Temperature acquisition control system and method for industrial production intelligent temperature control digestion furnace

Abstract

The invention discloses a temperature acquisition control system and method for an industrial production intelligent temperature control digestion furnace, and relates to the technical field of industrial production process control, and the method comprises the steps: constructing a fuzzy logic control model, processing fused temperature field data, calculating the actual temperature deviation and temperature change rate, and carrying out the fuzzy processing, generating a fuzzy temperature deviation information set; reasoning the fuzzification temperature deviation information set and the fuzzy control rule set to generate a heating power regulation instruction set; the heating power adjusting instruction set is issued to a heating element driver, the heating power is adjusted in real time, the latest temperature is collected, and a real-time temperature feedback data set is generated; and performing fusion analysis on the real-time temperature feedback data set and the fusion temperature field data, updating temperature field distribution, adjusting parameters of the fuzzy logic control model, and generating an optimal control data set. According to the invention, the digestion furnace can still maintain a reliable temperature monitoring effect under a complex working condition.

Description

Technical Field

[0001] This invention relates to the field of industrial production process control technology, and in particular to a temperature acquisition and control system and method for an intelligent temperature-controlled digestion furnace in industrial production. Background Technology

[0002] With the rapid development of automation and intelligence in industrial production, temperature control technology has gradually become a key factor affecting operational stability and product quality. In scenarios such as material digestion, elemental analysis, and complex sample pretreatment, digestion furnaces, as important heat treatment equipment, are widely used in industries such as chemical engineering, metallurgy, environmental monitoring, and food safety. Existing temperature-controlled digestion furnaces generally rely on multi-point temperature acquisition combined with data processing to monitor the furnace cavity temperature distribution, and use proportional-integral-differential algorithms to adjust the power of the heating elements to meet the requirements of temperature stability and rapid response.

[0003] The temperature control scenario of a digester is characterized by complex features such as multi-point distribution, nonlinear coupling, and dynamic changes. Relying solely on traditional temperature acquisition and proportional-integral-differential (PID) algorithms still has limitations in practical applications. Temperature sensors are prone to data loss or noise interference under long-term operating conditions, affecting the integrity and accuracy of temperature field data. Furthermore, when dealing with multi-source temperature data, the lack of a data fusion and optimization mechanism may lead to deviations between temperature control results and the actual temperature field. In addition, traditional temperature control strategies are mostly based on fixed parameters, making it difficult to dynamically correct the control model using real-time feedback. These factors make it difficult for the digester to maintain ideal temperature uniformity and energy consumption optimization levels during long-term operation. Summary of the Invention

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

[0005] Therefore, this invention provides a temperature acquisition and control method for an intelligent temperature-controlled digestion furnace in industrial production, which solves the problem of temperature field acquisition accuracy and adaptive optimization of control.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, the present invention provides a temperature acquisition and control method for an intelligent temperature-controlled digestion furnace in industrial production, which includes: acquiring real-time temperature data, performing preliminary verification and missing data compensation, and generating a preliminary temperature dataset. The Kalman filter method is used to fuse the preliminary temperature dataset to generate fused temperature field data; A fuzzy logic control model is constructed to process the fused temperature field data, calculate the actual temperature deviation and temperature change rate, and perform fuzzification processing to generate a fuzzy temperature deviation information set. Reasoning is performed on the fuzzy temperature deviation information set and the fuzzy control rule set to generate a heating power adjustment instruction set; The heating power adjustment command set is sent to the heating element driver to adjust the heating power in real time and collect the latest temperature to generate a real-time temperature feedback dataset. The real-time temperature feedback dataset and the fused temperature field data are fused and analyzed to update the temperature field distribution and adjust the parameters of the fuzzy logic control model, thereby generating an optimized control dataset.

[0007] As a preferred embodiment of the temperature acquisition and control method for the intelligent temperature-controlled digestion furnace in industrial production according to the present invention, the specific steps for generating the preliminary temperature dataset are as follows: Perform range checks and anomaly marking on real-time temperature data to generate a preliminary dataset of suspected temperatures; Missing value compensation and trend interpolation are performed on the initial suspicious temperature dataset to generate a smoothed and corrected temperature dataset. The smoothed temperature dataset is weighted and its integrity is verified to generate a preliminary temperature dataset.

[0008] As a preferred embodiment of the temperature acquisition and control method for the intelligent temperature-controlled digestion furnace in industrial production according to the present invention, the specific steps for generating fused temperature field data are as follows: The Kalman filter method is used to perform state prediction and measurement update on the preliminary temperature dataset to generate an updated temperature estimation vector. Based on the updated temperature estimation vector and the initial temperature dataset, the Kalman gain is calculated, and the initial temperature dataset is weighted and fused using the Kalman gain to generate the initial fused temperature dataset. The initial fused temperature dataset is smoothed and anomaly corrected to generate fused temperature field data.

[0009] As a preferred embodiment of the temperature acquisition and control method for the intelligent temperature-controlled digestion furnace in industrial production according to the present invention, the specific steps for constructing the fuzzy logic control model are as follows: Based on the temperature control requirements of the digestion furnace and the temperature range measured by each temperature acquisition device, the target temperature is obtained, and input and output variables are set. At the same time, membership functions are set for the input and output variables to generate a membership function set. Based on the membership function set and historical temperature control data, the fuzzy state of the input variable is mapped to the fuzzy control action of the output variable to generate a fuzzy control rule set; Using the membership function set, the preliminary temperature dataset and the target temperature are fuzzified, and rule matching and aggregation inference are performed according to the fuzzy control rule set to generate a fuzzy output control set; The fuzzy output control set is defuzzified to generate a heating power adjustment instruction set. Combined with the latest temperature dataset, the fuzzy control rule set and membership function set are optimized to generate a fuzzy logic control model.

[0010] As a preferred embodiment of the temperature acquisition and control method for the intelligent temperature-controlled digestion furnace in industrial production according to the present invention, the specific steps for generating the fuzzy temperature deviation information set are as follows: The fused temperature field data is compared with the target temperature to obtain the actual temperature deviation; The temperature change rate is obtained by performing time series difference calculation on the fused temperature field data; The temperature deviation signal and the rate of temperature change are input into the fuzzy logic control model, fuzzified, and a fuzzified temperature deviation information set is generated.

