Accurate control method and system for rapid temperature change test box

Abstract

The invention relates to the technical field of temperature control, in particular to an accurate control method and system for a rapid temperature change test box. The method comprises the following steps: acquiring an internal temperature parameter of a test box in a running state in real time based on a multi-sensor array; performing temperature error self-adaptive calibration on the internal temperature parameters of the test box, and constructing a three-dimensional temperature space distribution field; carrying out dynamic temperature transfer evolution on the three-dimensional temperature space distribution field and carrying out test box temperature change situation analysis so as to generate temperature change situation characteristics, and constructing a dynamic temperature change test box twinborn model; carrying out stage-by-stage temperature change rate calculation on a preset test box operation log so as to generate a temperature change state feature of each stage; and performing staged dynamic temperature change simulation on the dynamic temperature change test box twinborn model based on the temperature change state characteristics of each stage, thereby generating temperature change trend prediction data of each stage. According to the invention, rapid and accurate temperature change control of the test box is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature control, and in particular to a precise control method and system of a rapid temperature change test chamber. Background Art

[0002] With the continuous advancement of science and technology and the increasing diversification of industrial manufacturing needs, rapid temperature change test chambers are increasingly widely used in environmental testing, reliability testing, and product quality control. As an important device for simulating drastic changes in ambient temperature, rapid temperature change test chambers can provide extreme temperature change conditions and are used to verify the high temperature resistance, low temperature resistance, and temperature change resistance of electronic products, automotive parts, aerospace equipment, etc. However, with the continuous improvement of temperature testing requirements, traditional temperature change control methods are often difficult to meet high-precision testing requirements in terms of rapid response, precise control, and temperature uniformity.

[0003] During the rapid temperature change test, the temperature control accuracy of the test chamber is crucial to the accuracy of the test results. Traditional temperature control systems mostly use mechanical adjustment and a single PID control strategy, but these methods often have problems such as large temperature fluctuations, slow response speed, and poor temperature uniformity in a rapid temperature change environment. Especially when there is a large temperature change or a large temperature difference, the control accuracy is affected, and it is difficult to ensure the reliability and consistency of the test data. With the development of modern electronic technology and automatic control technology, researchers have proposed a variety of precise temperature control methods, including control technologies based on fuzzy logic control, intelligent algorithm control, and distributed temperature sensor networks. Although these methods have improved the accuracy and response speed of the temperature control system to a certain extent, they still face challenges such as poor temperature stability, complex system debugging, and high equipment costs.

[0004] Therefore, as the industry's requirements for the accuracy of rapid temperature change tests continue to increase, there is an urgent need for a precise control method for rapid temperature change test chambers that can effectively improve temperature control accuracy and optimize control performance. Summary of the invention

[0005] In order to solve the above technical problems, the present invention proposes a precise control method and system for a rapid temperature change test chamber to solve at least one of the above technical problems.

[0006] To achieve the above object, the present invention provides a precise control method for a rapid temperature change test chamber, comprising the following steps: Step S1: collecting the internal temperature parameters of the test box in the running state in real time based on the multi-sensor array; performing temperature error adaptive calibration on the internal temperature parameters of the test box, and performing temperature spatial distribution analysis to construct a three-dimensional temperature spatial distribution field; Step S2: Dynamically perform temperature transfer evolution on the three-dimensional temperature spatial distribution field and analyze the temperature change trend of the test chamber, thereby generating temperature change trend characteristics and constructing a dynamic temperature change test chamber twin model; Step S3: obtaining a preset test chamber operation log; calculating the temperature change rate of each stage of the preset test chamber operation log, and mining the stage temperature change state, thereby generating the temperature change state characteristics of each stage; Step S4: Based on the temperature change state characteristics of each stage, the dynamic temperature change test chamber twin model is simulated in stages, and then the temperature change trend is predicted, so as to generate the temperature change trend prediction data of each stage; Step S5: performing temperature change deviation compensation calculation on the temperature change trend prediction data of each stage, and adjusting the temperature control deviation compensation parameters to construct a dynamic temperature control fine-tuning strategy; Step S6: Optimize the response delay of the dynamic temperature control fine-tuning strategy, perform reinforcement transfer learning, and build a dynamic temperature control optimization engine to perform precise temperature control operations.

[0007] The present invention can ensure data accuracy by real-time collection of internal temperature parameters and adaptive calibration of temperature errors, providing a reliable basis for subsequent analysis and control. The construction of a three-dimensional temperature spatial distribution field is helpful for a comprehensive understanding of the temperature distribution inside the test chamber, providing detailed information for subsequent analysis. Through dynamic temperature transfer evolution and temperature change situation analysis, it is possible to have an in-depth understanding of the temperature change law, providing a basis for establishing a dynamic temperature change test chamber twin model. The construction of a dynamic temperature change test chamber twin model is helpful for real-time monitoring and prediction of temperature changes inside the test chamber, providing support for subsequent control. Calculating the temperature change rate and conducting stage temperature change state mining are helpful for understanding the temperature change characteristics of the test chamber at different stages, providing data support for model establishment and prediction. Generating temperature change state characteristics can help identify the temperature at different stages. Control requirements, provide a reference for subsequent simulation and adjustment, dynamic temperature change simulation and temperature change trend prediction based on stage temperature change state characteristics can achieve targeted temperature control and improve control accuracy, generate temperature change trend prediction data to help predict the temperature change of the test chamber in advance, and provide a basis for temperature control strategy adjustment, temperature change deviation compensation calculation and temperature control deviation parameter adjustment can make up for the error in temperature control and improve control accuracy and stability, build a dynamic temperature control fine-tuning strategy to help adjust temperature control parameters, improve the accuracy and response speed of temperature control, optimize the dynamic temperature control fine-tuning strategy and perform response delay optimization and transfer learning to improve the response speed and accuracy of the temperature control system, build a dynamic temperature control optimization engine to help achieve precise temperature control operations and improve the efficiency and stability of test chamber temperature control.

[0008] Preferably, step S1 comprises the following steps: Step S11: collecting the internal temperature parameters of the test chamber in the running state in real time based on the multi-sensor array; Step S12: Perform internal layout positioning on the multi-sensor array to obtain sensor node layout positioning data; Step S13: performing temperature sensing linear drift analysis on the temperature parameters inside the test box to generate temperature parameter linear drift data; Step S14: performing temperature error adaptive calibration based on temperature parameter linear drift data, thereby generating error calibration temperature parameters; Step S15: Perform temperature spatial distribution analysis on the error calibration temperature parameters according to the sensor node layout positioning data to construct a three-dimensional temperature spatial distribution field.

[0009] The present invention can provide timely temperature data by real-time acquisition of temperature parameters inside the test box, providing basic support for temperature control and analysis. By positioning the internal layout of the sensor nodes, the location information of the sensor can be accurately understood, which is helpful for the accurate collection and analysis of subsequent temperature data. Analyzing the linear drift of the temperature sensor can help identify the deviation generated by the sensor data and provide linear drift data for subsequent calibration. By calibrating the linear drift data of the temperature parameters, more accurate error calibration temperature parameters can be generated to improve the accuracy and reliability of the temperature data. Performing temperature spatial distribution analysis on the error calibration temperature parameters according to the sensor node layout positioning data can establish a three-dimensional temperature spatial distribution field, which helps to understand the distribution of temperature in the test box.

[0010] Preferably, step S15 specifically comprises the following steps: According to the sensor node layout positioning data, the temperature discrete distribution analysis of the error calibration temperature parameters is performed to obtain the temperature distribution data of the test chamber; Performing average temperature calculation on the error calibration temperature parameter to generate an average temperature value of the test chamber; Perform Fourier transform on the temperature distribution data of the test chamber to obtain the temperature distribution frequency domain data; Perform temperature difference frequency domain detection on the temperature distribution frequency domain data according to the average temperature value of the test chamber, and extract the temperature difference frequency domain data; Performing local temperature characteristic analysis based on the temperature difference frequency domain data to generate local temperature characteristic data; Based on the local temperature characteristic data, the three-dimensional spatial distribution fitting of the temperature distribution data of the test chamber is performed to construct a three-dimensional temperature spatial distribution field.

