Kiln temperature consistency control method and device, computer equipment and medium

Abstract

The invention relates to the technical field of kiln temperature control. The kiln temperature consistency control method comprises the steps that kiln internal environment information is input into a temperature change prediction model, temperature fluctuation trend information is obtained, kiln temperature control optimization parameters are generated according to the temperature fluctuation trend information, and the kiln temperature consistency is controlled according to the kiln temperature control optimization parameters. The current operation parameter is kept if the adjusted environment information conforms to a kiln temperature control target value, and the adjusted environment information is input into the temperature change prediction model again if the adjusted environment information does not conform to the kiln temperature control target value to generate a new kiln temperature control optimization parameter. And on the basis of the new kiln temperature control optimization parameter, the operation parameter in the kiln is adjusted again until the adjusted environment information accords with the kiln temperature control target value. The method has the effect of ensuring the consistency of the internal temperature of the kiln.

Description

Technical Field

[0001] The present invention relates to the technical field of kiln temperature control, and in particular to a kiln temperature consistency control method, device, computer equipment and medium. Background Art

[0002] Kilns are important heat treatment equipment in industrial production and are widely used in ceramics, glass, metallurgy and other industries. With the rapid development of modern manufacturing, the requirements for product quality are getting higher and higher. As one of the key production equipment, the temperature consistency of kilns directly affects the quality and output of products. Therefore, how to ensure the consistency of the temperature inside the kiln has become a technical problem that needs to be solved urgently. Summary of the invention

[0003] In order to ensure the consistency of the temperature inside the kiln, the present application provides a kiln temperature consistency control method, device, computer equipment and medium.

[0004] The above-mentioned invention objective of the present application is achieved through the following technical solutions: A method for controlling the temperature consistency of a kiln, the method comprising: Obtain the internal environment information of the kiln; Inputting the internal environment information of the kiln into a temperature change prediction model, using the temperature change prediction model to analyze the current operation status of the kiln to obtain temperature fluctuation trend information; Generate kiln temperature control optimization parameters based on the temperature fluctuation trend information and target temperature control requirements; According to the kiln temperature control optimization parameters, the operating parameters inside the kiln are adjusted in real time to obtain adjusted environmental information; Comparing the adjusted environmental information with the kiln temperature control target value, and if the adjusted environmental information meets the kiln temperature control target value, maintaining the current operating parameters; If the adjusted environmental information does not meet the kiln temperature control target value, the adjusted environmental information is re-input into the temperature change prediction model to generate new kiln temperature control optimization parameters, and the operating parameters inside the kiln are adjusted again based on the new kiln temperature control optimization parameters until the adjusted environmental information meets the kiln temperature control target value.

[0005] By adopting the above technical solution and with the help of the temperature change prediction model, it is possible to comprehensively analyze the current kiln operating status and temperature fluctuation trends, and quickly identify the temperature change patterns and abnormal fluctuations in different areas. According to the temperature fluctuation trend information, combined with the target temperature control requirements, the optimization parameters are generated, and the operating parameters such as fuel supply, airflow distribution and heating power can be dynamically adjusted to fundamentally reduce the temperature gradient between regions and ensure the consistency of the temperature distribution of the entire kiln. By obtaining the adjusted environmental information and comparing it with the target value, a closed-loop feedback control mechanism is formed, which can evaluate the adjustment effect in real time, accurately correct the operating parameters, continuously optimize the temperature control process, and avoid local overheating or insufficient temperature problems. The prediction model is input again according to the adjusted environmental information, and new optimization parameters are automatically generated to ensure that the system can quickly adapt to the dynamic changes in operating conditions, thereby achieving long-term and stable temperature consistency control.

[0006] In a preferred example, the present application may be further configured as follows: the kiln historical operating parameters are obtained, and a training set and a verification set characterizing the relationship between the temperature fluctuation inside the kiln and the environmental parameters are generated according to the kiln historical operating parameters; Using the training set, training the model through a supervised learning algorithm to obtain an initial temperature change prediction model; Using the validation set to perform a performance evaluation on the initial temperature change prediction model to obtain a model evaluation result; The initial temperature change prediction model is optimized according to the model evaluation result until the initial temperature change prediction model meets the prediction accuracy requirement, thereby obtaining the temperature change prediction model.

[0007] By adopting the above technical solution, using the supervised learning algorithm to train the model on the training set, combined with the performance evaluation and optimization process of the validation set, the prediction accuracy of the model can be effectively improved, ensuring that the temperature change prediction model can accurately reflect the temperature control characteristics in the kiln and reduce prediction errors. In the model training process, by inputting a large amount of historical operation data and a variety of training samples, the model can fully learn the complex characteristics of the kiln operation, such as the impact of temperature fluctuations and changes in environmental parameters on temperature control, thereby improving the model's adaptability to a variety of complex working conditions. Through the optimized temperature change prediction model, the temperature change trend of each area of ​​the kiln can be more accurately predicted, providing accurate data support for subsequent temperature control optimization, thereby achieving precise temperature control adjustment.

[0008] In a preferred example, the present application can be further configured as follows: the internal environment information of the kiln is input into a temperature change prediction model, and the temperature change prediction model is used to analyze the current operation state of the kiln to obtain temperature fluctuation trend information, including: Extracting features of the internal environment information of the kiln through the temperature change prediction model, and extracting temperature control feature parameters corresponding to the temperature control target of the kiln; The temperature change prediction model predicts the temperature control characteristic parameters and calculates the temperature change trend curve information of each area of ​​the kiln; According to the temperature change trend curve information, the temperature fluctuation amplitude of each area of ​​the kiln is predicted to obtain the temperature fluctuation trend information.

[0009] By adopting the above technical solution, based on the extracted temperature control characteristic parameters, the temperature change trend curve of each area of ​​the kiln is generated through the prediction model, which can fully reflect the dynamic change of temperature over time, including the direction of change, the rate of change and the key turning points of the trend, and provide a scientific basis for optimizing the temperature control strategy. By analyzing the temperature change trend curve information and further predicting the temperature fluctuation amplitude of each area, it is possible to identify in advance the problems of overheating, excessive temperature difference or local abnormal fluctuations that may exist in the operation of the kiln, and reduce the production risks caused by uneven temperature control. Accurately predicting the temperature fluctuation trend will help achieve a more uniform temperature control effect. In a preferred example, the present application can be further configured as follows: the temperature change prediction model predicts the temperature control characteristic parameters and calculates the temperature change trend curve information of each area of ​​the kiln, including: The temperature change prediction model establishes a temperature change trend prediction formula based on the temperature control characteristic parameters. The temperature change trend prediction formula is expressed as: , where T i (t), P i (t), V i (t), the ΔT i (t), said P i (t), the V i (t) and the ΔT i (t) are the temperature, ambient pressure, air flow velocity and temperature change rate at time t, respectively. i (t+1) is the predicted temperature of furnace zone i at time t+1, and the ΔT i (t) = T i (t)−T i (t−1) represents the temperature change rate at time t, α is the temperature weight coefficient, β is the pressure weight coefficient, γ is the airflow velocity weight coefficient, η is the temperature change rate weight coefficient, and ε i (t) is the error correction term; The temperature change trend prediction formula is used to calculate the temperature values ​​of each area of ​​the kiln at different time points to generate the temperature change trend curve information.