[0011] As a preferred embodiment of the temperature acquisition and control method for the intelligent temperature-controlled digestion furnace in industrial production according to the present invention, the specific steps for generating the heating power adjustment instruction set are as follows: The fuzzy temperature deviation information set is matched with the fuzzy control rule set one by one, the applicability of each fuzzy control rule is calculated, and a fuzzy rule matching matrix is ​​generated. The fuzzy rule matching matrix is ​​weighted and aggregated to form a fuzzy control action set; The fuzzy control action set is defuzzified to generate a heating power adjustment instruction set.

[0012] As a preferred embodiment of the temperature acquisition and control method for the intelligent temperature-controlled digestion furnace in industrial production according to the present invention, the specific steps for generating the real-time temperature feedback dataset are as follows: The heating power adjustment instruction set is converted into control instructions that the driver can execute and sent to the heating element driver to generate drive confirmation information; Based on the drive confirmation information, the heating element driver executes control commands, performs power regulation, outputs the actual power status, and generates real-time power feedback data. Using real-time power feedback data, noise suppression and correction are performed on the timestamped temperature signal collected by the temperature acquisition device to generate a smooth temperature sequence; The smoothed temperature sequence, drive confirmation information, and real-time power feedback data are fused and verified to generate a real-time temperature feedback dataset.

[0013] As a preferred embodiment of the temperature acquisition and control method for the intelligent temperature-controlled digestion furnace in industrial production according to the present invention, the specific steps for generating the optimized control dataset are as follows: Align and verify the real-time temperature feedback dataset with the fused temperature field data to generate a corrected temperature dataset; A difference analysis is performed between the corrected temperature dataset and the predicted temperature vector to generate temperature deviation mapping data. Based on the temperature deviation mapping data, the parameters of the fuzzy logic control model are iteratively optimized to generate an optimized control parameter set. The temperature field distribution is then updated using the optimized control parameter set, and the optimized control parameter sets are merged to form an optimized control dataset.

[0014] As a preferred embodiment of the temperature acquisition and control method for the intelligent temperature-controlled digestion furnace in industrial production according to the present invention, the specific steps for performing difference analysis on the corrected temperature dataset and the predicted temperature vector to generate temperature deviation mapping data are as follows. The preliminary fused temperature dataset is input into the fuzzy logic control model. Based on the parameters of the fuzzy logic control model and the previous heating power adjustment command, the predicted temperature is calculated and a predicted temperature vector is generated. The corrected temperature dataset and the predicted temperature vector are matched in time and space to generate an aligned temperature pair set. The deviation between the actual temperature and the predicted temperature is calculated for each acquisition point in the aligned temperature pair set to generate a preliminary temperature difference vector. The initial temperature difference vector is weighted to generate a weighted temperature difference vector, and then smoothed and anomaly-handled to generate temperature deviation mapping data.

[0015] Secondly, the present invention provides a temperature acquisition and control system for an intelligent temperature-controlled digestion furnace in industrial production, including a data acquisition module for acquiring real-time temperature data, performing preliminary verification and missing data compensation, and generating a preliminary temperature dataset. The data fusion module is used to fuse the preliminary temperature dataset using the Kalman filter method to generate fused temperature field data. The deviation calculation module is used to construct a fuzzy logic control model, process the fused temperature field data, calculate the actual temperature deviation and temperature change rate, and perform fuzzification processing to generate a fuzzy temperature deviation information set. The rule reasoning module is used to reason about the fuzzy temperature deviation information set and the fuzzy control rule set to generate a heating power adjustment instruction set; The power control module is used to send the heating power adjustment command set to the heating element driver, adjust the heating power in real time, and collect the latest temperature to generate a real-time temperature feedback dataset. The model optimization module is used to perform fusion analysis on the real-time temperature feedback dataset and the fused temperature field data, update the temperature field distribution, adjust the parameters of the fuzzy logic control model, and generate an optimized control dataset.

[0016] The beneficial effects of this invention are as follows: by using Kalman filtering to perform state prediction and measurement updates on the preliminary temperature dataset, and using the updated temperature estimation vector to calculate the Kalman gain to achieve data weighted fusion, thereby generating fused temperature field data, dynamic optimization and integration of multi-source temperature signals are realized; it can effectively suppress single-point temperature measurement errors and noise interference, ensure the overall continuity and stability of the temperature field, provide a more accurate data foundation for subsequent temperature control inference, improve temperature acquisition accuracy and anti-interference ability, and enable the digestion furnace to maintain reliable temperature monitoring effect under complex working conditions. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart for the temperature acquisition and control method of an intelligent temperature-controlled digestion furnace for industrial production.

[0019] Figure 2 A schematic diagram of the temperature acquisition and control system for an intelligent temperature-controlled digestion furnace in industrial production.

[0020] Figure 3 A flowchart for constructing a fuzzy logic control model.

[0021] Figure 4 A flowchart generated for fusing temperature field data.

[0022] Figure 5 This is a schematic diagram comparing the process before and after fusion.

[0023] Figure 6 This is a schematic diagram of the temperature field.

[0024] Figure 7 This is a schematic diagram for comparing temperature time series.

[0025] Figure 8 This is a schematic diagram of the temperature error distribution in the steady-state range.

[0026] Figure 9 This is a schematic diagram of the key quantities in the control loop. Detailed Implementation

[0027] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0028] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0029] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0030] Reference Figures 1-9 As one embodiment of the present invention, this embodiment provides a temperature acquisition and control method for an intelligent temperature-controlled digestion furnace in industrial production, comprising the following steps: S1. Collect real-time temperature data, perform preliminary verification and missing data compensation, and generate a preliminary temperature dataset.

[0031] S1.1 Perform range checks and anomaly marking on real-time temperature data to generate a preliminary dataset of suspected temperatures.