[0011] The present invention can understand the discrete distribution of temperature in the test box by analyzing the error calibration temperature parameters of the sensor node layout positioning data, which is helpful to identify the regularity and abnormality of temperature changes. The obtained test box temperature distribution data is helpful to optimize the temperature control strategy and improve the accuracy and stability of temperature control. By performing average temperature calculation on the error calibration temperature parameters, the average temperature value of the test box can be obtained to provide a benchmark reference for subsequent analysis. The generated average temperature value is helpful to monitor the overall temperature trend of the test box and provide important data support for temperature control and regulation. By performing Fourier transform processing on the test box temperature distribution data, the temperature distribution data can be converted to the frequency domain to help analyze the periodicity and frequency characteristics of temperature changes. The frequency domain data of temperature distribution can help identify the frequency components of temperature changes and provide more detailed information for further analysis. The difference detection of temperature distribution frequency domain data according to the average temperature value of the test chamber can find the frequency domain differences in temperature distribution, which helps to identify abnormal or uneven temperature distribution. Extracting temperature difference frequency domain data can help to accurately control temperature changes, improve temperature uniformity, and ensure the accuracy of test data. Analysis based on local temperature characteristic data can provide an in-depth understanding of the temperature change characteristics inside the test chamber and help find local temperature anomalies or hot spots. Constructing a three-dimensional temperature spatial distribution field can help visualize the temperature distribution, provide an intuitive reference for temperature regulation and optimization, and achieve precise control of temperature changes.

[0012] Preferably, the specific steps of step S2 are: Step S21: performing temperature fluctuation calculation on the three-dimensional temperature spatial distribution field to generate three-dimensional temperature distribution fluctuation data; Step S22: performing dynamic temperature transfer evolution on the three-dimensional temperature distribution fluctuation data, thereby generating a dynamic temperature transfer law; Step S23: analyzing the temperature change trend of the test chamber based on the dynamic temperature transfer law, thereby generating temperature change trend characteristics; Step S24: dynamically render the three-dimensional temperature spatial distribution field according to the temperature change trend characteristics, and construct a twin model of the dynamic temperature change test chamber.

[0013] The present invention calculates the temperature fluctuation of the three-dimensional temperature spatial distribution field, and can understand the dynamic change of temperature in space, including the temperature fluctuation range and frequency. The generation of three-dimensional temperature distribution fluctuation data is helpful to evaluate the stability and change trend of temperature, and provide basic data for subsequent analysis. By performing dynamic temperature transfer evolution on the temperature fluctuation data, the temperature transfer process in the test box can be simulated, and the dynamic evolution law of temperature in space can be revealed. The generation of dynamic temperature transfer law is helpful to understand the mechanism and influencing factors of temperature transfer, and provide a reference basis for controlling temperature transfer. The temperature change situation analysis based on the dynamic temperature transfer law can deeply understand the dynamic characteristics of temperature change inside the test box, including the temperature change trend and law. The generation of temperature change situation characteristics is helpful to predict the trend of temperature change, help optimize the temperature control strategy, and ensure the stability and accuracy of the temperature inside the test box. Dynamic temperature change rendering of the three-dimensional temperature spatial distribution field according to the temperature change situation characteristics can present the temperature change in a visual way, intuitively display the process and characteristics of temperature change, and construct a dynamic temperature change test box twin model to help simulate and predict the dynamic change of the temperature inside the test box, provide real-time reference for temperature control and regulation, and realize precise control of temperature change.

[0014] Preferably, step S3 specifically comprises the following steps: Step S31: obtaining a preset test chamber operation log; performing a predetermined temperature change analysis on the preset test chamber operation log, and extracting a predetermined temperature change curve; Step S32: dividing the predetermined temperature change curve into multiple stages of temperature change to obtain temperature change curves of multiple stages; Step S33: Calculating the temperature change rate of each stage of the temperature change curves of the multiple stages to generate the temperature change rate of each stage; Step S34: Analyze the temperature variation range of the temperature variation curves of multiple stages to generate the temperature variation range of each stage; Step S35: Calculating the start and end time points of the predetermined stages of the temperature change curves of the multiple stages, thereby obtaining the start and end timestamps of the stages; Step S36: Perform stage temperature change state mining on the temperature change rate of each stage, the temperature change range of each stage, and the start and end timestamps of each stage, so as to generate the temperature change state characteristics of each stage.

[0015] The present invention realizes effective utilization and analysis of the historical data of the test chamber by analyzing the preset test chamber operation log and extracting the predetermined temperature change curve. The extraction of the predetermined temperature change curve is helpful to understand the trend and characteristics of the temperature change of the test chamber, and provides a basis for subsequent analysis and control. The multi-stage temperature change segmentation of the predetermined temperature change curve can decompose the complex temperature change process into multiple stages, which is convenient for analysis and control. The multi-stage temperature change curve segmentation helps to refine the temperature change process and improve the ability to accurately control the temperature change. The temperature change rate calculation of each stage can quantify the temperature change speed of each stage, which helps to understand the speed of temperature change. Calculating the temperature change rate is helpful to analyze the dynamic characteristics of temperature change. It provides a reference for formulating control strategies. Analyzing the temperature change range of each stage can reveal the amplitude of temperature fluctuations and help evaluate the stability of temperature changes. Generating the temperature change range helps determine the appropriate temperature control range and ensure the accuracy of temperature control in the test chamber. Calculating the start and end timestamps of the stage can accurately determine the time range of each stage and provide a basis for time control. Obtaining the start and end timestamps can help divide the temperature change process into time periods and achieve precise time control. Generating the temperature change state characteristics of each stage through temperature change state mining can provide an in-depth understanding of the temperature change characteristics of each stage. Generating temperature change state characteristics can help establish models and laws of temperature changes and provide a basis for optimizing temperature control strategies.

[0016] Preferably, the specific steps of step S4 are: Step S41: making dynamic multi-stage temperature control decisions for the temperature change state characteristics of each stage and constructing a dynamic multi-stage temperature control strategy; Step S42: performing a stage-by-stage dynamic temperature change simulation on the twin model of the dynamic temperature change test chamber based on a dynamic multi-stage temperature control strategy to obtain dynamic temperature change simulation response data of multiple stages; Step S43: performing transient temperature fluctuation characteristic analysis on the dynamic temperature change response data of multiple simulation stages, and extracting the transient temperature fluctuation characteristics of each simulation stage; Step S44: predicting the temperature change trend of the transient temperature fluctuation characteristics of each simulation stage, thereby generating temperature change trend prediction data for each stage.

[0017] The present invention can adjust the temperature control strategy according to the real-time state by making dynamic multi-stage temperature control decisions on the temperature change state characteristics, thereby improving the control accuracy. Constructing a dynamic multi-stage temperature control strategy is helpful to formulate the best temperature control plan according to the experimental requirements and equipment characteristics. Based on the dynamic multi-stage temperature control strategy, the dynamic temperature change simulation of the twin model of the dynamic temperature change test chamber in stages can generate temperature response data for multiple stages. The simulation can predict the response of the test chamber under different temperature control strategies, which helps to optimize the temperature control plan. The transient temperature fluctuation feature analysis of the dynamic temperature change response data of multiple simulation stages can extract the transient temperature fluctuation feature of each stage. The analysis of the transient fluctuation feature helps to understand the regularity and fluctuation of temperature changes, and provides a basis for the optimization of the control strategy. The temperature change trend prediction of the transient temperature fluctuation feature of each simulation stage can predict the temperature change trend in advance. The predicted temperature change trend helps to adjust the temperature control strategy in time to ensure the accurate control and stability of the test chamber temperature.

[0018] Preferably, the specific steps of step S5 are: Step S51: performing predetermined temperature change characteristic deviation identification based on the temperature change trend prediction data of each stage, thereby marking the simulation stage of the temperature change deviation; Step S52: performing temperature change deviation calculation for the simulation stage of the temperature change deviation according to the temperature change state characteristics of each stage, thereby generating a temperature change deviation value; Step S53: performing temperature variation deviation compensation calculation on the temperature variation deviation value to generate a temperature variation compensation value in the deviation stage; Step S54: adjusting the temperature control deviation compensation parameters of the dynamic multi-stage temperature control strategy based on the temperature change compensation value in the deviation stage to construct a dynamic temperature control fine-tuning strategy.

[0019] The present invention can mark the simulation stage where the temperature deviation exists by identifying the temperature change characteristic deviation based on the temperature change trend prediction data. Identifying the temperature change deviation helps to promptly discover the stage where the temperature control of the test box is inaccurate, and provides an accurate data basis for subsequent adjustment and compensation. Calculating the temperature change deviation in the simulation stage of the temperature change deviation according to the temperature change state characteristics can generate an accurate temperature change deviation value. Calculating the temperature change deviation value helps to quantify the degree of deviation, and provides a specific numerical reference for subsequent compensation calculation and adjustment. Compensation calculation of the temperature change deviation value can generate a temperature change compensation value in the deviation stage, which is used to adjust the temperature control in the deviation stage. The temperature change deviation compensation calculation helps to adjust the deviation according to the actual situation, and improves the accuracy and stability of the overall temperature control. Adjusting the dynamic multi-stage temperature control strategy based on the temperature change compensation value in the deviation stage can construct a dynamic temperature control fine-tuning strategy. Adjusting the temperature control strategy parameters helps to compensate for the temperature deviation in real time, and improves the accuracy and stability of the temperature control of the test box.