[0010] By adopting the above technical solution and using the temperature change trend prediction formula, a variety of key parameters such as temperature, pressure, air flow velocity and temperature change rate are comprehensively modeled, which can accurately describe the dynamic law of temperature changes inside the kiln and significantly improve the accuracy of temperature prediction. The time step prediction method based on the formula can calculate the temperature change values ​​of each area of ​​the kiln at different times in the future and grasp the temperature evolution trend in advance. By calculating the temperature values ​​at each time point, the temperature change trend curve information is generated. This curve can not only intuitively reflect the dynamic changes in temperature in each area of ​​the kiln.

[0011] In a preferred example, the present application can be further configured as follows: predicting the temperature fluctuation amplitude of each area of ​​the kiln according to the temperature change trend curve information to obtain the temperature fluctuation trend information, including: Based on the temperature change trend data, analyzing the upper and lower temperature limits of each area of ​​the kiln, and calculating the temperature fluctuation amplitude; The rate of change of temperature over time is calculated through the temperature fluctuation amplitude, and the temperature change rate of each area of ​​the kiln is predicted. According to the temperature change rate, the temperature fluctuation trend information is generated.

[0012] By adopting the above technical solution, based on the temperature change trend data, the upper and lower temperature limits of each area can be accurately analyzed, so as to clearly define the temperature fluctuation range. By calculating the temperature fluctuation amplitude of each area of ​​the kiln, the temperature fluctuation can be intuitively quantified, which helps to identify high fluctuation areas and temperature abnormal areas. By using the temperature fluctuation amplitude and combining the time dimension to dynamically calculate the rate of change of temperature in each area over time, the trend of temperature change can be accurately determined, helping to achieve fast response temperature control adjustment.

[0013] In a preferred example, the present application can be further configured as follows: generating kiln temperature control optimization parameters according to the temperature fluctuation trend information and the target temperature control requirements, including: According to the temperature fluctuation trend information, the temperature distribution state of each area of ​​the current kiln is obtained; In combination with the target temperature control requirement, determining the target temperature range of each area of ​​the current kiln; Based on the temperature distribution state and the target temperature range, the operation control parameters to be adjusted are analyzed, and the kiln temperature control optimization parameters corresponding to the operation control parameters to be adjusted are generated.

[0014] By adopting the above technical solution, the actual temperature distribution status of each area of ​​the current kiln can be accurately analyzed according to the temperature fluctuation trend information, including temperature gradient, temperature difference distribution and local abnormal areas. Based on the comparative analysis of the temperature distribution status and the target temperature range, the operating control parameters that need to be adjusted can be accurately identified. By dynamically analyzing the difference between the temperature distribution status and the target range, the temperature of each area of ​​the kiln can be accurately controlled, the occurrence of areas with too high or too low temperature can be reduced, and the overall temperature control stability of the kiln can be improved.

[0015] In a preferred example, the present application can be further configured as follows: adjusting the operating parameters inside the kiln in real time according to the kiln temperature control optimization parameters to obtain the adjusted environmental information, including: According to the kiln temperature control optimization parameters, determining the adjustment direction and adjustment range of the operating parameters to be adjusted; Based on the adjustment direction and the adjustment range, the operating parameters inside the kiln are adjusted. After the parameter adjustment is completed, the real-time environmental information of the kiln is obtained, and the real-time environmental information of the kiln is summarized to obtain the adjusted environmental information.

[0016] By adopting the above technical solution, based on the kiln temperature control optimization parameters, the operating parameters that need to be adjusted and their adjustment direction and amplitude can be accurately analyzed, such as increasing fuel supply, increasing air flow speed or reducing heating power. By clearly adjusting the direction and amplitude, the operating parameters inside the kiln can be dynamically adjusted to quickly respond to changes in temperature control requirements. After the adjustment is completed, by obtaining the real-time environmental information of the kiln and summarizing it as the adjusted environmental information, a closed-loop control mechanism can be formed to monitor the adjustment effect in real time to ensure that the adjustment operation achieves the expected goal.

[0017] The second object of the invention is achieved by the following technical solutions: A kiln temperature consistency control device, the kiln temperature consistency control device comprising: Kiln environment information collection module, used to obtain the internal environment information of the kiln; A temperature change analysis module, used to input the internal environment information of the kiln into a temperature change prediction model, and use the temperature change prediction model to analyze the current operation status of the kiln to obtain temperature fluctuation trend information; A temperature control optimization parameter generation module is used to generate kiln temperature control optimization parameters according to the temperature fluctuation trend information and the target temperature control requirements; An operating parameter adjustment module is used to adjust the operating parameters inside the kiln in real time according to the kiln temperature control optimization parameters to obtain adjusted environmental information; A target value comparison module, used to compare the adjusted environmental information with the kiln temperature control target value, and if the adjusted environmental information meets the kiln temperature control target value, maintain the current operating parameters; The feedback iterative optimization module is used to re-input the adjusted environmental information into the temperature change prediction model if the adjusted environmental information does not meet the kiln temperature control target value, generate new kiln temperature control optimization parameters, and adjust the operating parameters inside the kiln again based on the new kiln temperature control optimization parameters until the adjusted environmental information meets the kiln temperature control target value.

[0018] By adopting the above technical solution and with the help of the temperature change prediction model, it is possible to comprehensively analyze the current kiln operating status and temperature fluctuation trends, and quickly identify the temperature change patterns and abnormal fluctuations in different areas. According to the temperature fluctuation trend information, combined with the target temperature control requirements, the optimization parameters are generated, and the operating parameters such as fuel supply, airflow distribution and heating power can be dynamically adjusted to fundamentally reduce the temperature gradient between regions and ensure the consistency of the temperature distribution of the entire kiln. By obtaining the adjusted environmental information and comparing it with the target value, a closed-loop feedback control mechanism is formed, which can evaluate the adjustment effect in real time, accurately correct the operating parameters, continuously optimize the temperature control process, and avoid local overheating or insufficient temperature problems. The prediction model is input again according to the adjusted environmental information, and new optimization parameters are automatically generated to ensure that the system can quickly adapt to the dynamic changes in operating conditions, thereby achieving long-term and stable temperature consistency control.

