents feature category c i feature data set, D represents the feature data set, C represents the total number of feature categories, p(c i ) represents the feature category c i The probability in the feature data set, Gini(D) represents the Gini index of the feature data set.

5. The method for dynamic temperature regulation of an oven according to claim 1, characterized in that: The method of dynamically adjusting the baking temperature according to the baking stage temperature, the baking stage time and the real-time temperature data in combination with a fuzzy PID control algorithm comprises: According to the first stage temperature control, the oven bakes at maximum power, the oven enters the first baking stage and starts recording the baking time; When the real-time temperature data reaches the first stage temperature, a first corrected temperature is calculated according to the real-time temperature data and the first stage temperature in combination with a fuzzy PID control algorithm; According to the real-time temperature data and the first corrected temperature, the output power of the oven is adjusted to control the real-time temperature data to reach the first corrected temperature; When the real-time temperature data does not reach a preset error range centered on the first correction temperature and the baking time reaches the first stage time, the output power is adjusted according to the real-time temperature data and the first correction temperature and the first stage time is extended according to a preset delay step; When the real-time temperature data reaches a preset error range centered on the first correction temperature and the baking time reaches the first stage time, the second baking stage is entered; Calculate a second corrected temperature based on the real-time temperature data and the second stage temperature in combination with a fuzzy PID control algorithm; According to the real-time temperature data and the second corrected temperature, the output power of the oven is adjusted to control the real-time temperature data to reach the second corrected temperature; When the real-time temperature data does not reach a preset error range centered on the second corrected temperature and the baking time reaches the second stage time, the output power is adjusted according to the real-time temperature data and the second corrected temperature and the second stage time is extended according to a preset delay step; When the real-time temperature data reaches a preset error range centered on the second corrected temperature and the baking time reaches the second stage time, the third baking stage is entered; Calculate a third corrected temperature based on the real-time temperature data and the third stage temperature in combination with a fuzzy PID control algorithm; According to the real-time temperature data and the third corrected temperature, the output power of the oven is adjusted to control the real-time temperature data to reach the third corrected temperature; When the real-time temperature data does not reach a preset error range centered on the third corrected temperature and the baking time reaches the third stage time, the output power is adjusted according to the real-time temperature data and the third corrected temperature and the third stage time is extended according to a preset delay step; When the real-time temperature data reaches a preset error range centered on the third corrected temperature and the baking time reaches the third stage time, the fourth baking stage is entered; Calculate a fourth corrected temperature based on the real-time temperature data and the fourth stage temperature in combination with a fuzzy PID control algorithm; According to the real-time temperature data and the fourth corrected temperature, the output power of the oven is adjusted to control the real-time temperature data to reach the fourth corrected temperature; When the real-time temperature data does not reach a preset error range centered on the fourth corrected temperature and the baking time reaches the fourth stage time, the output power is adjusted according to the real-time temperature data and the fourth corrected temperature and the fourth stage time is extended according to a preset delay step; When the real-time temperature data reaches a preset error range centered on the fourth corrected temperature and the baking time reaches the fourth stage time, the baking ends.

6. The method for dynamic temperature regulation of an oven according to claim 1, characterized in that: The implementation process of the fuzzy PID control algorithm includes: Calculate the error between the baking stage temperature and the real-time temperature data at the current moment to obtain a current temperature error; Calculate the difference between the current temperature error and the historical temperature error stored at the previous moment to obtain the error change rate; Calculating the degree of membership using a Gaussian membership function according to the current temperature error and the error change rate; Performing fuzzy reasoning using a weighted average method according to the membership degree and predefined fuzzy rules to obtain a fuzzy output; Adjusting PID parameters according to the fuzzy output to obtain proportional correction parameters, integral correction parameters and differential correction parameters; Calculating an error correction coefficient according to the current temperature error, the proportional correction parameter, the integral correction parameter and the differential correction parameter; Calculate the stage correction temperature according to the error correction coefficient and the real-time temperature data, wherein the correction stage temperature includes a first correction temperature, a second correction temperature, a third correction temperature and a fourth correction temperature; Among them, the membership degree is calculated by: The fuzzy output is calculated by the following formula: Adjust the PID parameters by the following formula: K′ p =K p +ΔK p K′ i =K i +ΔK i K′ d =K d +ΔK d The error correction factor is calculated using the following formula: The stage corrected temperature is calculated by the following formula: T corrected =T target +C e Among them, μ NB (E(t)) represents the negative large temperature error membership, μ ZO (E(t)) represents the zero temperature error membership, μ PB (E(t)) represents the positive temperature error membership, E(t) represents the current temperature error, c E Represents the preset temperature error center coefficient, σ E Represents the pre-stored temperature error standard deviation, μ NB (ΔE(t)) represents the negative large change rate membership, μ ZO (ΔE(t)) represents the zero-rate membership, μ PB (ΔE(t)) represents the positive change rate membership, ΔE(t) represents the error change rate, c ΔE Represents the preset error change rate center coefficient, σ ΔE Indicates the standard deviation of the pre-stored error change rate, ΔK p Indicates the proportional integrated fuzzy output, ΔK i Indicates the integral comprehensive fuzzy output, ΔK d represents the differential integrated fuzzy output, w i represents the weight corresponding to the i-th fuzzy rule, x pi represents the proportional fuzzy output under the i-th fuzzy rule, x ii represents the integral fuzzy output under the i-th fuzzy rule, x di represents the differential fuzzy output under the i-th fuzzy rule, K′ p Represents the proportional correction coefficient, K′ i Indicates the integral correction coefficient, K′ d Denotes the differential correction coefficient, K p Represents the proportionality coefficient, K i Indicates the integral coefficient, K d represents the differential coefficient, τ represents the preset time step, C e represents the error correction factor, T target Indicates the baking stage temperature, T corrected Indicates the correction stage temperature.

7. The method for dynamic temperature regulation of an oven according to claim 5, characterized in that: The step of adjusting the output power of the oven according to the real-time temperature data and the first corrected temperature, and controlling the real-time temperature data to reach the first corrected temperature, comprises: Calculate the oven's output power using the following formula: E′(t)=T corrected -T real Among them, P(t) represents the adjusted output power, P0 represents the output power at the current moment, and P N represents the rated power, E′(t) represents the correction error, T corrected Indicates the correction stage temperature, T real Indicates real-time temperature, K′ p Represents the proportional correction coefficient, K′ i Indicates the integral correction coefficient, K′ d represents the differential correction coefficient, and τ represents the preset time step.

8. A dynamic temperature control system for an oven, characterized in that: include: A data acquisition module is used to obtain food type, food weight, initial set temperature and real-time temperature data; a stage temperature calculation module, used for calculating the baking stage temperature of each baking stage according to the food type, the food weight and the initial set temperature, wherein the baking stage temperature includes a first stage temperature, a second stage temperature, a third stage temperature and a fourth stage temperature; a stage time calculation module, for inputting the food type, the food weight and the baking stage temperature into a pre-trained decision tree model to obtain the baking stage time, wherein the baking stage time includes the first stage time, the second stage time, the third stage time and the fourth stage time; The dynamic temperature adjustment module is used to dynamically adjust the baking temperature according to the baking stage temperature, the baking stage time and the real-time temperature data in combination with a fuzzy PID control algorithm.

9. An electronic device, characterized in that: The invention comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the method for dynamic temperature adjustment of the oven according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the method for dynamic temperature adjustment of an oven according to any one of claims 1 to 7.

Images