[0020] Preferably, the specific steps of step S6 are: Step S61: performing a quantitative evaluation of the response delay of each stage on the dynamic temperature change simulation response data of multiple stages, so as to obtain the response delay value of each stage; Step S62: optimizing the dynamic temperature control fine-tuning strategy for response delay according to the response delay value of each stage to generate a dynamic temperature control response optimization strategy; Step S63: Performing enhanced transfer learning on the dynamic temperature control response optimization strategy to build a dynamic temperature control optimization engine; Step S64: Execute precise temperature control of the rapid temperature change test chamber based on the dynamic temperature control optimization engine.

[0021] The present invention can obtain the response delay value of each stage by quantitatively evaluating the response delay of the dynamic temperature change simulation response data stage by stage. Quantitatively evaluating the response delay is helpful to understand the response speed of each stage and provide basic data for subsequent optimization. Optimizing the response delay of the dynamic temperature control fine-tuning strategy according to the response delay value of each stage can generate a dynamic temperature control response optimization strategy. Optimizing the response delay is helpful to adjust the control strategy and improve the response speed and accuracy of the experimental box to temperature changes. Strengthening transfer learning of the dynamic temperature control response optimization strategy can construct a dynamic temperature control optimization engine. Strengthening transfer learning is helpful to accumulate experience, optimize strategies, and gradually improve the accuracy and stability of temperature control. Executing temperature change control operations of a rapid temperature change test box based on the dynamic temperature control optimization engine can achieve precise control. Using the optimization engine to perform temperature control operations is helpful to improve experimental efficiency, accuracy and stability, and ensure the reliability of experimental data.

[0022] In this specification, a precise control system of a rapid temperature change test chamber is provided, which is used to execute the precise control method of the rapid temperature change test chamber as described above, including: A three-dimensional temperature distribution module is used to collect the internal temperature parameters of the test box in the running state in real time based on a multi-sensor array; perform temperature error adaptive calibration on the internal temperature parameters of the test box, and perform temperature spatial distribution analysis to construct a three-dimensional temperature spatial distribution field; The twin model module is used to dynamically transfer and evolve the three-dimensional temperature spatial distribution field and analyze the temperature change trend of the test chamber, thereby generating temperature change trend characteristics and constructing a twin model of the dynamic temperature change test chamber; The stage temperature change state module is used to obtain the preset test chamber operation log; calculate the temperature change rate of each stage of the preset test chamber operation log, and perform stage temperature change state mining to generate the temperature change state characteristics of each stage; The temperature change simulation module is used to simulate the dynamic temperature change of the dynamic temperature change test chamber twin model in stages based on the temperature change state characteristics of each stage, and then predict the temperature change trend, so as to generate the temperature change trend prediction data of each stage; The temperature control deviation compensation module is used to calculate the temperature change deviation compensation for the temperature change trend prediction data at each stage, and adjust the temperature control deviation compensation parameters to build a dynamic temperature control fine-tuning strategy; The dynamic temperature control optimization module is used to optimize the response delay of the dynamic temperature control fine-tuning strategy, perform reinforcement transfer learning, and build a dynamic temperature control optimization engine to perform precise temperature control operations.

[0023] The present invention ensures the real-time and accuracy of experimental data by real-time collection of internal temperature parameters of the test chamber. Temperature error adaptive calibration and temperature spatial distribution analysis help to construct a three-dimensional temperature spatial distribution field and provide comprehensive temperature information. Dynamic temperature transfer evolution and temperature change situation analysis help to generate temperature change situation characteristics and provide a basis for subsequent control strategies. The construction of a dynamic temperature change test chamber twin model can simulate actual temperature changes and help optimize experimental design and temperature control. By calculating the temperature change rate of each stage and mining the temperature change state characteristics, the temperature change situation of each stage can be accurately described. The generated temperature change state characteristics provide an important basis for subsequent simulation and control. The staged dynamic temperature change simulation and temperature change trend prediction data generation help to predict temperature changes and guide experiments and control adjustments. Simulation based on the characteristics of each stage can more accurately control the temperature change of the test chamber. Temperature change deviation compensation calculation and parameter adjustment can correct the error between the actual temperature and the ideal temperature and improve control accuracy. The construction of a dynamic temperature control fine-tuning strategy helps to respond to temperature changes in real time and ensure the accuracy of experimental data. Response delay optimization and enhanced transfer learning are used to construct a dynamic temperature control optimization engine to improve control efficiency and stability. The dynamic temperature control optimization engine performs precise temperature control operations to ensure stable and accurate temperature during the experiment. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a schematic flow chart of the steps of a precise control method of a rapid temperature change test chamber of the present invention; Figure 2 Detailed implementation flow chart of step S1; Figure 3 Detailed implementation flow chart of step S2; Figure 4 Detailed implementation flow chart of step S3. DETAILED DESCRIPTION

[0025] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0026] The present application example provides a precise control method and system for a rapid temperature change test chamber. The execution subject of the precise control method and system for the rapid temperature change test chamber includes but is not limited to: mechanical equipment, data processing platform, cloud server node, network upload device, etc. equipped with the system can be regarded as the general computing node of the present application, and the data processing platform includes but is not limited to: at least one of an audio and image management system, an information management system, and a cloud data management system.

[0027] See also Figures 1 to 4 The present invention provides a precise control method for a rapid temperature change test chamber, and the precise control method for a rapid temperature change test chamber comprises the following steps: Step S1: collecting the internal temperature parameters of the test box in the running state in real time based on the multi-sensor array; performing temperature error adaptive calibration on the internal temperature parameters of the test box, and performing temperature spatial distribution analysis to construct a three-dimensional temperature spatial distribution field; Step S2: Dynamically perform temperature transfer evolution on the three-dimensional temperature spatial distribution field and analyze the temperature change trend of the test chamber, thereby generating temperature change trend characteristics and constructing a dynamic temperature change test chamber twin model; Step S3: obtaining a preset test chamber operation log; calculating the temperature change rate of each stage of the preset test chamber operation log, and mining the stage temperature change state, thereby generating the temperature change state characteristics of each stage; Step S4: Based on the temperature change state characteristics of each stage, the dynamic temperature change test chamber twin model is simulated in stages, and then the temperature change trend is predicted, so as to generate the temperature change trend prediction data of each stage; Step S5: performing temperature change deviation compensation calculation on the temperature change trend prediction data of each stage, and adjusting the temperature control deviation compensation parameters to construct a dynamic temperature control fine-tuning strategy; Step S6: Optimize the response delay of the dynamic temperature control fine-tuning strategy, perform reinforcement transfer learning, and build a dynamic temperature control optimization engine to perform precise temperature control operations.

[0028] The present invention can ensure data accuracy by real-time collection of internal temperature parameters and adaptive calibration of temperature errors, providing a reliable basis for subsequent analysis and control. The construction of a three-dimensional temperature spatial distribution field is helpful for a comprehensive understanding of the temperature distribution inside the test chamber, providing detailed information for subsequent analysis. Through dynamic temperature transfer evolution and temperature change situation analysis, it is possible to have an in-depth understanding of the temperature change law, providing a basis for establishing a dynamic temperature change test chamber twin model. The construction of a dynamic temperature change test chamber twin model is helpful for real-time monitoring and prediction of temperature changes inside the test chamber, providing support for subsequent control. Calculating the temperature change rate and conducting stage temperature change state mining are helpful for understanding the temperature change characteristics of the test chamber at different stages, providing data support for model establishment and prediction. Generating temperature change state characteristics can help identify the temperature at different stages. Control requirements, provide a reference for subsequent simulation and adjustment, dynamic temperature change simulation and temperature change trend prediction based on stage temperature change state characteristics can achieve targeted temperature control and improve control accuracy, generate temperature change trend prediction data to help predict the temperature change of the test chamber in advance, and provide a basis for temperature control strategy adjustment, temperature change deviation compensation calculation and temperature control deviation parameter adjustment can make up for the error in temperature control and improve control accuracy and stability, build a dynamic temperature control fine-tuning strategy to help adjust temperature control parameters, improve the accuracy and response speed of temperature control, optimize the dynamic temperature control fine-tuning strategy and perform response delay optimization and transfer learning to improve the response speed and accuracy of the temperature control system, build a dynamic temperature control optimization engine to help achieve precise temperature control operations and improve the efficiency and stability of test chamber temperature control.