[0019] The third objective of the present application is achieved through the following technical solutions: A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned kiln temperature consistency control method when executing the computer program.

[0020] The fourth objective of the present application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned kiln temperature consistency control method are implemented.

[0021] In summary, the present application includes at least one of the following beneficial technical effects: 1. With the help of the temperature change prediction model, the current kiln operating status and temperature fluctuation trends can be comprehensively analyzed, and the temperature change patterns and abnormal fluctuations in different areas can be quickly identified. According to the temperature fluctuation trend information, combined with the target temperature control requirements, the optimization parameters can be generated, and the operating parameters such as fuel supply, airflow distribution and heating power can be dynamically adjusted to fundamentally reduce the temperature gradient between areas and ensure the consistency of the temperature distribution of the entire kiln. By obtaining the adjusted environmental information and comparing it with the target value, a closed-loop feedback control mechanism is formed, which can evaluate the adjustment effect in real time, accurately correct the operating parameters, continuously optimize the temperature control process, and avoid local overheating or insufficient temperature problems. The prediction model is input again according to the adjusted environmental information, and new optimization parameters are automatically generated to ensure that the system can quickly adapt to the dynamic changes in operating conditions, thereby achieving long-term and stable temperature consistency control; 2. Based on the temperature fluctuation trend information, the actual temperature distribution status of each area of ​​the current kiln can be accurately analyzed, including temperature gradient, temperature difference distribution and local abnormal areas. Based on the comparative analysis of the temperature distribution status and the target temperature range, the operation control parameters that need to be adjusted can be accurately identified. By dynamically analyzing the difference between the temperature distribution status and the target range, the temperature of each area of ​​the kiln can be accurately controlled, the occurrence of areas with too high or too low temperature can be reduced, and the overall temperature control stability of the kiln can be improved; 3. Using the temperature change trend prediction formula, a variety of key parameters such as temperature, pressure, air flow velocity and temperature change rate are comprehensively modeled, which can accurately describe the dynamic law of temperature changes inside the kiln and significantly improve the accuracy of temperature prediction. The time step prediction method based on the formula can calculate the temperature change values ​​of each area of ​​the kiln at different times in the future and grasp the temperature evolution trend in advance. By calculating the temperature values ​​at each time point, the temperature change trend curve information is generated. This curve can not only intuitively reflect the dynamic changes in temperature in each area of ​​the kiln. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 is a flow chart of a method for controlling kiln temperature consistency in one embodiment of the present application; Figure 2 This is a flowchart of the implementation of the kiln temperature consistency control method before step S20 in one embodiment of the present application; Figure 3 This is a flowchart for implementing step S20 in a method for controlling the temperature consistency of a kiln in an embodiment of the present application; Figure 4 This is a flowchart for implementing step S202 in a method for controlling the temperature consistency of a kiln in an embodiment of the present application; Figure 5 This is a flowchart for implementing step S203 in the kiln temperature consistency control method in one embodiment of the present application; Figure 6This is a flowchart for implementing step S30 in a method for controlling the temperature consistency of a kiln in an embodiment of the present application; Figure 7 This is a flowchart for implementing step S40 in a method for controlling the temperature consistency of a kiln in an embodiment of the present application; Figure 8 This is a principle block diagram of a kiln temperature consistency control device in one embodiment of the present application; Fig. 9 It is a schematic diagram of a device in an embodiment of the present application. DETAILED DESCRIPTION

[0023] The present application is further described in detail below in conjunction with the accompanying drawings.

[0024] In one embodiment, if Figure 1 As shown, the present application discloses a method for controlling the temperature consistency of a kiln, which specifically includes the following steps: S10: Obtaining the internal environment information of the kiln.

[0025] Specifically, by arranging temperature sensors, pressure sensors and gas concentration sensors in multiple key areas inside the kiln, the sensor arrangement points cover high-temperature areas, low-temperature areas and areas easily affected by external conditions. The sensors are used to collect real-time environmental information, including temperature information, pressure information and gas concentration information inside the kiln.

[0026] S20: Inputting the internal environment information of the kiln into the temperature change prediction model, using the temperature change prediction model to analyze the current operation status of the kiln, and obtaining the temperature fluctuation trend information.

[0027] Specifically, the acquired internal environmental information of the kiln is input into the temperature change prediction model. The temperature change prediction model performs dynamic analysis based on historical information and real-time information. The model extracts core temperature control features through a feature extraction algorithm, including the temperature change rate, pressure fluctuation trend, and correlation characteristics of gas concentration. The temperature distribution state and fluctuation trend of the current kiln are calculated through the trained prediction model, and the current operating state is further analyzed. The generated temperature fluctuation trend information includes the temperature change curves of each area of ​​the kiln, the fluctuation range, and possible abnormal area information.

[0028] S30: Generate kiln temperature control optimization parameters based on temperature fluctuation trend information and target temperature control requirements.

[0029] Specifically, the temperature fluctuation trend information is used to analyze the current temperature control status of each area of ​​the kiln, including the deviation between the current temperature and the target temperature range, the amplitude of the temperature fluctuation and its rate of change. Combined with the target temperature control requirements, such as uniform temperature control requirements or target temperature setting values ​​for certain specific areas, an optimization calculation method based on a genetic algorithm is used to generate the kiln temperature control optimization parameters. By calculating the difference between the target temperature control requirement and the current temperature control state, the best combination of adjustment parameters is iteratively calculated, and finally the kiln temperature control optimization parameters are generated, including adjusting the fuel supply, airflow distribution parameters and specific optimization values ​​of the heating power.

[0030] S40: According to the kiln temperature control optimization parameters, the operating parameters inside the kiln are adjusted in real time to obtain adjusted environmental information.

[0031] Specifically, the generated kiln temperature control optimization parameters are used as execution signals and directly transmitted to the execution device. The fuel supply is adjusted by adjusting the opening of the supply valve. The airflow distribution is achieved by controlling the wind speed and wind direction of the air supply device. The heating power is dynamically regulated by adjusting the current output of the electric heating equipment or the gas supply of the combustion equipment. During the adjustment process, the adjusted temperature information, pressure information and gas concentration information are obtained in real time through sensors. The adjustment results are used as the adjusted environmental information to verify whether the adjustment has achieved the expected goals and for subsequent analysis.

[0032] S50: Compare the adjusted environmental information with the kiln temperature control target value. If the adjusted environmental information meets the kiln temperature control target value, maintain the current operating parameters.