[0032] Specifically, collecting real-time temperature data includes sequentially acquiring the temperature values ​​of each temperature acquisition point at fixed time intervals and recording the corresponding timestamp information; reading the real-time temperature data one by one, comparing each real-time temperature data with a preset temperature range, marking the real-time temperature data as normal if it is within the preset temperature range, and marking it as abnormal if it exceeds the preset temperature range; and summarizing all real-time temperature data marked as abnormal to form a preliminary suspicious temperature dataset.

[0033] It should also be explained that the specific steps for preset temperature range are as follows: Based on the temperature control requirements of the digester and the temperature measurement capabilities of each temperature acquisition device, set the upper and lower limits of the allowable temperature for each temperature acquisition point. For example, set the lowest temperature to 200℃ and the highest temperature to 400℃. Record the allowable temperature range of each temperature acquisition point in the temperature parameter table for subsequent range checks and anomaly marking of the real-time temperature data.

[0034] S1.2 Perform missing value compensation and trend interpolation on the preliminary suspicious temperature dataset to generate a smoothed corrected temperature dataset.

[0035] Specifically, for missing temperature points in the preliminary suspected temperature dataset, the average temperature of adjacent time steps is used for compensation. For example, the average temperature values ​​of three time steps before and after the missing point are used to fill the missing value. For temperature data with abnormal fluctuations, interpolation calculations are performed on adjacent temperature points according to the time series trend interpolation method and the quadratic curve fitting method to generate continuous temperature values. All compensated and interpolated temperature points are checked in sequence to ensure that the temperature changes are continuous and without abrupt changes, thus generating a smoothed corrected temperature dataset.

[0036] S1.3. Adjust the weights and verify the integrity of the smoothed temperature dataset to generate a preliminary temperature dataset.

[0037] Specifically, based on the historical stability and measurement accuracy of each temperature acquisition point, a weight is assigned to each temperature point in the smoothed temperature dataset. For example, temperature points with small historical fluctuations and high reliability are assigned a weight value of 0.8 to 1.0, while temperature points with larger fluctuations are assigned a weight value of 0.5 to 0.7. The smoothed temperature dataset is then checked for completeness, with each data point examined for missing, duplicate, or abnormal temperature values. If any abnormalities are found, corrections are made based on a weighted average of the preceding and following temperature points. The temperature data after weight adjustment and completeness check are then integrated sequentially to generate a preliminary temperature dataset.

[0038] It should also be noted that historical stability refers to the fluctuation of temperature measurements over a past period. For example, calculating the standard deviation of temperature data collected over a continuous hour; a smaller standard deviation indicates higher historical stability, meaning the temperature measurements are relatively stable and reliable. Measurement accuracy refers to how closely the temperature measured at a point approximates the actual temperature. For example, the temperature deviation range obtained through calibration experiments; a smaller deviation indicates higher measurement accuracy, accurately reflecting the true temperature. These parameters are used to evaluate the reliability of each temperature point, thereby allowing for the appropriate allocation of weights during the weighting process.

[0039] S2. The Kalman filter method is used to fuse the preliminary temperature dataset to generate fused temperature field data.

[0040] S2.1. Using the Kalman filter method, state prediction and measurement updates are performed on the initial temperature dataset to generate an updated temperature estimation vector.

[0041] Specifically, a state prediction equation and a measurement update equation are established for the temperature data of each temperature acquisition point. The predicted temperature is calculated based on the temperature estimate of the previous moment and the preliminary temperature dataset. The predicted value is adjusted using the measurement noise covariance and the process noise covariance. The predicted value and the actual measured value are weighted and fused using Kalman gain. The temperature estimate of each temperature acquisition point is iteratively updated to generate an updated temperature estimate vector. For example, the temperature acquisition point is continuously updated at an example time interval of 1 second.

[0042] It should also be noted that establishing the state prediction equation and measurement update equation includes defining temperature state variables and state transition relationships for each temperature acquisition point, such as setting the temperature at the next moment to be equal to the current temperature plus the example prediction increment; constructing the measurement equation based on the preliminary temperature dataset and the measurement noise covariance matrix, associating the actual measured temperature with the predicted state; calculating the process noise covariance and measurement noise covariance for subsequent Kalman gain calculation; and performing prediction and measurement updates for each temperature acquisition point to generate the preliminary predicted temperature and the corrected temperature, forming the state prediction equation and measurement update equation that can be used for iteration.

[0043] S2.2. Based on the updated temperature estimation vector and the preliminary temperature dataset, calculate the Kalman gain, and use the Kalman gain to perform weighted fusion of the preliminary temperature dataset to generate a preliminary fused temperature dataset.

[0044] Specifically, based on the updated temperature estimation vector and the preliminary temperature dataset, the Kalman filter method is used to calculate the prediction error covariance for each temperature acquisition point, and the Kalman gain is calculated based on the prediction error covariance and the measurement error covariance. The updated temperature estimation vector and the preliminary temperature dataset are then fused using the Kalman gain in a weighted manner, and the temperature value of each acquisition point is adjusted sequentially to form a preliminary fused temperature dataset. During the weighted fusion process, extreme or outlier values ​​(e.g., exceeding ±5°C) are smoothed to ensure that the temperature of each acquisition point is within a reasonable range, and a preliminary fused temperature dataset is generated.

[0045] S2.3. Smooth and correct anomalies in the preliminary fused temperature dataset to generate fused temperature field data.

[0046] Specifically, the temperature value at each temperature acquisition point is smoothed by a sliding window average. For example, the smoothed temperature is calculated by using the moving average of five consecutive sampling points, and the smoothed temperature value is compared with a preset temperature range. Abnormal temperatures that exceed the preset temperature range are marked. The marked abnormal temperatures are corrected by using a linear interpolation method. For example, the correction value is calculated by using the linear interpolation of two adjacent normal temperature points, and the corrected temperature value replaces the corresponding temperature in the initial fused temperature data set. After repeating the process for all temperature acquisition points, fused temperature field data is generated.

[0047] S3. Construct a fuzzy logic control model to process the fused temperature field data, calculate the actual temperature deviation and temperature change rate, and perform fuzzification processing to generate a fuzzy temperature deviation information set.