[0029] In the embodiment of the present invention, refer to Figure 1 , is a schematic flow chart of the steps of a precise control method of a rapid temperature change test chamber of the present invention. In this example, the steps of the method include: Step S1: collecting the internal temperature parameters of the test box in the running state in real time based on the multi-sensor array; performing temperature error adaptive calibration on the internal temperature parameters of the test box, and performing temperature spatial distribution analysis to construct a three-dimensional temperature spatial distribution field; In this embodiment, a suitable temperature sensor (such as a thermocouple, RTD, digital temperature sensor, etc.) is selected to ensure that its accuracy and response time meet the experimental requirements. The sensors are reasonably arranged inside the test box. Usually, multiple sensors are arranged at different heights and positions to ensure comprehensive coverage of the temperature distribution. A data acquisition system (such as Arduino, Raspberry Pi) is used. Pi or dedicated temperature control system), connect the sensor to the data acquisition unit, configure the data acquisition software, set the sampling frequency (e.g., once per second) and the data storage format (e.g., CSV, database, etc.), start the data acquisition system, monitor and record the temperature parameters inside the test chamber in real time, and use the following methods: write Python or MATLAB scripts, read and store sensor data at regular intervals, implement a graphical user interface (GUI) on the data acquisition system, display temperature data in real time, collect temperature data within a certain period of time, and establish a relationship model between temperature and actual reference temperature. Methods such as linear regression or polynomial regression can be used to identify systematic errors in temperature measurement, such as offset and gain errors, and use adaptive calibration algorithms (e.g., Kalman filtering, least squares method, etc.) to calibrate temperature data. The specific steps include: adjusting the sensor output according to the calibration model, updating the calibration parameters in real time, comparing the calibrated temperature data with the standard temperature, and verifying the calibration effect. The standard deviation or root mean square error (RMSE) can be used to evaluate the accuracy of the calibration, and the calibrated temperature data is organized into a three-dimensional matrix. The data dimensions usually include the sensor position (x, y, z) and the corresponding temperature value, select an appropriate 3D interpolation method (such as 3D linear interpolation, Kriging interpolation, or spline interpolation) to fill the temperature data gaps between sensors, and use software tools (such as MATLAB, Python's Matplotlib, or Mayavi) to visualize the 3D temperature spatial distribution field. The specific steps include: using visualization tools to draw temperature isosurfaces or heat maps to display the spatial distribution of temperature, analyzing the characteristics of the 3D temperature distribution field, identifying temperature hotspots and cold spots, and storing the 3D temperature data and distribution field model in a database for subsequent analysis and application.

[0030] Step S2: Dynamically perform temperature transfer evolution on the three-dimensional temperature spatial distribution field and analyze the temperature change trend of the test chamber, thereby generating temperature change trend characteristics and constructing a dynamic temperature change test chamber twin model; In this embodiment, a suitable heat conduction model is selected, usually using finite element analysis (FEA) or a heat conduction equation. Software tools such as COMSOL Multiphysics, ANSYS or MATLAB can be used for simulation. The extracted three-dimensional temperature spatial distribution data is used as the initial condition to ensure that the data format meets the simulation requirements (for example, meshing and boundary condition setting). The heat conduction model is set in the selected software, including: determining material properties (such as thermal conductivity, specific heat capacity, etc.), setting the initial temperature field (from the three-dimensional temperature spatial distribution field), setting boundary conditions and external environmental conditions (such as ambient temperature, heat flow, etc.), running the simulation, observing the evolution of temperature over time, recording the temperature distribution data of each time step, generating result data of dynamic temperature transfer evolution, including the temperature distribution field of each time step, visualizing the temperature evolution process, using the visualization tool provided by the software to generate a heat map, contour map or three-dimensional animation, extracting the temperature data of each stage from the results of the dynamic temperature transfer evolution, organizing them into time series data, selecting a suitable analysis method, such as time series analysis, state transition analysis or trend analysis, and analyzing The pattern, trend and periodicity of temperature change, for example, calculate the temperature change rate, maximum value, minimum value and its range at each time step. Data analysis tools (such as Python's Pandas library) can be used for statistical analysis to identify the key characteristics of temperature change and design a twin model of the dynamic temperature change test chamber to ensure that the model can reflect the temperature change of the test chamber in real time. Select appropriate modeling tools, such as Simulink, MATLAB or other system modeling software, and build a twin model based on the extracted temperature change trend characteristics and temperature evolution data. The implementation steps include: defining the model's input (such as control variables, environmental conditions) and output (such as temperature response), integrating the dynamic temperature transfer model and the temperature change trend analysis results to form a complete twin model of the test chamber, and using actual test data to verify the twin model to ensure that the model can accurately reflect the dynamic temperature characteristics of the test chamber. Optimize the model parameters according to the verification results to improve the accuracy and reliability of the model.

[0031] Step S3: obtaining a preset test chamber operation log; calculating the temperature change rate of each stage of the preset test chamber operation log, and mining the stage temperature change state, thereby generating the temperature change state characteristics of each stage; In this embodiment, the log recording system of the test box is determined, and the operation log file is obtained. The log usually includes information such as timestamp, temperature reading, set temperature, humidity, etc., and the log file format (such as CSV, TXT) is ensured to be suitable for subsequent processing. A data processing tool (such as Python's Pandas library) is used to read the log file, and relevant data is extracted into a data frame, the data is cleaned, missing values ​​and outliers are processed, and the integrity and accuracy of the data are ensured. Interpolation or deletion methods can be used to process missing data. According to the preset temperature change setting, multiple stages are divided. A threshold method or a change point detection algorithm (such as a CUSUM algorithm) can be used to determine the start and end time of the stage. The temperature data in each stage is analyzed one by one, the temperature change rate is calculated, and the definition of the stage temperature change state characteristics is clarified, including the temperature change rate, the temperature change range, the stage duration, etc., and the temperature change rate and other characteristics of each stage are combined to perform stage temperature change state mining. Cluster analysis (such as K-Means clustering) or classification algorithms (such as decision trees) can be used to identify different temperature change states, generate temperature change state characteristics for each stage, including stage name, temperature change rate, state classification, etc., and store the results in a database or export them as a CSV file.

[0032] Step S4: Based on the temperature change state characteristics of each stage, the dynamic temperature change test chamber twin model is simulated in stages, and then the temperature change trend is predicted, so as to generate the temperature change trend prediction data of each stage; In this embodiment, it is ensured that the twin model of the dynamic temperature change test chamber has been established and verified. The model can be constructed using the finite element method (FEM) or computational fluid dynamics (CFD) tools such as COMSOL Multiphysics or ANSYS. The temperature change state characteristics extracted from the simulation are used as input data to ensure that the temperature change rate, duration and initial temperature of each stage are complete. The simulation conditions of each stage are set in the simulation software, including: initial temperature distribution (obtained from the simulation results of the previous stage), set temperature change rate and target temperature, boundary conditions and environmental influences (such as external temperature, heat flow, etc.). Run the simulation, monitor the temperature changes in each stage, record the temperature distribution data and response characteristics of each time step, ensure that the simulation time step and total simulation time match the actual operating conditions, extract the temperature data of each stage from the dynamic temperature change simulation, and organize it into a format suitable for analysis, such as time series data. Select a suitable prediction model, such as time series analysis (ARIMA), machine learning model (such as support vector machine, LSTM, etc.), divide the organized temperature data into training set and test set for model training and verification, for example: use historical data to train the ARIMA model, select appropriate parameters (p, d, q), for machine learning models (such as LSTM), convert the data into a suitable input format (such as sliding window method), use the trained model to predict the temperature changes in each stage, generate temperature change trend data at future time points, input the initial conditions and characteristic data of the corresponding stage, perform short-term temperature prediction, record the prediction results of each stage, including the predicted temperature value and the corresponding timestamp, organize the temperature change trend prediction data of each stage into a table, including stage name, predicted temperature, timestamp and other information, use Matplotlib, Seaborn or other visualization tools to visualize the prediction results, for example, draw a temperature change trend graph to help intuitively understand the prediction results, store the temperature change trend prediction data in the database or export it as a CSV file for subsequent use and analysis.