[0033] Specifically, the adjusted environmental information is compared item by item with the temperature control target value of the kiln. The temperature control target value includes the target temperature range, the allowable fluctuation amplitude, and the limited range of pressure and gas concentration. The comparison process is completed by calculating the deviation between the adjusted environmental information and the target value, wherein the temperature deviation is realized by calculating the difference between the adjusted actual temperature and the target temperature, and the fluctuation amplitude is realized by comparing the extreme value difference of the time series with the target range. If all deviations are within the target value range, it is judged that the adjusted environmental information meets the temperature control target value, and the current operating parameters are kept unchanged.

[0034] S60: If the adjusted environmental information does not meet the kiln temperature control target value, the adjusted environmental information is re-input into the temperature change prediction model to generate new kiln temperature control optimization parameters, and the operating parameters inside the kiln are adjusted again based on the new kiln temperature control optimization parameters until the adjusted environmental information meets the kiln temperature control target value.

[0035] Specifically, when the comparison result between the adjusted environmental information and the kiln temperature control target value shows that the deviation exceeds the allowable range, the adjusted environmental information will be re-transmitted as input to the temperature change prediction model. The model will re-analyze the kiln operating status and calculate new temperature control optimization parameters. The newly generated optimization parameters include the fuel adjustment amount, airflow optimization direction and power change value, which are again transmitted to the execution device to execute the operating parameter adjustment. At the same time, the adjustment results are collected in real time, and the environmental information acquisition, optimization calculation and parameter adjustment are repeated until the deviation between the adjusted environmental information and the temperature control target value fully meets the target requirements.

[0036] In one embodiment, if Figure 2 As shown, before step S20, the temperature change prediction model includes: S11: Obtain the historical operating parameters of the kiln, and generate a training set and a verification set that characterize the relationship between the temperature fluctuation inside the kiln and the environmental parameters based on the historical operating parameters of the kiln.

[0037] Specifically, historical operating parameter information, including temperature, pressure, gas concentration, fuel supply of operating equipment, airflow distribution parameters and heating power parameters, is retrieved from the kiln operation database. These historical operating parameters are stored in the form of time series and record the temperature fluctuation characteristics of the kiln under different operating conditions. By analyzing the relationship between the law of temperature fluctuation inside the kiln in the historical operating parameters and the changes in environmental parameters, key variables characterizing the temperature change characteristics are extracted, such as temperature fluctuation amplitude, change rate and abnormal point distribution. The correlation of characteristic variables is used to generate training sets and validation sets, where the training set accounts for 80% of the historical operating parameters and the validation set accounts for 20%. The training set is used for model learning and training, and the validation set is used for model performance evaluation. S12: Using the training set, the model is trained through a supervised learning algorithm to obtain an initial temperature change prediction model.

[0038] Specifically, the generated training set is input into the supervised learning model. The model adopts a hybrid algorithm based on regression analysis and neural network. Regression analysis is used to establish the linear relationship between temperature fluctuation characteristics and environmental parameters, and neural network is used to capture nonlinear change laws. The model structure includes input layer, hidden layer and output layer. The input layer receives the environmental parameters and temperature fluctuation characteristics in the training set. The hidden layer performs feature mapping through a multi-layer network to extract the correlation between environmental parameters and temperature fluctuations. The weight coefficient of the model is continuously optimized through the back propagation algorithm. The output layer generates temperature change prediction values. A loss function is set during the training process to evaluate the error between the predicted value and the actual value. The loss function is minimized by the gradient descent method, and the model parameters are gradually adjusted. After the training is completed, the initial temperature change prediction model is output.

[0039] S13: Use the validation set to evaluate the performance of the initial temperature change prediction model and obtain the model evaluation results.

[0040] Specifically, the environmental information in the validation set is input into the initial temperature change prediction model one by one. The model generates predicted temperature values ​​based on the input environmental information, and then compares the predicted values ​​with the actual measured temperature values ​​in the validation set point by point. The performance of the model is comprehensively analyzed by calculating multiple evaluation indicators. First, the mean square error (MSE) is calculated. Specifically, the difference between each predicted value and the actual value in the validation set is taken, and the difference is squared and averaged to measure the overall deviation level between the model predicted value and the actual value. The formula is expressed as: , T i，pred To predict the temperature value, T i，true is the true temperature value, and n is the total number of samples in the validation set. Then, the mean absolute error (MAE) is calculated. Specifically, the absolute value of the difference between each predicted value and the true value in the validation set is taken and averaged to measure the average deviation of the prediction results. The formula is: Next, calculate the coefficient of determination (R²). Specifically, the overall prediction performance of the model is evaluated by measuring the degree of fit between the predicted value and the true value. The closer the R² value is to 1, the better the prediction effect of the model. The formula is: ,in, is the average value of the true value in the validation set. In addition, in order to comprehensively evaluate the model performance, the prediction errors under different working conditions (such as high temperature operation, low temperature stability, and conditions with large airflow fluctuations) are grouped and statistically analyzed during the validation process. Specifically, by screening the specific working condition information in the validation set, the MSE, MAE, and R² values ​​under these working conditions are calculated separately, so as to analyze the adaptability and prediction ability of the model under different working conditions. Through these evaluation processes, a model performance evaluation report is generated.

[0041] S14: Optimizing the initial temperature change prediction model according to the model evaluation result until the initial temperature change prediction model meets the prediction accuracy requirement, thereby obtaining the temperature change prediction model.

[0042] Specifically, according to the quantitative indicators of mean square error, mean absolute error and prediction accuracy in the model evaluation results, the performance bottlenecks of the model under different working conditions are analyzed. For example, the reason for the large error under high temperature conditions may be insufficient nonlinear characteristics, and the model may be overfitting under low temperature stable conditions. The initial model is optimized by analyzing these problems, including adjusting the structural parameters of the model (such as the number of hidden layers and the number of nodes in each layer), modifying the loss function to enhance the fitting ability of nonlinear changes, and increasing the data weight in the high error area to improve the adaptability of the model to specific working conditions. During the optimization process, the model is iteratively optimized through repeated training and verification until the model meets the set prediction accuracy requirements on all evaluation indicators, and finally the optimized temperature change prediction model is obtained.

[0043] In one embodiment, if Figure 3 As shown, in step S20, the internal environment information of the kiln is input into the temperature change prediction model, and the temperature change prediction model is used to analyze the current operation state of the kiln to obtain temperature fluctuation trend information, including: S201: extracting features of the internal environment information of the kiln through a temperature change prediction model, and extracting temperature control feature parameters corresponding to the temperature control target of the kiln.

[0044] Specifically, the obtained internal environmental information of the kiln, including the temperature information, pressure information and gas concentration information of each area of ​​the kiln, is input into the temperature change prediction model. The input layer of the model will normalize different types of information to eliminate the influence of different data magnitudes. Then the model performs nonlinear mapping on the input information through the feature extraction layer to extract key characteristic parameters directly related to the temperature control target of the kiln, such as the temperature change rate, pressure gradient and gas concentration change curve. These characteristic parameters are core variables identified through the training process, which can reflect the impact of environmental changes during kiln operation on the temperature control effect. The feature extraction process is combined with historical operation data for correction, and redundant information is eliminated by automatically selecting the most important parameters. Finally, the temperature control characteristic parameters that can directly characterize temperature fluctuations and control requirements are extracted.