[0048] S3.1. Based on the temperature control requirements of the digestion furnace and the temperature range measured by each temperature acquisition device, obtain the target temperature, set the input and output variables, and set the membership functions for the input and output variables to generate a membership function set.

[0049] Specifically, by comparing the temperature data measured by each temperature acquisition device with the temperature control requirements of the digestion furnace, the temperature value that meets the stability and accuracy requirements is selected as the target temperature. For example, within the range of 500℃ to 800℃, the target temperature is determined to be 650℃. The input variables are set as temperature deviation and temperature change rate. The temperature deviation is calculated by calculating the difference between the target temperature and the real-time temperature measured by each temperature acquisition device, and the temperature change rate is calculated by calculating the rate of change of the real-time temperature measured by each temperature acquisition device at adjacent times. The adjustment of the heating power is set as the output variable. Membership functions are set for the input and output variables respectively. For example, the input variable temperature deviation is set as seven triangular membership functions: negative large, negative medium, negative small, zero, positive small, positive medium, and positive large. The input variable temperature change rate is set as five membership functions: negative fast, negative slow, zero, positive slow, and positive fast. The output variable control quantity is set as three membership functions: low, medium, and high. The membership functions corresponding to the input and output variables are combined to form a membership function set.

[0050] S3.2 Based on the membership function set and historical temperature control data, map the fuzzy state of the input variable to the fuzzy control action of the output variable to generate a fuzzy control rule set.

[0051] Specifically, based on the membership function set and historical temperature control data, the actual values ​​of the input variables, temperature deviation and temperature change rate, are calculated according to their respective membership function definition intervals, and the membership degree is obtained using the membership function method to obtain the fuzzy states of temperature deviation and temperature change rate. Then, based on the correspondence between temperature deviation, temperature change rate and the adjustment of heating power in the historical temperature control data, the fuzzy control actions for adjusting the heating power under different fuzzy states are determined. Finally, the fuzzy states of temperature deviation and temperature change rate are mapped one-to-one with the fuzzy control actions for adjusting the heating power to generate a fuzzy control rule set.

[0052] It should also be noted that historical temperature control data refers to the set of temperature control-related data continuously recorded by each temperature acquisition device during the operation of the digester, including temperature change curves, temperature stabilization time, temperature fluctuation amplitude, and corresponding heating power adjustment commands at each temperature acquisition point in the furnace cavity under different heating powers.

[0053] S3.3. Using the membership function set, the preliminary temperature dataset and the target temperature are fuzzified, and rule matching and aggregation reasoning are performed according to the fuzzy control rule set to generate the fuzzy output control set.

[0054] Specifically, using a membership function set, the temperature deviation and rate of change between each temperature acquisition point value and the target temperature in the preliminary temperature dataset are fuzzified. Membership degrees are calculated and mapped to the membership function set. For example, when the temperature deviation is +10℃, the membership degree of the "positive large" membership function is 0.7, while when the temperature rate of change is -2℃ / min, the membership degree of the "negative small" membership function is 0.5. Based on the fuzzy control rule set, the fuzzy states corresponding to the temperature deviation and rate of change are matched with the fuzzy control actions of the output variable, heating power adjustment, selecting multiple fuzzy control rules that meet the conditions. Then, the fuzzy control actions of all fuzzy control rules that meet the conditions are aggregated to generate a fuzzy output control set.

[0055] It should also be noted that the process of calculating the membership value is as follows: the difference between the preliminary temperature dataset and the target temperature is used as the temperature deviation input, the difference in temperature change over continuous time periods is used as the temperature change rate input, and the heating power adjustment is used as the output input. These values ​​are then substituted into the corresponding membership function formulas in the membership function set to calculate the membership degree. For example, piecewise linear calculation is used in the triangular membership function, and interval linear calculation is used in the trapezoidal membership function to obtain the membership value of each input variable under each fuzzy subset.

[0056] S3.4 Defuzzify the fuzzy output control set to generate a heating power adjustment instruction set. Combine the latest temperature dataset to optimize the fuzzy control rule set and membership function set, and generate a fuzzy logic control model.

[0057] Specifically, the centroid method is used to defuzzify the fuzzy output control set, calculating the continuous control quantity and quantizing and limiting it according to the actuator's allowable range and sampling period to form a heating power adjustment command set. The execution results of the heating power adjustment command set are matched with the latest temperature dataset in time and location, and the activation degree of each fuzzy control rule in this execution and the temperature deviation error signal generated by the activation degree are calculated. Based on the activation degree and temperature deviation error signal of each rule in the fuzzy control rule set, the rule weights in the fuzzy control rule set are iteratively updated using the least squares method, and the peak position and width of each membership function in the membership function set are slightly modified according to the temperature deviation error signal. The updated fuzzy control rule set and membership function set are normalized, and the boundary consistency of the rule weights and membership function parameters is checked according to the preset allowable range of fuzzy control parameters. The checked fuzzy control rule set and membership function set are used as input to train the fuzzy logic control model, optimize the control performance, and form an optimized fuzzy logic control model.

[0058] It should also be noted that the allowable range of the actuator refers to the upper and lower limits of the control quantity that the actuator can safely and stably output during actual operation. The upper and lower limits of the control quantity are determined by the rated parameters and physical limits of the actuator. For example, the allowable range of the heating power actuator can be from 0% to 100% of the rated power output. Below 0% is invalid, and above 100% will cause overload. Therefore, the allowable range of the actuator is used to constrain the control quantity obtained by defuzzification calculation and ensure that the control command operates within the acceptable range of the actuator. The specific steps for setting the allowable range of fuzzy control parameters include: collecting historical temperature control data and extracting the numerical range of the input variables temperature deviation and temperature change rate; determining the minimum and maximum values ​​of temperature deviation and temperature change rate as range boundaries according to the temperature control requirements of the digester; setting the minimum and maximum values ​​of rule weights, for example, the minimum value is 0.1 and the maximum value is 1.0; setting the upper and lower limits of the membership function parameters, for example, the membership function center value range is [-5, 5] and the width range is [1, 10]; forming the allowable range of fuzzy control parameters for subsequent normalization and boundary consistency verification.