[0033] Step S5: performing temperature change deviation compensation calculation on the temperature change trend prediction data of each stage, and adjusting the temperature control deviation compensation parameters to construct a dynamic temperature control fine-tuning strategy; In this embodiment, the temperature change trend prediction data of each stage is extracted from step S4, including the predicted temperature value and the set target temperature, the temperature deviation of each stage is calculated, and the calculation method of temperature change deviation compensation is determined. Linear compensation, proportional compensation or PID control strategy can be used to select a compensation algorithm suitable for the temperature control system. According to the calculated deviation value, the temperature change compensation calculation is implemented. According to the result of the compensation calculation, a suitable adjustment strategy is selected. For example, the target temperature can be directly adjusted or the control algorithm parameters (such as the gain of the PID controller) can be corrected. For each stage, the temperature control parameters are adjusted based on the compensation value: if there is a negative deviation, the target temperature is increased; if there is a positive deviation, the target temperature is reduced, and the set point of the controller is updated. , apply the compensation value to the temperature control system, ensure real-time monitoring and adjustment, record the specific parameters of each adjustment and the corresponding feedback, and conduct a series of tests after the adjustment to verify whether the adjusted temperature control system can effectively eliminate the deviation. The effect can be verified through simulation or actual experiments, record the test results, analyze whether the adjustment effect meets expectations, and whether further optimization is needed. All compensation calculations and parameter adjustment records are organized into documents to form a standard operating procedure (SOP) for the dynamic temperature control fine-tuning strategy. Implement the dynamic temperature control fine-tuning strategy to ensure that parameters can be adjusted in real time during operation, establish a feedback mechanism, continuously monitor temperature changes and system responses, and make dynamic adjustments for different operating states.

[0034] Step S6: Optimize the response delay of the dynamic temperature control fine-tuning strategy, perform reinforcement transfer learning, and build a dynamic temperature control optimization engine to perform precise temperature control operations.

[0035] In this embodiment, by analyzing historical temperature control data and evaluating the response delay of the current dynamic temperature control fine-tuning strategy, cross-correlation analysis or time delay estimation algorithm can be used to identify the response characteristics of the system, select a suitable optimization method, such as feedback control theory (PID control) or adaptive control method, and determine the optimization direction according to the evaluation results. For example, if the delay is found to be large, it can be considered to increase the control gain, shorten the control cycle or adjust the control algorithm. According to the evaluation results and the optimization method, the control parameters in the dynamic temperature control fine-tuning strategy, such as the proportional (Kp), integral (Ki) and differential (Kd) values ​​of the PID controller, are adjusted. A simulation test is performed to verify whether the response speed of the optimized strategy in actual operation is improved, and the performance of the optimized strategy in actual operation is monitored to ensure that the system can respond to temperature changes faster. The strategy is further adjusted according to the test results, and each step and result of the optimization process is recorded. The historical data related to the dynamic temperature control fine-tuning strategy, including temperature changes, control inputs, system responses, etc., are collected and organized to provide training samples for reinforcement learning, and a suitable reinforcement learning algorithm, such as a deep Q network (DQN) or a policy gradient method, is selected to construct a Build a learning model that adapts to dynamic temperature control, use the existing temperature control model for transfer learning, initialize the parameters of the new model so that it can quickly adapt to new environments and tasks. During the training process, use the current temperature control strategy as the baseline, and continuously update the model weights through interaction with the environment to improve the temperature control performance. Train the model, use a simulated environment to test the temperature control effect of the model, and verify its adaptability under different temperature change conditions. Design the architecture of the dynamic temperature control optimization engine to ensure that it can integrate temperature control strategies, real-time data acquisition, response optimization and learning modules. The engine should include a data input module, a control decision module, an optimization module and a feedback module. Use programming languages ​​(such as Python and C++) to develop a dynamic temperature control optimization engine to ensure effective communication and data sharing between modules. Integrate a reinforcement learning model so that it can adjust the temperature control strategy in real time. Perform system testing in an actual environment, monitor the performance of the engine when performing precise temperature control operations, optimize according to the test results, ensure that the engine can perform temperature control tasks stably and efficiently, and document the design, implementation process and test results of the dynamic temperature control optimization engine to form an operation manual and maintenance guide.

[0036] In this embodiment, refer to Figure 2 , is a flowchart of detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include: Step S11: collecting the internal temperature parameters of the test chamber in the running state in real time based on the multi-sensor array; Step S12: Perform internal layout positioning on the multi-sensor array to obtain sensor node layout positioning data; Step S13: performing temperature sensing linear drift analysis on the temperature parameters inside the test box to generate temperature parameter linear drift data; Step S14: performing temperature error adaptive calibration based on temperature parameter linear drift data, thereby generating error calibration temperature parameters; Step S15: Perform temperature spatial distribution analysis on the error calibration temperature parameters according to the sensor node layout positioning data to construct a three-dimensional temperature spatial distribution field.

[0037] In this embodiment, a suitable temperature sensor (such as a thermocouple, PT100, DS18B20, etc.) is selected to ensure that its measurement range and accuracy meet the experimental requirements. According to the size of the test box and the required temperature monitoring accuracy, the number and placement of the sensors are determined, a data acquisition system is built, a microcontroller (such as Arduino, Raspberry Pi) or a data acquisition card is used to connect the sensors, and a data acquisition software (such as LabVIEW, MATLAB) is configured to acquire and record temperature data in real time. The data acquisition system is started to monitor the temperature parameters inside the test box in real time, and the data is recorded in a database or file. The data acquisition frequency is ensured to be appropriate to capture temperature changes, usually once per second. The reasonable layout of the sensors is determined to ensure that the key areas of the test box are covered and blind spots are avoided. A layout diagram is designed and the installation position of each sensor is marked. According to the layout design, the temperature sensors are physically installed in the test box to ensure that they are fixed and in good contact with the environment. The installation position and number of each sensor are recorded for subsequent data analysis. The node layout positioning data of the sensor is recorded, including the three-dimensional coordinates (X, Y, Z), use a coordinate system (such as Cartesian coordinate system) to ensure data consistency and operability, extract temperature parameter data from the data acquisition system, organize it into an analyzable format (such as CSV, Excel), ensure that the data contains timestamps and corresponding temperature values, use statistical analysis tools (such as MATLAB, Python) to perform linear regression analysis, identify drift trends in temperature sensor data, calculate the linear drift coefficient of each sensor, analyze its stability over time, generate temperature parameter linear drift data for each sensor based on the linear regression results, record the magnitude and direction of the drift, organize the analysis results, and form a report for subsequent calibration use, and establish a temperature error prediction model based on the linear drift analysis results. A temperature error model is used to describe the temperature drift characteristics of the sensor. For example, a linear equation is used to represent the relationship between temperature error and time. An adaptive calibration algorithm is designed to dynamically adjust the calibration coefficient according to the real-time collected data. Methods such as Kalman filtering or adaptive filtering are used to ensure the accuracy and real-time performance of the calibration. The calibration algorithm is applied to the temperature error model to the real-time temperature data to generate error calibration temperature parameters. The calibrated temperature data is recorded to ensure that it meets the expected accuracy standards. The error-calibrated temperature parameters are combined with the sensor node layout and positioning data to prepare for spatial distribution analysis to ensure that the calibration temperature value of each sensor corresponds to its position. A three-dimensional temperature distribution model is constructed using three-dimensional visualization tools (such as MATLAB, Python's Matplotlib, ParaView), and the calibration temperature parameters are mapped into three-dimensional space to form a temperature distribution field. The three-dimensional temperature spatial distribution field is visualized to identify the uniformity of the temperature distribution and the hot spots. Further analysis is performed to evaluate the temperature characteristics of the environment in the test chamber to ensure that it meets the experimental requirements.

[0038] In this embodiment, the specific steps of step S15 are: According to the sensor node layout positioning data, the temperature discrete distribution analysis of the error calibration temperature parameters is performed to obtain the temperature distribution data of the test chamber; Performing average temperature calculation on the error calibration temperature parameter to generate an average temperature value of the test chamber; Perform Fourier transform on the temperature distribution data of the test chamber to obtain the temperature distribution frequency domain data; Perform temperature difference frequency domain detection on the temperature distribution frequency domain data according to the average temperature value of the test chamber, and extract the temperature difference frequency domain data; Performing local temperature characteristic analysis based on the temperature difference frequency domain data to generate local temperature characteristic data; Based on the local temperature characteristic data, the three-dimensional spatial distribution fitting of the temperature distribution data of the test chamber is performed to construct a three-dimensional temperature spatial distribution field.

[0039] In this embodiment, information is extracted from the previously obtained error calibration temperature parameters and sensor node layout positioning data to ensure that the temperature data matches the corresponding sensor locations for spatial distribution analysis. Statistical analysis tools (such as Python's NumPy or SciPy) to calculate the degree of dispersion of temperature data, such as standard deviation and variance, generate temperature distribution graphs, use heat maps or scatter plots to visualize the discrete distribution of temperature inside the test chamber, calculate the average values ​​of all temperature parameters, generate the average temperature value of the test chamber, perform fast Fourier transform (FFT) on the temperature distribution data to convert it from the time domain to the frequency domain, analyze the frequency domain data, identify the effects of different frequency components on the temperature distribution, and visualize the relationship between frequency and amplitude, calculate the difference in the temperature distribution frequency domain data based on the average temperature value of the test chamber, identify the frequency components that deviate significantly from the average temperature, record the frequency components with significant differences, and generate a temperature difference frequency domain data set, which will be used for local temperature feature analysis, analyze the temperature characteristics of the local area based on the temperature difference frequency domain data, identify hot and cold spots, calculate local temperature feature data, including local maximum, minimum and change rate, organize local temperature feature data, record the temperature characteristics of each area and its dynamic changes, use local temperature feature data to fit the three-dimensional spatial distribution, use the interpolation method to generate a temperature distribution model, verify the accuracy of the fitting model, evaluate the reliability of the model by comparing with the actual measurement data, and make necessary adjustments based on the verification results.