[0045] S202: The temperature change prediction model predicts the temperature control characteristic parameters and calculates the temperature change trend curve information of each area of ​​the kiln.

[0046] Specifically, the extracted temperature control characteristic parameters are input into the temperature change prediction model. The model uses the trained multi-layer structure to gradually predict the temperature control characteristic parameters. First, the temperature change trend of each area of ​​the current kiln is identified through time series analysis. The model generates a predicted value of the temperature change in each area in the future time period based on the correlation between the historical temperature control characteristics and the current input. The prediction result is expressed in the form of a trend curve, including the temperature value at each time point and the direction and amplitude of the temperature change. The temperature change trend curve information also includes predictions of key nodes, such as possible temperature peaks, valleys and mutation points of the change rate. This information can be used to characterize the dynamic temperature control characteristics of each area of ​​the kiln.

[0047] S203: Predicting the temperature fluctuation amplitude of each area of ​​the kiln according to the temperature change trend curve information, and obtaining the temperature fluctuation trend information.

[0048] Specifically, by analyzing the temperature change trend curve information, the key characteristic points in the curve are identified, including the highest temperature, the lowest temperature and the corresponding time points in each area. The temperature fluctuation amplitude of each area is calculated based on these key characteristic points. The temperature fluctuation amplitude represents the difference between the highest temperature and the lowest temperature. At the same time, the slope change characteristics of the curve are analyzed to predict the rate of temperature change and the mutation area. The temperature fluctuation trend information is generated by comprehensively analyzing the fluctuation amplitude, change rate and abnormal point distribution. The trend information is presented in an intuitive graphical form, which is used to dynamically reflect the temperature control stability of each area of ​​the kiln and provide a direct basis for optimizing the control strategy.

[0049] In one embodiment, if Figure 4 As shown, in step S202, the temperature change prediction model predicts the temperature control characteristic parameters and calculates the temperature change trend curve information of each area of ​​the kiln, including: S2021: The temperature change prediction model establishes a temperature change trend prediction formula based on the temperature control characteristic parameters. The temperature change trend prediction formula is expressed as: , where T i (t), P i (t), V i (t), ΔT i (t), P i (t), V i (t) and ΔT i (t) are the temperature, ambient pressure, air flow velocity and temperature change rate at time t, respectively. i (t+1) is the predicted temperature of kiln zone i at time t+1, ΔT i (t) = T i (t)−T i(t−1) represents the temperature change rate at time t, α is the temperature weight coefficient, β is the pressure weight coefficient, γ is the air flow velocity weight coefficient, η is the temperature change rate weight coefficient, ε i (t) is the error correction term.

[0050] Specifically, the temperature change trend prediction formula is established by combining nonlinear regression with time series analysis. First, based on the temperature control characteristic parameters in the historical operating parameters, the multivariate linear regression method is used to determine the basic linear relationship between key variables. Then, the time series analysis model is introduced to capture the dynamic nonlinear characteristics and time dependence in temperature changes. Finally, the comprehensive influence of temperature, pressure, airflow velocity and temperature change rate on the temperature control results is calculated through weighted optimization iteration to form a temperature change trend prediction formula.

[0051] S2022: Use the temperature change trend prediction formula to calculate the temperature values ​​of each area of ​​the kiln at different time points and generate temperature change trend curve information.

[0052] Specifically, the temperature control characteristic parameters are input into the temperature change trend prediction formula hour by hour. The formula gradually calculates the temperature value at each future moment by receiving characteristic parameters such as the temperature, ambient pressure, air flow velocity and temperature change rate of each area at the current moment. The prediction process is iteratively updated in units of time step Δt. For example, at time t+1, the predicted temperature value of each area is calculated using the characteristic parameters and prediction formula at time t, and then the predicted temperature value is used as the input of time t+1 to continue to calculate the temperature value at time t+2, and so on, until the temperature prediction of all time points within the target time range is completed; during the calculation process, the error correction term in the temperature change trend prediction formula will be dynamically adjusted to correct the deviation between the predicted value and the historical trend in real time, thereby improving the accuracy of the prediction. After completing the prediction of all time points, the predicted temperature values ​​of each area are integrated into a temperature change trend curve in the form of a time series. The curve uses time as the horizontal axis and temperature as the vertical axis to intuitively present the dynamic characteristics of temperature changes in each area of ​​the kiln, including the overall trend of temperature change, change rate, fluctuation amplitude and key nodes (such as peak value, valley value, mutation point) and other information, and generates temperature change trend curve information.

[0053] In one embodiment, if Figure 5 As shown, in step S203, the temperature fluctuation amplitude of each area of ​​the kiln is predicted according to the temperature change trend curve information, and the temperature fluctuation trend information is obtained, including: S2031: Based on the temperature change trend data, analyze the upper and lower temperature limits of each area of ​​the kiln and calculate the temperature fluctuation range.

[0054] Specifically, by analyzing the temperature change curves of each area in the temperature change trend data, representative key points in the temperature curve are extracted, including the highest temperature and the lowest temperature in each time period, where the upper temperature limit is determined by the local maximum value of the temperature curve, and the lower temperature limit is determined by the local minimum value of the temperature curve. To ensure the accuracy of data analysis, the temperature curve is smoothed using a sliding window algorithm to eliminate short-term abnormal points that may be caused by data acquisition noise. The size of the sliding window is dynamically set according to the operation cycle of the kiln and the historical temperature control law; after obtaining the upper and lower temperature limits of each area, the temperature fluctuation amplitude is calculated. The temperature fluctuation amplitude is defined as the difference between the upper temperature limit and the lower temperature limit. The specific calculation formula is: ΔT 幅度 =T 上限 −T 下限。 ΔT 幅度 is the temperature fluctuation amplitude, T 上限 Temperature upper limit, T 下限 is the lower limit of temperature.

[0055] S2032: Calculate the rate of temperature change over time through the temperature fluctuation amplitude, predict the temperature change rate of each area of ​​the kiln, and generate temperature fluctuation trend information based on the temperature change rate.