[0059] S3.5. Compare the fused temperature field data with the target temperature to obtain the actual temperature deviation.

[0060] Specifically, the temperature value of each temperature acquisition point in the fused temperature field data is matched with the target temperature in time and space. The difference between the target temperature and the fused temperature field data is calculated to form a set of actual temperature deviation values ​​for each temperature acquisition point. For example, for a temperature acquisition point with a target temperature of 300℃, if the temperature measured by the fused temperature field data is 295℃, the actual temperature deviation is calculated to be -5℃. This calculation is repeated for all acquisition points to generate the actual temperature deviation.

[0061] S3.6 Perform time series difference calculation on the fused temperature field data to obtain the temperature change rate.

[0062] Specifically, for the continuous time series temperature values ​​of each temperature acquisition point in the fused temperature field data, the temperature difference between adjacent time points is calculated sequentially using the differential calculation method as the temperature change rate. For example, if a temperature acquisition point measures an example temperature of 295℃ at time t1 and an example temperature of 298℃ at time t2, then the temperature change rate is the example value 3℃ / Δt. This calculation is repeated for all temperature acquisition points and all time steps to generate the temperature change rate.

[0063] S3.7 Input the temperature deviation signal and temperature change rate into the fuzzy logic control model, perform fuzzification processing, and generate a fuzzy temperature deviation information set.

[0064] Specifically, the temperature deviation signal and the rate of temperature change are input into the fuzzy logic control model. Based on the membership function set, the temperature deviation signal and the rate of temperature change are mapped to corresponding membership values. According to the fuzzy control rule set in the fuzzy logic control model, the membership values ​​of each input variable are matched with the rule condition terms. The matching results are then aggregated and inferred using the maximum membership method to generate a fuzzy temperature deviation information set for each time step. Here, the rule condition term refers to the conditional expression in the fuzzy control rules used to determine the state of the input variables, and is used to determine the specific control rules that should be activated in the fuzzy control rule set.

[0065] It should be noted that fused temperature field data, rather than traditional single-point temperature measurement data, is used as the input to the fuzzy logic control model. Simultaneously, the actual temperature deviation and temperature change rate are comprehensively fuzzified to generate a fuzzy temperature deviation information set. By fusing temperature field data and performing fuzzification processing, a shift from single-point temperature control to multi-dimensional temperature field control is achieved, improving the adaptability and anti-interference capability of temperature control to complex operating conditions.

[0066] S4. Reason about the fuzzy temperature deviation information set and the fuzzy control rule set to generate a heating power adjustment instruction set.

[0067] S4.1 Match the fuzzy temperature deviation information set with the fuzzy control rule set one by one, calculate the applicability of each fuzzy control rule, and generate a fuzzy rule matching matrix.

[0068] Specifically, each fuzzified input item in the fuzzified temperature deviation information set is sequentially compared with the rule condition items in the fuzzy control rule set. The applicability of each fuzzy control rule is calculated using the minimum membership degree method. For example, for a fuzzy control rule, the applicability is taken as the minimum value among the membership degrees of each antecedent. The applicability of each fuzzy control rule is recorded in the corresponding position, and a fuzzy rule matching matrix is ​​generated sequentially to ensure that the applicability of each fuzzy control rule corresponds one-to-one with the corresponding fuzzified input state.

[0069] S4.2. Perform weighted aggregation on the fuzzy rule matching matrix to form a fuzzy control action set.

[0070] Specifically, the applicability of each rule in the fuzzy rule matching matrix is ​​taken in turn, and associated with the fuzzy output control action of the corresponding fuzzy control rule. The aggregate membership degree of each output variable is calculated using the maximum membership degree method. For example, for the control output, the membership degree of the output action corresponding to all fuzzy control rules is matched and calculated with the applicability of the rule condition terms. The maximum value method or the average value method is used to process all output variables in turn to form a fuzzy control action set, ensuring that the aggregate membership degree of each output variable reflects the comprehensive effect of all fuzzy control rules.

[0071] S4.3 Defuzzify the fuzzy control action set to generate a heating power adjustment instruction set.

[0072] Specifically, the aggregated membership degree of each output variable in the fuzzy control action set is sequentially taken, and the aggregated membership degree is mapped to the actual control quantity value range. For example, the membership degree of the control quantity output is calculated using the centroid method to obtain the clear value of each output variable. All control quantity outputs are processed sequentially, and the defuzzification results of each output variable are combined to form a heating power adjustment instruction set. This ensures that each heating power adjustment instruction can reflect the comprehensive control action under fuzzy logic control and can be directly used for the adjustment execution of the heating element driver. For example, for an input variable with a temperature deviation of "moderately high" and a temperature change rate of "rapidly rising", the fuzzy state values ​​obtained through membership function mapping are 0.7 and 0.8. The corresponding output variables may be "increase heating power" or "maintain heating power", with membership degrees of 0.6 and 0.4, respectively. The membership degree value is the fuzzification result, which is used for subsequent defuzzification processing.

[0073] S5. Send the heating power adjustment command set to the heating element driver to adjust the heating power in real time, collect the latest temperature, and generate a real-time temperature feedback dataset.

[0074] S5.1. Convert the heating power adjustment instruction set into control instructions that the driver can execute, and send them to the heating element driver to generate driver confirmation information.

[0075] Specifically, each control value in the heating power adjustment instruction set is read sequentially, and the control value is encoded according to the acceptable numerical range and communication protocol format of the heating element driver. For example, the power percentage value is converted into the corresponding value of driver voltage or pulse width. The encoded control instructions are packaged in sequence to form a continuous instruction frame and sent to the corresponding heating element driver through the communication channel. The execution status signal returned by the heating element driver is received, and the execution success or abnormal information is recorded to generate driver confirmation information.

[0076] It should also be noted that the acceptable numerical range of the heating element driver refers to the boundary of the control quantity that the driver can correctly identify and execute. For example, the input power value is usually limited to 0% to 100%, or the corresponding voltage / current signal is limited to the range of 0 volts to 24 volts. The communication protocol format refers to the control command transmission specification defined by the driver, including the command frame structure, byte order, check method and signal encoding rules. For example, each command consists of a start byte, a control quantity byte, a check byte and an end byte to ensure that the heating element driver can accurately parse and execute the control command.