[0040] In this embodiment, refer to Figure 3 , is a flowchart of detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include: Step S21: performing temperature fluctuation calculation on the three-dimensional temperature spatial distribution field to generate three-dimensional temperature distribution fluctuation data; Step S22: performing dynamic temperature transfer evolution on the three-dimensional temperature distribution fluctuation data, thereby generating a dynamic temperature transfer law; Step S23: analyzing the temperature change trend of the test chamber based on the dynamic temperature transfer law, thereby generating temperature change trend characteristics; Step S24: dynamically render the three-dimensional temperature spatial distribution field according to the temperature change trend characteristics, and construct a twin model of the dynamic temperature change test chamber.

[0041] In this embodiment, temperature data is extracted from the three-dimensional temperature spatial distribution field to ensure that the data is complete and in a uniform format. The fluctuation in the three-dimensional temperature distribution is calculated. The standard deviation or root mean square (RMS) is usually used to quantify the degree of temperature fluctuation, and three-dimensional temperature distribution fluctuation data is generated to characterize the temperature changes in different regions. The fluctuation data is presented as a three-dimensional graph using a visualization tool to facilitate the observation of the spatial distribution characteristics of temperature fluctuations. In step S21, three-dimensional temperature distribution fluctuation data has been obtained. These data are usually obtained by temperature sensors, thermal imaging equipment or numerical simulation, and can provide temperature changes at different time points and spatial positions. These data are denoised, filtered and normalized to ensure the accuracy and effectiveness of the temperature fluctuation data. The preprocessed data can remove the influence of sensor errors or external interference and provide real and effective temperature change information. The transfer of temperature is usually affected by factors such as heat conduction, convection, and radiation. In order to describe how temperature fluctuations are transmitted in the space within the test chamber, the heat conduction equation can be used to establish a mathematical model of three-dimensional temperature transfer. For temperature transfer in three-dimensional space, the following heat conduction equation can be used to describe: . Where T(x,y,z,t) is the temperature value at a certain time t and spatial position (x,y,z), is the thermal diffusion coefficient, which indicates the ability of heat to spread in an object. By solving the dynamic temperature transfer model, the temperature distribution data at different time steps can be obtained. These data not only reflect the evolution of temperature, but also reflect the temperature transfer law between different spatial positions. The periodicity, trend and sudden change law of temperature fluctuation can be extracted through data mining techniques (such as time series analysis and frequency domain analysis). Since the temperature transfer process in the test chamber involves multiple heat transfer mechanisms (such as convection, radiation, heat conduction, etc.), the coupling between these mechanisms needs to be considered. Through coupling analysis, the temperature transfer relationship between different components can be revealed, and the key factors affecting temperature changes can be extracted. Finally, the dynamic temperature transfer law can be presented through visualization tools to help researchers understand the temperature transfer trend at different time points and different spatial positions. For example, the temperature transfer speed in the test chamber, the temperature change amplitude at different positions, the temperature transfer direction between the heat source and the cold source, etc. The dynamic temperature transfer law data is stored in the database for subsequent analysis and use. A suitable analysis method is selected, such as time series analysis, trend analysis or state transition analysis. The dynamic temperature transfer law data is extracted from the database. The situation analysis is prepared to analyze the dynamic temperature transfer law and identify the pattern and trend of temperature change. The Pandas library in Python can be used for time series analysis to generate trend graphs and extract temperature change situation characteristics, such as temperature rise rate, drop rate and periodicity. The temperature change situation characteristic data is stored in the database for subsequent application and reference. A suitable dynamic rendering tool or engine is selected, such as Unity, Unreal Engine or Blender. The temperature change situation characteristics and three-dimensional temperature spatial distribution field data are extracted from the database to ensure data format compatibility. The temperature change situation characteristics are applied to the three-dimensional temperature spatial distribution field data to build a dynamic temperature change model. The rendering engine is used for dynamic display to simulate the temperature change process over time. Animation effects can be set to show the real-time temperature change. According to the dynamic temperature change rendering results, a dynamic temperature change twin model of the test chamber is constructed to ensure that the model is consistent with the temperature change of the actual test chamber. The model is stored in the system for subsequent analysis and decision support.

[0042] In this embodiment, refer to Figure 4 , is a flowchart of detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include: Step S31: obtaining a preset test chamber operation log; performing a predetermined temperature change analysis on the preset test chamber operation log, and extracting a predetermined temperature change curve; Step S32: dividing the predetermined temperature change curve into multiple stages of temperature change to obtain temperature change curves of multiple stages; Step S33: Calculating the temperature change rate of each stage of the temperature change curves of the multiple stages to generate the temperature change rate of each stage; Step S34: Analyze the temperature variation range of the temperature variation curves of multiple stages to generate the temperature variation range of each stage; Step S35: Calculating the start and end time points of the predetermined stages of the temperature change curves of the multiple stages, thereby obtaining the start and end timestamps of the stages; Step S36: Perform stage temperature change state mining on the temperature change rate of each stage, the temperature change range of each stage, and the start and end timestamps of each stage, so as to generate the temperature change state characteristics of each stage.

[0043] In this embodiment, the log recording system of the test box is determined, and the preset operation logs are obtained. These logs usually include timestamps, temperature readings, humidity, operating status and other information. Data processing tools (such as Python scripts) are used to extract temperature-related data from the log files, and the data format is ensured to be suitable for analysis. The extracted data is stored in a structured format, such as a CSV file or a database. The extracted temperature data is analyzed to generate a temperature change curve, which can be visualized using Python's Matplotlib library to help identify a predetermined temperature change trend. A suitable segmentation method is selected, such as threshold-based segmentation, change point detection (such as CUSUM algorithm), etc. The selected segmentation method is applied to analyze the temperature change curve to identify different temperature change stages, record the start and end time of each stage, generate temperature change curves of multiple stages, and store the temperature change curve data of each stage in a database for subsequent analysis. A suitable rate calculation method is selected, usually using a differential method or regression analysis, and the temperature change curve of each stage is analyzed. Analyze one by one and calculate the temperature change rate. The temperature change rate = ΔT / Δt, where ΔT is the temperature change and Δt is the time change. Generate the temperature change rate data for each stage and organize it into a table or graph for subsequent analysis. Determine the temperature change range of each stage, including the minimum temperature and the maximum temperature. Analyze the temperature change curve of each stage and calculate the temperature change range: temperature change range = maximum temperature − minimum temperature. Generate the temperature change range data for each stage and organize it into a clear report or graph. Extract the start and end timestamps of each stage from the operation log and segmentation results, and organize the start and end timestamps of each stage into a table to ensure that the time information is accurate for subsequent analysis. Select a suitable mining method, such as cluster analysis, pattern recognition or feature engineering. Combine the temperature change rate, change range and start and end timestamps of each stage to analyze the temperature change state. You can use machine learning algorithms (such as K-Means clustering) to classify the stages, generate temperature change state features, and identify temperature change features and trends under different states.

[0044] In this embodiment, step S4 includes the following steps: Step S41: making dynamic multi-stage temperature control decisions for the temperature change state characteristics of each stage and constructing a dynamic multi-stage temperature control strategy; Step S42: performing a stage-by-stage dynamic temperature change simulation on the twin model of the dynamic temperature change test chamber based on a dynamic multi-stage temperature control strategy to obtain dynamic temperature change simulation response data of multiple stages; Step S43: performing transient temperature fluctuation characteristic analysis on the dynamic temperature change response data of multiple simulation stages, and extracting the transient temperature fluctuation characteristics of each simulation stage; Step S44: predicting the temperature change trend of the transient temperature fluctuation characteristics of each simulation stage, thereby generating temperature change trend prediction data for each stage.