[0056] Specifically, based on the temperature fluctuation amplitude of each area, combined with the temperature value at each time point in the temperature change trend data, the temperature change rate of each area is calculated using the difference method. Specifically, the temperature change between adjacent time points is calculated and divided by the time interval. The temperature change rate formula is: , where T i (t+1) and T i (t) are the temperature values ​​at time t+1 and time t, respectively, and Δt is the time interval. The temperature change rate of each region at each time point is obtained through the above calculation; then, according to the temperature change rate, the temperature change law of each region is analyzed, including the direction of temperature change (increase or decrease), the speed of the change rate, and the mutation point of the change rate. By comparing the change rates of different regions, possible abnormal conditions in the temperature control state are identified. For example, if the temperature change rate of a certain region is significantly higher than that of other regions, it may indicate that there is a problem of local overheating or poor heat dissipation in the region; finally, according to the temperature change rate of each region and its evolution law over time, the temperature fluctuation trend information is generated. The temperature fluctuation trend information includes the temperature fluctuation amplitude, the change curve of the change rate over time, and the possible abnormal area. The formed fluctuation trend information is output in a visual form to guide the subsequent temperature control optimization and adjustment.

[0057] In one embodiment, if Figure 6As shown, in step S30, the kiln temperature control optimization parameters are generated according to the temperature fluctuation trend information and the target temperature control requirements, including: S301: Obtain the temperature distribution status of each area of ​​the current kiln according to the temperature fluctuation trend information.

[0058] Specifically, by analyzing the temperature change curve in the temperature fluctuation trend information, the actual temperature value of each area of ​​the kiln at the current time point is extracted, and the current temperature state is verified in combination with the historical trend data to ensure the accuracy of the data. The acquired temperature distribution state includes the temperature distribution range of each area, the temperature gradient between adjacent areas and the overall temperature consistency of the entire kiln. In addition, through a comprehensive analysis of the temperature change rate and fluctuation amplitude of each area in the temperature fluctuation trend, the possible local abnormal conditions of the current kiln are further identified, such as the temperature in a certain area is obviously too high or the fluctuation amplitude is too large. This information is presented in the form of a distribution diagram or matrix to clearly characterize the temperature distribution state of the current kiln.

[0059] S302: Determine the target temperature range of each area of ​​the current kiln in combination with the target temperature control requirements.

[0060] Specifically, according to the preset target temperature control requirements, the temperature control targets of the kiln as a whole and each area are clarified. For example, uniform temperature control requirements usually require that the temperature distribution of each area of ​​the entire kiln is as consistent as possible, and specific temperature control requirements may require different areas to have different target temperature ranges. The target temperature control requirements are compared with the current temperature distribution status to determine the target temperature range for each area. The target temperature range is defined by specific upper and lower limits. The upper limit value represents the maximum temperature allowed by the target, and the lower limit value represents the minimum temperature allowed by the target. In addition, combined with the historical data of the kiln operating conditions, the target temperature control range is dynamically adjusted. For example, under operating conditions with heavy loads, the temperature control range is appropriately relaxed to improve the flexibility of regulation. Under the requirements of precise control, the range is narrowed to ensure quality, and finally the target temperature range for each area of ​​the current kiln is formed. S303: Based on the temperature distribution state and the target temperature range, analyzing the operation control parameters that need to be adjusted, and generating kiln temperature control optimization parameters corresponding to the operation control parameters that need to be adjusted.

[0061] Specifically, by comparing the temperature distribution status of each area of ​​the current kiln with the target temperature range, the areas beyond the target range are identified, and the direction and amplitude of the temperature deviation in these areas are analyzed. For example, if the temperature of a certain area exceeds the target upper limit, it is judged as overheating, and it is necessary to reduce the fuel input or increase the airflow speed to lower the temperature. Conversely, if the temperature of a certain area is lower than the target lower limit, it is necessary to increase the fuel input or reduce the airflow speed to increase the temperature. After identifying the area that needs to be adjusted, combined with the current operating conditions, the operating control parameters that need to be adjusted are calculated, including the fuel input, airflow speed, wind direction angle and heating power adjustment amount. The calculation of the adjustment amount is based on the optimization algorithm. The optimization algorithm adopts a multi-objective optimization strategy, comprehensively considering the temperature control response speed, adjustment energy consumption and temperature control accuracy, and selects the optimal combination of operating control parameters through iterative calculation to finally generate the kiln temperature control optimization parameters.

[0062] In one embodiment, if Figure 7 As shown, in step S40, the operating parameters inside the kiln are adjusted in real time according to the kiln temperature control optimization parameters to obtain the adjusted environmental information, including: S401: Determine the adjustment direction and adjustment range of the operating parameters that need to be adjusted according to the kiln temperature control optimization parameters.

[0063] Specifically, if the actual temperature is higher than the upper limit of the target temperature control range, the adjustment direction to be lowered is determined, such as reducing the fuel input or increasing the airflow velocity. If the actual temperature is lower than the lower limit of the target temperature control range, the adjustment direction to be increased is determined, such as increasing the fuel supply or reducing the airflow velocity. At the same time, the current operating conditions of the kiln are analyzed, including the dynamic response capability of the fuel input system, the wind speed adjustment range of the air supply device, and the power output upper limit of the heating equipment, to ensure that the adjustment direction meets the current operating conditions. After determining the adjustment direction, the adjustment amplitude is calculated according to the temperature control optimization parameters. The calculation of the adjustment amplitude is achieved by combining the deviation amount with the adjustment coefficient in the optimization algorithm. For example, the temperature deviation value is proportionally mapped to the adjustment amount of the fuel supply, airflow velocity and heating power, and finally the specific direction and amplitude of the operating parameters to be adjusted are clarified.

[0064] S402: Based on the adjustment direction and adjustment range, the operating parameters inside the kiln are adjusted. After the parameter adjustment is completed, the real-time environmental information of the kiln is obtained, and the real-time environmental information of the kiln is summarized to obtain the adjusted environmental information.

[0065] Specifically, the increase or decrease of the fuel supply amount is achieved by adjusting the opening of the fuel supply valve. The adjustment range of the fuel valve is directly mapped from the adjustment range value to the change in the valve opening. The airflow velocity and direction are adjusted by controlling the fan speed and guide vane angle of the air supply device. The adjustment range of the airflow velocity is determined in real time according to the calculation results of the optimization algorithm. The dynamic regulation of the heating power is achieved by adjusting the current output of the electric heating equipment or the gas supply of the combustion equipment. After the parameter adjustment is completed, the internal environment information collection module of the kiln is immediately started. Through the sensors arranged in different areas of the kiln, real-time environmental information is collected, including adjusted temperature, pressure, gas concentration and other information. The collected information is summarized after anti-interference processing and data preprocessing. The summary content includes the latest temperature distribution, pressure status and gas concentration information of each area, and finally the adjusted environmental information is formed.