[0077] S5.2. Based on the drive confirmation information, execute the control command, the heating element driver performs power adjustment and outputs the actual power status, generating real-time power feedback data.

[0078] Specifically, based on the driver confirmation information, each instruction in the heating power adjustment instruction set is parsed into a control signal recognizable by the heating element driver according to a preset communication protocol format. This includes the parsed instruction type, target power value, and timestamp, which are then sequentially encoded into data frames executable by the driver and sent to the heating element driver. After receiving the control signal, the heating element driver adjusts its output power to the instruction value, for example, a power range of 50% to 80%. Simultaneously, it collects the actual output power through its internal measurement circuit and generates real-time power feedback data, including a timestamp, actual power value, and power status identifier, ensuring that each control instruction corresponds to a unique feedback record.

[0079] S5.3. Using real-time power feedback data, noise suppression and correction are performed on the timestamped temperature signal collected by the temperature acquisition unit to generate a smooth temperature sequence.

[0080] Specifically, for the time-stamped temperature signals collected by the temperature acquisition device, based on the real-time power feedback data at the corresponding time, the temperature signals are first smoothed by weighted moving average, for example, by weighting and averaging three adjacent temperature signals to obtain a preliminary smoothed temperature sequence; power compensation correction is then performed on the preliminary smoothed temperature sequence, adjusting the temperature values ​​proportionally based on the difference between the real-time power feedback data and the target power to generate a smoothed temperature sequence. Each temperature data point retains its original timestamp and correction identifier to ensure the continuity and consistency of the temperature data.

[0081] S5.4. The smoothed temperature sequence, drive confirmation information and real-time power feedback data are fused and verified to generate a real-time temperature feedback dataset.

[0082] Specifically, for each temperature data point in the smoothed temperature sequence, consistency verification is performed based on the corresponding time-based drive confirmation information and real-time power feedback data. For each temperature data point in the smoothed temperature sequence, the change in commanded heating power is obtained based on the corresponding time-based drive confirmation information, and the actual power change is obtained by combining it with the real-time power feedback data. The temperature change rate is compared with the change in commanded heating power and the actual power change, and the deviation value is calculated using the absolute difference method to form temperature change trend matching information. Temperature data without anomalies is fused with real-time power feedback data using a weighted average method, for example, the smoothed temperature sequence accounts for 0.7 weights and the real-time power feedback data accounts for 0.3 weights, generating preliminary real-time temperature data. Boundary verification and timestamp correction are performed on the preliminary real-time temperature data to generate a real-time temperature feedback dataset containing temperature values, verification identifiers, and timestamps.

[0083] S6. Perform fusion analysis on the real-time temperature feedback dataset and the fused temperature field data, update the temperature field distribution and adjust the parameters of the fuzzy logic control model to generate an optimized control dataset.

[0084] S6.1 Align and verify the real-time temperature feedback dataset with the fused temperature field data to generate a corrected temperature dataset.

[0085] Specifically, the real-time temperature feedback dataset and the fused temperature field data are aligned point by point in time. The real-time temperature feedback value at each time point is compared with the corresponding fused temperature field data value. Data consistency is determined based on the acceptable deviation range. Temperature values ​​that exceed the acceptable deviation range are corrected using the mean correction method. All temperature acquisition points are processed in sequence to generate a corrected temperature dataset.

[0086] It should also be noted that the acceptable deviation range refers to the pre-set allowable error range for temperature values ​​or measurement data, such as ±2℃. Deviations within this range are considered normal and do not require correction. The allowable error range is determined by analyzing the deviation distribution between historical temperature data and the target temperature.

[0087] S6.2 Perform a difference analysis on the corrected temperature dataset and the predicted temperature vector to generate temperature deviation mapping data.

[0088] S6.2.1 Input the preliminary fused temperature dataset into the fuzzy logic control model, calculate the predicted temperature based on the fuzzy logic control model parameters and the previous heating power adjustment command, and generate the predicted temperature vector.

[0089] Specifically, the temperature deviation and temperature change rate corresponding to the preliminary fused temperature dataset and the previous heating power adjustment command are input into the fuzzy logic control model. The input variables are mapped to the membership function set for fuzzification. According to the fuzzy control rule set in the fuzzy logic control model, rule matching and weighted aggregation are performed on each input fuzzy state to generate a fuzzy output control action set. Then, the fuzzy output control action set is converted into the numerical value corresponding to the predicted temperature through a defuzzification method to form a predicted temperature vector, such as generating the predicted temperature value of each temperature acquisition point for the future time step.

[0090] S6.2.2 Match the corrected temperature dataset with the predicted temperature vector in time and space to generate an aligned temperature pair set, and calculate the deviation between the actual temperature and the predicted temperature for each acquisition point in the aligned temperature pair set to generate a preliminary temperature difference vector.

[0091] Specifically, each time-stamped temperature acquisition point in the corrected temperature dataset is matched one by one with the predicted temperature of the corresponding time step and spatial location in the predicted temperature vector to form an aligned temperature pair set. For each temperature acquisition point in the aligned temperature pair set, the actual temperature in the corrected temperature dataset is subtracted from the predicted temperature in the predicted temperature vector, and the deviation value is calculated using the subtraction method. The deviations of all temperature acquisition points are recorded in sequence to form a preliminary temperature difference vector. For example, an example deviation value is generated for each temperature acquisition point.

[0092] S6.2.3. The initial temperature difference vector is weighted to generate a weighted temperature difference vector, and then smoothed and anomaly-handled to generate temperature deviation mapping data.

[0093] Specifically, each deviation value in the initial temperature difference vector is weighted according to the corresponding weight coefficient to generate a weighted temperature difference vector. The weighted temperature difference vector is then smoothed, for example, by using a moving average method to average the deviation values ​​of continuous collection points to reduce local fluctuations. Outliers whose deviation values ​​significantly exceed the allowable error range are also processed, for example, by replacing outliers with the mean or median of neighboring collection points to form temperature deviation mapping data.