[0045] In this embodiment, a suitable decision model is selected, such as a rule-based decision tree, fuzzy logic control or reinforcement learning algorithm, and the temperature change state characteristics of each stage are extracted from the database, including the temperature change rate, the change range, and the start and end time of the stage. According to the extracted temperature change state characteristics, a dynamic multi-stage temperature control strategy is formulated, and the target temperature, control method (such as heating, cooling) and adjustment time are set for each stage. The control strategy is generated using an algorithm to ensure that the temperature changes within the set range. An optimization algorithm (such as a genetic algorithm) can be applied to improve the control effect. A suitable simulation tool is selected, such as MATLAB, Simulink or other thermal analysis software, and the dynamic multi-stage temperature control strategy is extracted from the database to ensure that its format is suitable for simulation. The dynamic temperature control strategy is used to simulate the test chamber twin model in stages, and the initial conditions of each stage are set. The temperature is gradually adjusted according to the control strategy, and the dynamic temperature change response data of each stage is recorded, including the change of temperature over time. The obtained dynamic temperature change simulation response data of multiple stages are stored in the database for subsequent analysis. Select a suitable analysis method, such as Fourier transform, time series analysis or wavelet transform, extract dynamic temperature change response data of multiple stages from the database, prepare for transient fluctuation feature analysis, analyze the dynamic temperature change response data of each simulation stage, extract transient temperature fluctuation features, and use wavelet transform to extract transient features of signals to identify rapidly changing temperature fluctuations. Record transient temperature fluctuation feature data of each stage, select a suitable trend prediction model, such as linear regression, ARIMA model or machine learning model (such as LSTM), extract transient temperature fluctuation feature data of each stage from the database, prepare for temperature change trend prediction, use the selected prediction model to analyze transient fluctuation features of each simulation stage, and generate temperature change trend prediction data. The following steps can be used: divide transient fluctuation feature data into training set and test set, train model, adjust hyperparameters to optimize prediction effect, predict the test set, record results, and store the generated temperature change trend prediction data of each stage in the database for subsequent use and analysis.

[0046] In this embodiment, step S5 includes the following steps: Step S51: performing predetermined temperature change characteristic deviation identification based on the temperature change trend prediction data of each stage, thereby marking the simulation stage of the temperature change deviation; Step S52: performing temperature change deviation calculation for the simulation stage of the temperature change deviation according to the temperature change state characteristics of each stage, thereby generating a temperature change deviation value; Step S53: performing temperature variation deviation compensation calculation on the temperature variation deviation value to generate a temperature variation compensation value in the deviation stage; Step S54: adjusting the temperature control deviation compensation parameters of the dynamic multi-stage temperature control strategy based on the temperature change compensation value in the deviation stage to construct a dynamic temperature control fine-tuning strategy.

[0047] In this embodiment, the expected range or standard of the temperature change characteristic is determined, such as the set temperature target range and the allowable fluctuation limit, the temperature change trend prediction data of each stage is extracted from the database to ensure the integrity and accuracy of the data, the actual temperature change trend is compared with the predetermined standard, the simulation stage of the deviation is identified, the simulation stage of the temperature change deviation is marked, and the deviation value is recorded, and a suitable calculation method is selected, such as a calculation method based on absolute deviation or relative deviation. For each marked deviation simulation stage, the temperature change deviation value is calculated, and a suitable compensation method is determined, such as linear compensation, proportional compensation or a model-based compensation strategy to deal with the identified temperature change deviation. Compensation calculation is performed for the temperature change deviation value of each stage to generate a temperature change compensation value. According to the temperature change compensation value of the deviation stage, the control parameters in the dynamic multi-stage temperature control strategy that need to be adjusted are identified, and the parameters in the temperature control strategy, such as the temperature set point, the heating / cooling rate and the holding time, are adjusted to reflect the compensation value to ensure that the adjusted parameters can effectively correct the previous deviation and improve the temperature control accuracy. A dynamic temperature control fine-tuning strategy is constructed according to the new control parameters to enhance the temperature control capability of the system at different stages, and the fine-tuning strategy is recorded, and preparation is made for actual application verification.

[0048] In this embodiment, step S6 includes the following steps: Step S61: performing a quantitative evaluation of the response delay of each stage on the dynamic temperature change simulation response data of multiple stages, so as to obtain the response delay value of each stage; Step S62: optimizing the dynamic temperature control fine-tuning strategy for response delay according to the response delay value of each stage to generate a dynamic temperature control response optimization strategy; Step S63: Performing enhanced transfer learning on the dynamic temperature control response optimization strategy to build a dynamic temperature control optimization engine; Step S64: Execute precise temperature control of the rapid temperature change test chamber based on the dynamic temperature control optimization engine.

[0049] In this embodiment, the temperature response data and the corresponding control input data of each stage are extracted from the dynamic temperature change simulation response data of multiple stages, the temperature change and control input of each stage are analyzed, and the response delay is identified. The response delay can be quantified by calculating the time required for the temperature to reach the set target, and the response delay value of each stage is calculated using the following formula: response delay value = time required to reach the set temperature − expected time, the response delay value of each stage is analyzed, the stage with longer delay is identified, and the optimization target is determined, and the dynamic temperature control fine-tuning strategy is adjusted according to the response delay value to optimize the control parameters, such as increasing or decreasing the heating / cooling rate, adjusting the temperature set point and holding time, ensuring that the optimized strategy can effectively reduce the response delay, recording the optimized dynamic temperature control response strategy, forming a new strategy document, and preparing for verification, selecting a suitable machine learning framework (such as TensorFlow or PyTorch) to build a reinforcement learning model, designing for the optimization of the dynamic temperature control strategy, and inputting the dynamic temperature control response optimization strategy and its corresponding response delay data as training data into the learning model, and using a reinforcement learning algorithm (such as Q-learning) to perform the optimization. Or deep Q network) for training, optimize the dynamic temperature control strategy, so that it can adaptively adjust the control parameters at different stages, conduct multiple rounds of training to ensure that the model can effectively learn and adapt to different temperature control scenarios, integrate the trained model into a dynamic temperature control optimization engine, which can handle temperature changes and response delays in real time, automatically adjust the control strategy, and deploy the dynamic temperature control optimization engine to the control system of the rapid temperature change test chamber to ensure that it can receive environmental data and output control instructions in real time, perform precise temperature change control operations, monitor the temperature changes in the test chamber in real time, and adjust according to the instructions of the optimization engine, record the temperature response data, and ensure that it meets the predetermined change curve. During the control process, continuously collect data, evaluate the effect of the temperature control optimization engine, make necessary adjustments, and feedback the learning system to improve the model and strategy to ensure the accuracy and response speed of future control operations.

[0050] In this embodiment, a precise control system of a rapid temperature change test chamber is provided, which is used to execute the precise control method of the rapid temperature change test chamber as described above, including: A three-dimensional temperature distribution module is used to collect the internal temperature parameters of the test box in the running state in real time based on a multi-sensor array; perform temperature error adaptive calibration on the internal temperature parameters of the test box, and perform temperature spatial distribution analysis to construct a three-dimensional temperature spatial distribution field; The twin model module is used to dynamically transfer and evolve the three-dimensional temperature spatial distribution field and analyze the temperature change trend of the test chamber, thereby generating temperature change trend characteristics and constructing a twin model of the dynamic temperature change test chamber; The stage temperature change state module is used to obtain the preset test chamber operation log; calculate the temperature change rate of each stage of the preset test chamber operation log, and perform stage temperature change state mining to generate the temperature change state characteristics of each stage; The temperature change simulation module is used to simulate the dynamic temperature change of the dynamic temperature change test chamber twin model in stages based on the temperature change state characteristics of each stage, and then predict the temperature change trend, so as to generate the temperature change trend prediction data of each stage; The temperature control deviation compensation module is used to calculate the temperature change deviation compensation for the temperature change trend prediction data at each stage, and adjust the temperature control deviation compensation parameters to build a dynamic temperature control fine-tuning strategy; The dynamic temperature control optimization module is used to optimize the response delay of the dynamic temperature control fine-tuning strategy, perform reinforcement transfer learning, and build a dynamic temperature control optimization engine to perform precise temperature control operations.

[0051] The present invention ensures the real-time and accuracy of experimental data by real-time collection of internal temperature parameters of the test chamber. Temperature error adaptive calibration and temperature spatial distribution analysis help to construct a three-dimensional temperature spatial distribution field and provide comprehensive temperature information. Dynamic temperature transfer evolution and temperature change situation analysis help to generate temperature change situation characteristics and provide a basis for subsequent control strategies. The construction of a dynamic temperature change test chamber twin model can simulate actual temperature changes and help optimize experimental design and temperature control. By calculating the temperature change rate of each stage and mining the temperature change state characteristics, the temperature change situation of each stage can be accurately described. The generated temperature change state characteristics provide an important basis for subsequent simulation and control. The staged dynamic temperature change simulation and temperature change trend prediction data generation help to predict temperature changes and guide experiments and control adjustments. Simulation based on the characteristics of each stage can more accurately control the temperature change of the test chamber. Temperature change deviation compensation calculation and parameter adjustment can correct the error between the actual temperature and the ideal temperature and improve control accuracy. The construction of a dynamic temperature control fine-tuning strategy helps to respond to temperature changes in real time and ensure the accuracy of experimental data. Response delay optimization and enhanced transfer learning are used to construct a dynamic temperature control optimization engine to improve control efficiency and stability. The dynamic temperature control optimization engine performs precise temperature control operations to ensure stable and accurate temperature during the experiment.