[0066] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0067] In one embodiment, a kiln temperature consistency control device is provided, and the kiln temperature consistency control device corresponds to the kiln temperature consistency control method in the above embodiment. Figure 8 As shown, the kiln temperature consistency control device includes a kiln environment information acquisition module, a temperature change analysis module, a temperature control optimization parameter generation module, an operation parameter adjustment module, a target value comparison module and a feedback iteration optimization module. The functional modules are described in detail as follows: Kiln environment information collection module, used to obtain the internal environment information of the kiln; The temperature change analysis module is used to input the internal environment information of the kiln into the temperature change prediction model, and use the temperature change prediction model to analyze the current operation status of the kiln to obtain the temperature fluctuation trend information; The temperature control optimization parameter generation module is used to generate the kiln temperature control optimization parameters according to the temperature fluctuation trend information and the target temperature control requirements; The operating parameter adjustment module is used to adjust the operating parameters inside the kiln in real time according to the kiln temperature control optimization parameters to obtain the adjusted environmental information; The target value comparison module is used to compare the adjusted environmental information with the kiln temperature control target value. If the adjusted environmental information meets the kiln temperature control target value, the current operating parameters are maintained; The feedback iterative optimization module is used to re-input the adjusted environmental information into the temperature change prediction model if the adjusted environmental information does not meet the kiln temperature control target value, generate new kiln temperature control optimization parameters, and adjust the internal operating parameters of the kiln again based on the new kiln temperature control optimization parameters until the adjusted environmental information meets the kiln temperature control target value.

[0068] Optionally, the temperature change analysis module includes: A historical operation parameter processing module is used to obtain the historical operation parameters of the kiln, and generate a training set and a verification set that characterize the relationship between the temperature fluctuation inside the kiln and the environmental parameters according to the historical operation parameters of the kiln; A model training module is used to train the model using a training set through a supervised learning algorithm to obtain an initial temperature change prediction model; A model performance evaluation module is used to evaluate the performance of the initial temperature change prediction model using a validation set to obtain a model evaluation result; The model optimization module is used to optimize the initial temperature change prediction model according to the model evaluation results until the initial temperature change prediction model meets the prediction accuracy requirements, thereby obtaining the temperature change prediction model.

[0069] Optional, temperature change analysis module includes: The temperature control characteristic parameter extraction submodule is used to extract the characteristics of the internal environment information of the kiln through the temperature change prediction model, and extract the temperature control characteristic parameters corresponding to the temperature control target of the kiln; The temperature change trend prediction submodule is used to predict the temperature control characteristic parameters using the temperature change prediction model and calculate the temperature change trend curve information of each area of ​​the kiln; The temperature fluctuation trend analysis submodule is used to predict the temperature fluctuation amplitude of each area of ​​the kiln according to the temperature change trend curve information and obtain the temperature fluctuation trend information.

[0070] Optionally, the temperature change trend prediction submodule includes: The change trend prediction formula unit is used for the temperature change prediction model to establish the temperature change trend prediction formula based on the temperature control characteristic parameters. The temperature change trend prediction formula is expressed as: , where T i (t), P i (t), V i (t), ΔT i (t) are the temperature, ambient pressure, air flow velocity and temperature change rate at time t, respectively. i (t+1) is the predicted temperature of kiln zone i at time t+1, ΔT i (t) = T i (t)−T i(t−1) represents the temperature change rate at time t, α is the temperature weight coefficient, β is the pressure weight coefficient, γ is the air flow velocity weight coefficient, η is the temperature change rate weight coefficient, ε i (t) is the error correction term; Temperature change trend calculation unit. Used to calculate the temperature values ​​of each area of ​​the kiln at different time points using the temperature change trend prediction formula, and generate temperature change trend curve information.

[0071] Optional, temperature fluctuation trend analysis submodule includes: The temperature fluctuation amplitude calculation unit is used to analyze the upper and lower temperature limits of each area of ​​the kiln based on the temperature change trend data and calculate the temperature fluctuation amplitude; The temperature change rate analysis unit is used to calculate the temperature change rate over time through the temperature fluctuation amplitude, predict the temperature change rate of each area of ​​the kiln, and generate temperature fluctuation trend information based on the temperature change rate.

[0072] Optionally, the temperature control optimization parameter generation module includes: The temperature distribution state acquisition submodule is used to obtain the temperature distribution state of each area of ​​the current kiln according to the temperature fluctuation trend information; The target temperature range determination submodule is used to determine the target temperature range of each area of ​​the current kiln in combination with the target temperature control requirements; The operation control parameter optimization submodule is used to analyze the operation control parameters that need to be adjusted based on the temperature distribution state and the target temperature range, and generate kiln temperature control optimization parameters corresponding to the operation control parameters that need to be adjusted.

[0073] Optionally, the operating parameter adjustment module includes: The submodule for determining the adjustment direction and amplitude of the operating parameters is used to determine the adjustment direction and amplitude of the operating parameters to be adjusted according to the kiln temperature control optimization parameters; The operating parameter adjustment execution submodule is used to adjust the operating parameters inside the kiln based on the adjustment direction and adjustment range. After completing the parameter adjustment, the real-time environmental information of the kiln is obtained, the real-time environmental information of the kiln is summarized, and the adjusted environmental information is obtained.

[0074] The specific definition of the kiln temperature consistency control device can be found in the definition of the kiln temperature consistency control method above, which will not be repeated here. Each module in the above kiln temperature consistency control device can be implemented in whole or in part by software, hardware and a combination thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0075] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig. 9 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used for a kiln operation database. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a kiln temperature consistency control method is implemented.

[0076] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: Obtain the internal environment information of the kiln; Input the internal environment information of the kiln into the temperature change prediction model, use the temperature change prediction model to analyze the current operation status of the kiln, and obtain the temperature fluctuation trend information; Generate kiln temperature control optimization parameters based on temperature fluctuation trend information and target temperature control requirements; According to the kiln temperature control optimization parameters, the operating parameters inside the kiln are adjusted in real time to obtain the adjusted environmental information; Compare the adjusted environmental information with the kiln temperature control target value. If the adjusted environmental information meets the kiln temperature control target value, keep the current operating parameters; If the adjusted environmental information does not meet the kiln temperature control target value, the adjusted environmental information will be re-input into the temperature change prediction model to generate new kiln temperature control optimization parameters, and the internal operating parameters of the kiln will be adjusted again based on the new kiln temperature control optimization parameters until the adjusted environmental information meets the kiln temperature control target value.

[0077] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: Obtain the internal environment information of the kiln; Input the internal environment information of the kiln into the temperature change prediction model, use the temperature change prediction model to analyze the current operation status of the kiln, and obtain the temperature fluctuation trend information; Generate kiln temperature control optimization parameters based on temperature fluctuation trend information and target temperature control requirements; According to the kiln temperature control optimization parameters, the operating parameters inside the kiln are adjusted in real time to obtain the adjusted environmental information; Compare the adjusted environmental information with the kiln temperature control target value. If the adjusted environmental information meets the kiln temperature control target value, keep the current operating parameters; If the adjusted environmental information does not meet the kiln temperature control target value, the adjusted environmental information will be re-input into the temperature change prediction model to generate new kiln temperature control optimization parameters, and the internal operating parameters of the kiln will be adjusted again based on the new kiln temperature control optimization parameters until the adjusted environmental information meets the kiln temperature control target value.