[0094] S6.3. Based on the temperature deviation mapping data, iteratively optimize the parameters of the fuzzy logic control model to generate an optimized control parameter set. Then, use the optimized control parameter set to update the temperature field distribution and merge the optimized control parameter sets to form an optimized control dataset.

[0095] Specifically, the deviation value of each temperature acquisition point in the temperature deviation mapping data is input into the fuzzy logic control model. The control output is calculated based on the current parameters of the fuzzy logic control model, and the values ​​of each fuzzy logic control model parameter are adjusted according to the deviation value, forming an iterative optimization operation. This iteration is repeated until the deviation converges or the example iteration number is reached, resulting in an optimized control parameter set. The distribution values ​​of each temperature acquisition point in the temperature field are recalculated based on the optimized control parameter set. The optimized temperature field distribution is then merged with the optimized control parameter set to generate an optimized control dataset. For example, each optimized control parameter can be stored in chronological order along with its corresponding temperature field value.

[0096] It should also be noted that the optimized control parameter set is subjected to iterative processing. The temperature deviation value of each temperature acquisition point is compared with the predicted temperature calculated in the previous iteration. Based on the deviation, the parameters of the fuzzy logic control model are adjusted to generate a new control output. The new control output is applied to the temperature field calculation to update the temperature of each temperature acquisition point. Then, the deviation value is recalculated and it is determined whether the deviation is lower than the convergence threshold, such as ±0.5℃. If the deviation has not converged and the maximum number of iterations in the example has not been reached, such as 50 times, the next round of iteration continues. Otherwise, the iteration is terminated, and the optimized control parameter set that meets the convergence condition or has reached the number of iterations in the example is output. The convergence threshold is determined by analyzing the temperature deviation fluctuation range in historical temperature control data. The maximum, minimum and standard deviation of temperature deviation at each temperature acquisition point in multiple control cycles are statistically analyzed. The upper limit of the deviation is selected as the convergence threshold according to the temperature control accuracy requirements. For example, a value in the range of ±0.5℃ to ±1℃ is selected as a reference standard for judging whether the temperature deviation has reached convergence in iterative optimization.

[0097] It should be noted that by fusing and analyzing real-time temperature feedback datasets and fused temperature field data, not only is the temperature field distribution dynamically corrected, but the membership functions and rule parameters of the fuzzy logic control model are also adaptively adjusted, thereby generating an optimized control dataset. This significantly improves the adaptability to operating disturbances, thermal inertia effects, and nonlinear factors, ensuring that the accuracy and robustness of the digester temperature control are continuously optimized under long-term operation and complex environmental conditions, thus achieving a more stable and efficient intelligent temperature control effect.

[0098] This embodiment also provides a temperature acquisition and control system for an intelligent temperature-controlled digestion furnace in industrial production, including: a data acquisition module for acquiring real-time temperature data, performing preliminary verification and missing data compensation, and generating a preliminary temperature dataset; a data fusion module for fusing the preliminary temperature dataset using Kalman filtering to generate fused temperature field data; a deviation calculation module for constructing a fuzzy logic control model, processing the fused temperature field data, calculating the actual temperature deviation and temperature change rate, and performing fuzzification processing to generate a fuzzy temperature deviation information set; a rule reasoning module for reasoning between the fuzzy temperature deviation information set and the fuzzy control rule set to generate a heating power adjustment command set; a power control module for sending the heating power adjustment command set to the heating element driver, adjusting the heating power in real time, and acquiring the latest temperature to generate a real-time temperature feedback dataset; and a model optimization module for performing fusion analysis on the real-time temperature feedback dataset and the fused temperature field data, updating the temperature field distribution, adjusting the fuzzy logic control model parameters, and generating an optimized control dataset.

[0099] This embodiment also provides a computer device applicable to the temperature acquisition and control method of an intelligent temperature-controlled digestion furnace for industrial production, 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 realize the temperature acquisition and control method of the intelligent temperature-controlled digestion furnace for industrial production as proposed in the above embodiment.

[0100] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0101] This embodiment also provides a storage medium storing a computer program. When executed by a processor, the program implements the temperature acquisition and control method for an intelligent temperature-controlled digestion furnace for industrial production as proposed in the above embodiments. 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 (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0102] In summary, this invention achieves dynamic optimization and integration of multi-source temperature signals by employing Kalman filtering to predict and update the state of the initial temperature dataset, and using the updated temperature estimation vector to calculate the Kalman gain for weighted data fusion, thereby generating fused temperature field data. This effectively suppresses single-point temperature measurement errors and noise interference, ensuring the overall continuity and stability of the temperature field, providing a more accurate data foundation for subsequent temperature control inference, improving temperature acquisition accuracy and anti-interference capability, and enabling the digestion furnace to maintain reliable temperature monitoring performance under complex operating conditions.

[0103] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for temperature acquisition and control of an intelligent temperature-controlled digestion furnace for industrial production, characterized in that: include, Collect real-time temperature data, perform preliminary verification and missing data compensation, and generate a preliminary temperature dataset; The Kalman filter method is used to fuse the preliminary temperature dataset to generate fused temperature field data; A fuzzy logic control model is constructed to process the fused temperature field data, calculate the actual temperature deviation and temperature change rate, and perform fuzzification processing to generate a fuzzy temperature deviation information set. Reasoning is performed on the fuzzy temperature deviation information set and the fuzzy control rule set to generate a heating power adjustment instruction set; The heating power adjustment command set is sent to the heating element driver to adjust the heating power in real time and collect the latest temperature to generate a real-time temperature feedback dataset. The real-time temperature feedback dataset and the fused temperature field data are fused and analyzed to update the temperature field distribution and adjust the parameters of the fuzzy logic control model, thereby generating an optimized control dataset.

2. The temperature acquisition and control method for an intelligent temperature-controlled digestion furnace in industrial production as described in claim 1, characterized in that: The specific steps for generating the preliminary temperature dataset are as follows. Perform range checks and anomaly marking on real-time temperature data to generate a preliminary dataset of suspected temperatures; Missing value compensation and trend interpolation are performed on the initial suspicious temperature dataset to generate a smoothed and corrected temperature dataset. The smoothed temperature dataset is weighted and its integrity is verified to generate a preliminary temperature dataset.