[0052] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0053] The above is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A precise control method for a rapid temperature change test chamber, characterized in that: The following steps are involved: Step S1: collecting the internal temperature parameters of the test box in the running state in real time based on the multi-sensor array; performing temperature error adaptive calibration on the internal temperature parameters of the test box, and performing temperature spatial distribution analysis to construct a three-dimensional temperature spatial distribution field; Step S2: Dynamically perform temperature transfer evolution on the three-dimensional temperature spatial distribution field and analyze the temperature change trend of the test chamber, thereby generating temperature change trend characteristics and constructing a dynamic temperature change test chamber twin model; Step S3: obtaining a preset test chamber operation log; calculating the temperature change rate of each stage of the preset test chamber operation log, and mining the stage temperature change state, thereby generating the temperature change state characteristics of each stage; Step S4: Based on the temperature change state characteristics of each stage, the dynamic temperature change test chamber twin model is simulated in stages, and then the temperature change trend is predicted, so as to generate the temperature change trend prediction data of each stage; Step S5: performing temperature change deviation compensation calculation on the temperature change trend prediction data of each stage, and adjusting the temperature control deviation compensation parameters to construct a dynamic temperature control fine-tuning strategy; Step S6: Optimize the response delay of the dynamic temperature control fine-tuning strategy, perform reinforcement transfer learning, and build a dynamic temperature control optimization engine to perform precise temperature control operations.

2. The precise control method of the rapid temperature change test chamber according to claim 1 is characterized in that: The specific steps of step S1 are: Step S11: collecting the internal temperature parameters of the test chamber in the running state in real time based on the multi-sensor array; Step S12: Perform internal layout positioning on the multi-sensor array to obtain sensor node layout positioning data; Step S13: performing temperature sensor linear drift analysis on the temperature parameters inside the test box to generate temperature parameter linear drift data; Step S14: performing temperature error adaptive calibration based on temperature parameter linear drift data, thereby generating error calibration temperature parameters; Step S15: Perform temperature spatial distribution analysis on the error calibration temperature parameters according to the sensor node layout positioning data, and construct a three-dimensional temperature spatial distribution field.

3. The precise control method of the rapid temperature change test chamber according to claim 2 is characterized in that: The specific steps of step S15 are: According to the sensor node layout positioning data, the temperature discrete distribution analysis of the error calibration temperature parameters is performed to obtain the temperature distribution data of the test chamber; Performing average temperature calculation on the error calibration temperature parameter to generate an average temperature value of the test chamber; Perform Fourier transform on the temperature distribution data of the test chamber to obtain the temperature distribution frequency domain data; Perform temperature difference frequency domain detection on the temperature distribution frequency domain data according to the average temperature value of the test chamber, and extract the temperature difference frequency domain data; Performing local temperature characteristic analysis based on the temperature difference frequency domain data to generate local temperature characteristic data; Based on the local temperature characteristic data, the three-dimensional spatial distribution fitting of the temperature distribution data of the test chamber is performed to construct a three-dimensional temperature spatial distribution field.

4. The precise control method of the rapid temperature change test chamber according to claim 1 is characterized in that: The specific steps of step S2 are: Step S21: performing temperature fluctuation calculation on the three-dimensional temperature spatial distribution field to generate three-dimensional temperature distribution fluctuation data; Step S22: performing dynamic temperature transfer evolution on the three-dimensional temperature distribution fluctuation data, thereby generating a dynamic temperature transfer law; Step S23: analyzing the temperature change trend of the test chamber based on the dynamic temperature transfer law, thereby generating temperature change trend characteristics; Step S24: dynamically render the three-dimensional temperature spatial distribution field according to the temperature change trend characteristics, and construct a twin model of the dynamic temperature change test chamber.

5. The precise control method of the rapid temperature change test chamber according to claim 1 is characterized in that: The specific steps of step S3 are: Step S31: obtaining a preset test chamber operation log; performing a predetermined temperature change analysis on the preset test chamber operation log, and extracting a predetermined temperature change curve; Step S32: dividing the predetermined temperature change curve into multiple stages of temperature change to obtain temperature change curves of multiple stages; Step S33: Calculating the temperature change rate of each stage of the temperature change curves of the multiple stages to generate the temperature change rate of each stage; Step S34: Analyze the temperature variation range of the temperature variation curves of multiple stages to generate the temperature variation range of each stage; Step S35: Calculating the start and end time points of the predetermined stages of the temperature change curves of the multiple stages, thereby obtaining the start and end timestamps of the stages; Step S36: Perform stage temperature change state mining on the temperature change rate of each stage, the temperature change range of each stage, and the start and end timestamps of each stage, so as to generate the temperature change state characteristics of each stage.

6. The precise control method of the rapid temperature change test chamber according to claim 1 is characterized in that: The specific steps of step S4 are: Step S41: making dynamic multi-stage temperature control decisions for the temperature change state characteristics of each stage and constructing a dynamic multi-stage temperature control strategy; Step S42: performing a stage-by-stage dynamic temperature change simulation on the twin model of the dynamic temperature change test chamber based on a dynamic multi-stage temperature control strategy to obtain dynamic temperature change simulation response data of multiple stages; Step S43: performing transient temperature fluctuation characteristic analysis on the dynamic temperature change response data of multiple simulation stages, and extracting the transient temperature fluctuation characteristics of each simulation stage; Step S44: predicting the temperature change trend of the transient temperature fluctuation characteristics of each simulation stage, thereby generating temperature change trend prediction data for each stage.

7. The precise control method of the rapid temperature change test chamber according to claim 1 is characterized in that: The specific steps of step S5 are: Step S51: performing predetermined temperature change characteristic deviation identification based on the temperature change trend prediction data of each stage, thereby marking the simulation stage of the temperature change deviation; Step S52: performing temperature change deviation calculation for the simulation stage of the temperature change deviation according to the temperature change state characteristics of each stage, thereby generating a temperature change deviation value; Step S53: performing temperature variation deviation compensation calculation on the temperature variation deviation value to generate a temperature variation compensation value in the deviation stage; Step S54: adjusting the temperature control deviation compensation parameters of the dynamic multi-stage temperature control strategy based on the temperature change compensation value in the deviation stage to construct a dynamic temperature control fine-tuning strategy.

8. The precise control method of the rapid temperature change test chamber according to claim 1 is characterized in that: The specific steps of step S6 are: Step S61: performing a quantitative evaluation of the response delay of each stage on the dynamic temperature change simulation response data of multiple stages, so as to obtain the response delay value of each stage; Step S62: optimizing the dynamic temperature control fine-tuning strategy for response delay according to the response delay value of each stage to generate a dynamic temperature control response optimization strategy; Step S63: Performing enhanced transfer learning on the dynamic temperature control response optimization strategy to build a dynamic temperature control optimization engine; Step S64: Execute precise temperature control of the rapid temperature change test chamber based on the dynamic temperature control optimization engine.

9. A precise control system for a rapid temperature change test chamber, characterized in that: The precise control method for executing the rapid temperature change test chamber as claimed in claim 1 comprises: A three-dimensional temperature distribution module is used to collect the internal temperature parameters of the test box in the running state in real time based on a multi-sensor array; perform temperature error adaptive calibration on the internal temperature parameters of the test box, and perform temperature spatial distribution analysis to construct a three-dimensional temperature spatial distribution field; The twin model module is used to dynamically transfer and evolve the three-dimensional temperature spatial distribution field and analyze the temperature change trend of the test chamber, thereby generating temperature change trend characteristics and constructing a twin model of the dynamic temperature change test chamber; The stage temperature change state module is used to obtain the preset test chamber operation log; calculate the temperature change rate of each stage of the preset test chamber operation log, and perform stage temperature change state mining to generate the temperature change state characteristics of each stage; The temperature change simulation module is used to simulate the dynamic temperature change of the dynamic temperature change test chamber twin model in stages based on the temperature change state characteristics of each stage, and then predict the temperature change trend, so as to generate the temperature change trend prediction data of each stage; The temperature control deviation compensation module is used to calculate the temperature change deviation compensation for the temperature change trend prediction data at each stage, and adjust the temperature control deviation compensation parameters to build a dynamic temperature control fine-tuning strategy; The dynamic temperature control optimization module is used to optimize the response delay of the dynamic temperature control fine-tuning strategy, perform reinforcement transfer learning, and build a dynamic temperature control optimization engine to perform precise temperature control operations.

Images