[0078] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0079] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0080] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for controlling the temperature consistency of a kiln, characterized in that: The kiln temperature consistency control method comprises: Obtain the internal environment information of the kiln; Inputting the internal environment information of the kiln into a temperature change prediction model, using the temperature change prediction model to analyze the current operation status of the kiln to obtain temperature fluctuation trend information; Generate kiln temperature control optimization parameters based on the temperature fluctuation trend information and target temperature control requirements; According to the kiln temperature control optimization parameters, the operating parameters inside the kiln are adjusted in real time to obtain adjusted environmental information; Comparing the adjusted environmental information with the kiln temperature control target value, and if the adjusted environmental information meets the kiln temperature control target value, maintaining the current operating parameters; If the adjusted environmental information does not meet the kiln temperature control target value, the adjusted environmental information is re-input into the temperature change prediction model to generate new kiln temperature control optimization parameters, and the operating parameters inside the kiln are adjusted again based on the new kiln temperature control optimization parameters until the adjusted environmental information meets the kiln temperature control target value.

2. The kiln temperature consistency control method according to claim 1, characterized in that: The temperature change prediction model previously included: Acquire historical operating parameters of the kiln, and generate a training set and a validation set that characterize the relationship between temperature fluctuations inside the kiln and environmental parameters based on the historical operating parameters of the kiln; Using the training set, training the model through a supervised learning algorithm to obtain an initial temperature change prediction model; Using the validation set to perform a performance evaluation on the initial temperature change prediction model to obtain a model evaluation result; The initial temperature change prediction model is optimized according to the model evaluation result until the initial temperature change prediction model meets the prediction accuracy requirement, thereby obtaining the temperature change prediction model.

3. The kiln temperature consistency control method according to claim 1, characterized in that: The step of inputting the internal environment information of the kiln into a temperature change prediction model, using the temperature change prediction model to analyze the current operation state of the kiln, and obtaining temperature fluctuation trend information includes: Performing feature extraction on the internal environment information of the kiln by using the temperature change prediction model to extract temperature control feature parameters corresponding to the temperature control target of the kiln; The temperature change prediction model predicts the temperature control characteristic parameters and calculates the temperature change trend curve information of each area of ​​the kiln; According to the temperature change trend curve information, the temperature fluctuation amplitude of each area of ​​the kiln is predicted to obtain the temperature fluctuation trend information.

4. The kiln temperature consistency control method according to claim 3, characterized in that: The temperature change prediction model predicts the temperature control characteristic parameters and calculates the temperature change trend curve information of each area of ​​the kiln, including: The temperature change prediction model establishes a temperature change trend prediction formula based on the temperature control characteristic parameters. The temperature change trend prediction formula is expressed as: , where T i (t), P i (t), V i (t), the ΔT i (t), said P i (t), the V i (t) and the ΔT i (t) are the temperature, ambient pressure, air flow velocity and temperature change rate at time t, respectively. i (t+1) is the predicted temperature of furnace zone i at time t+1, and the ΔT i (t) = T i (t)−T i (t−1) represents the temperature change rate at time t, α is the temperature weight coefficient, β is the pressure weight coefficient, γ is the airflow velocity weight coefficient, η is the temperature change rate weight coefficient, and ε i (t) is the error correction term; The temperature change trend prediction formula is used to calculate the temperature values ​​of each area of ​​the kiln at different time points to generate the temperature change trend curve information.

5. The kiln temperature consistency control method according to claim 3, characterized in that: The step of predicting the temperature fluctuation amplitude of each area of ​​the kiln according to the temperature change trend curve information to obtain the temperature fluctuation trend information includes: Based on the temperature change trend data, analyzing the upper and lower temperature limits of each area of ​​the kiln, and calculating the temperature fluctuation amplitude; The rate of change of temperature over time is calculated through the temperature fluctuation amplitude, and the temperature change rate of each area of ​​the kiln is predicted. According to the temperature change rate, the temperature fluctuation trend information is generated.

6. The kiln temperature consistency control method according to claim 1, characterized in that: The method of generating kiln temperature control optimization parameters according to the temperature fluctuation trend information and the target temperature control requirements includes: According to the temperature fluctuation trend information, the temperature distribution state of each area of ​​the current kiln is obtained; In combination with the target temperature control requirement, determining the target temperature range of each area of ​​the current kiln; Based on the temperature distribution state and the target temperature range, the operation control parameters to be adjusted are analyzed, and the kiln temperature control optimization parameters corresponding to the operation control parameters to be adjusted are generated.

7. The kiln temperature consistency control method according to claim 1, characterized in that: According to the kiln temperature control optimization parameters, the operating parameters inside the kiln are adjusted in real time to obtain the adjusted environmental information, including: According to the kiln temperature control optimization parameters, determining the adjustment direction and adjustment range of the operating parameters to be adjusted; Based on the adjustment direction and the adjustment range, the operating parameters inside the kiln are adjusted. After the parameter adjustment is completed, the real-time environmental information of the kiln is obtained, and the real-time environmental information of the kiln is summarized to obtain the adjusted environmental information.

8. A kiln temperature consistency control device, characterized in that: The kiln temperature consistency control device comprises: Kiln environment information collection module, used to obtain the internal environment information of the kiln; A temperature change analysis module, used to input the internal environment information of the kiln into a temperature change prediction model, and use the temperature change prediction model to analyze the current operation status of the kiln to obtain temperature fluctuation trend information; A temperature control optimization parameter generation module is used to generate kiln temperature control optimization parameters according to the temperature fluctuation trend information and the target temperature control requirements; An operating parameter adjustment module is used to adjust the operating parameters inside the kiln in real time according to the kiln temperature control optimization parameters to obtain adjusted environmental information; A target value comparison module, used to compare the adjusted environmental information with the kiln temperature control target value, and if the adjusted environmental information meets the kiln temperature control target value, maintain the current operating parameters; The feedback iterative optimization module is used to re-input the adjusted environmental information into the temperature change prediction model if the adjusted environmental information does not meet the kiln temperature control target value, generate new kiln temperature control optimization parameters, and adjust the operating parameters inside the kiln again based on the new kiln temperature control optimization parameters until the adjusted environmental information meets the kiln temperature control target value.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the kiln temperature consistency control method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the kiln temperature consistency control method according to any one of claims 1 to 7 are implemented.

Images