3. The temperature acquisition and control method for an intelligent temperature-controlled digestion furnace in industrial production as described in claim 1, characterized in that: The specific steps for generating the fused temperature field data are as follows: The Kalman filter method is used to perform state prediction and measurement update on the preliminary temperature dataset to generate an updated temperature estimation vector. Based on the updated temperature estimation vector and the initial temperature dataset, the Kalman gain is calculated, and the initial temperature dataset is weighted and fused using the Kalman gain to generate the initial fused temperature dataset. The initial fused temperature dataset is smoothed and anomaly corrected to generate fused temperature field data.

4. The temperature acquisition and control method for an intelligent temperature-controlled digestion furnace in industrial production as described in claim 1, characterized in that: The specific steps for constructing the fuzzy logic control model are as follows: Based on the temperature control requirements of the digestion furnace and the temperature range measured by each temperature acquisition device, the target temperature is obtained, and input and output variables are set. At the same time, membership functions are set for the input and output variables to generate a membership function set. Based on the membership function set and historical temperature control data, the fuzzy state of the input variable is mapped to the fuzzy control action of the output variable to generate a fuzzy control rule set; Using the membership function set, the preliminary temperature dataset and the target temperature are fuzzified, and rule matching and aggregation inference are performed according to the fuzzy control rule set to generate a fuzzy output control set; The fuzzy output control set is defuzzified to generate a heating power adjustment instruction set. Combined with the latest temperature dataset, the fuzzy control rule set and membership function set are optimized to generate a fuzzy logic control model.

5. The temperature acquisition and control method for an intelligent temperature-controlled digestion furnace in industrial production as described in claim 1, characterized in that: The specific steps for generating the fuzzy temperature deviation information set are as follows. The fused temperature field data is compared with the target temperature to obtain the actual temperature deviation; The temperature change rate is obtained by performing time series difference calculation on the fused temperature field data; The temperature deviation signal and the rate of temperature change are input into the fuzzy logic control model, fuzzified, and a fuzzified temperature deviation information set is generated.

6. The temperature acquisition and control method for an intelligent temperature-controlled digestion furnace in industrial production as described in claim 1, characterized in that: The specific steps for generating the heating power adjustment instruction set are as follows: The fuzzy temperature deviation information set is matched with the fuzzy control rule set one by one, the applicability of each fuzzy control rule is calculated, and a fuzzy rule matching matrix is ​​generated. The fuzzy rule matching matrix is ​​weighted and aggregated to form a fuzzy control action set; The fuzzy control action set is defuzzified to generate a heating power adjustment instruction set.

7. The temperature acquisition and control method for an intelligent temperature-controlled digestion furnace in industrial production as described in claim 1, characterized in that: The specific steps for generating the real-time temperature feedback dataset are as follows: The heating power adjustment instruction set is converted into control instructions that the driver can execute and sent to the heating element driver to generate drive confirmation information; Based on the drive confirmation information, the heating element driver executes control commands, performs power regulation, outputs the actual power status, and generates real-time power feedback data. Using real-time power feedback data, noise suppression and correction are performed on the timestamped temperature signal collected by the temperature acquisition device to generate a smooth temperature sequence; The smoothed temperature sequence, drive confirmation information, and real-time power feedback data are fused and verified to generate a real-time temperature feedback dataset.

8. The temperature acquisition and control method for an intelligent temperature-controlled digestion furnace in industrial production as described in claim 1, characterized in that: The specific steps for generating the optimized control dataset are as follows: Align and verify the real-time temperature feedback dataset with the fused temperature field data to generate a corrected temperature dataset; A difference analysis is performed between the corrected temperature dataset and the predicted temperature vector to generate temperature deviation mapping data. Based on the temperature deviation mapping data, the parameters of the fuzzy logic control model are iteratively optimized to generate an optimized control parameter set. The temperature field distribution is then updated using the optimized control parameter set, and the optimized control parameter sets are merged to form an optimized control dataset.

9. The temperature acquisition and control method for an intelligent temperature-controlled digestion furnace in industrial production as described in claim 8, characterized in that: The specific steps for performing difference analysis between the corrected temperature dataset and the predicted temperature vector to generate temperature deviation mapping data are as follows. The preliminary fused temperature dataset is input into the fuzzy logic control model. Based on the parameters of the fuzzy logic control model and the previous heating power adjustment command, the predicted temperature is calculated and a predicted temperature vector is generated. The corrected temperature dataset and the predicted temperature vector are matched in time and space to generate an aligned temperature pair set. The deviation between the actual temperature and the predicted temperature is calculated for each acquisition point in the aligned temperature pair set to generate a preliminary temperature difference vector. The initial temperature difference vector is weighted to generate a weighted temperature difference vector, and then smoothed and anomaly-handled to generate temperature deviation mapping data.

10. A temperature acquisition and control system for an intelligent temperature-controlled digestion furnace for industrial production, based on the temperature acquisition and control method for an intelligent temperature-controlled digestion furnace for industrial production as described in any one of claims 1 to 9, characterized in that: include, The data acquisition module is used to collect real-time temperature data, perform preliminary verification and missing data compensation, and generate a preliminary temperature dataset. The data fusion module is used to fuse the preliminary temperature dataset using the Kalman filter method to generate fused temperature field data. The deviation calculation module is used to construct a fuzzy logic control model, process the fused temperature field data, calculate the actual temperature deviation and temperature change rate, and perform fuzzification processing to generate a fuzzy temperature deviation information set. The rule reasoning module is used to reason about the fuzzy temperature deviation information set and the fuzzy control rule set to generate a heating power adjustment instruction set; The power control module is used to send the heating power adjustment command set to the heating element driver, adjust the heating power in real time, and collect the latest temperature to generate a real-time temperature feedback dataset. The model optimization module is used to perform fusion analysis on the real-time temperature feedback dataset and the fused temperature field data, update the temperature field distribution, adjust the parameters of the fuzzy logic control model, and generate an optimized control dataset.

Images