Method and device for compensating humidity gradient of alternating humidity-heat test chamber

Abstract

The invention relates to the technical field of humidity compensation, in particular to a humidity gradient compensation method and device for an alternating humidity heat test box. The method comprises the following steps: acquiring test box state monitoring parameters based on a multi-dimensional sensor array; performing spatial humidity gradient distribution analysis on the state monitoring parameters of the test box, performing discrete interpolation fitting, and constructing a three-dimensional humidity gradient trend network; carrying out internal dynamic airflow diffusion analysis on the alternating damp heat test box so as to generate dynamic airflow diffusion data of the test box; carrying out dynamic humidity diffusion path mining on the three-dimensional humidity gradient trend network based on the dynamic airflow diffusion data of the test box, and constructing a dynamic humidity diffusion twin model; acquiring external environment monitoring parameters of the test box; and carrying out environment change association mining on the three-dimensional humidity gradient trend network based on the test box external environment monitoring parameters so as to generate humidity gradient change association data under environment fluctuation. According to the invention, efficient and accurate humidity gradient compensation is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of humidity compensation, and in particular to a humidity gradient compensation method and device for an alternating humidity and heat test chamber. Background Art

[0002] As a widely used equipment for environmental testing and reliability evaluation, the alternating humidity test chamber is usually used to simulate the working state of equipment under different environmental conditions, especially to evaluate the durability of materials, electronic components, mechanical equipment, etc. under high temperature and high humidity conditions. In the alternating humidity test, humidity is a key environmental factor, and the fluctuation of humidity directly affects the accuracy and reliability of the test results. However, in practical applications, the distribution of humidity inside the alternating humidity test chamber often has a gradient effect, that is, there is a difference in humidity at different locations in the test chamber. This humidity gradient problem is mainly caused by factors such as the local non-uniformity of the temperature and humidity control system, the location of the test sample, and the airflow in the chamber.

[0003] The existence of humidity gradient not only leads to errors in test results, but also affects the actual performance of the test samples, which in turn has an adverse effect on product quality assessment. For example, some test pieces are exposed to an environment with too high or too low humidity, which causes them to be damp or dry unevenly, affecting their physical properties or electrical characteristics. Therefore, during the alternating humidity test, how to effectively compensate for the humidity gradient and ensure the uniformity and accuracy of the humidity in the test chamber has become a key issue in improving the performance of the test chamber and the test accuracy.

[0004] At present, traditional humidity gradient compensation methods mostly rely on increasing the stability of the humidity control system or reducing the unevenness of humidity distribution by adjusting the internal structure of the test chamber. However, these methods often have disadvantages such as limited adjustment effect, high cost, and complex implementation. Therefore, a more intelligent, accurate and efficient humidity gradient compensation method is urgently needed to meet the needs of modern alternating humidity test chambers in high-precision and high-efficiency environmental testing. Summary of the invention

[0005] In order to solve the above technical problems, the present invention proposes a humidity gradient compensation method and device for an alternating humidity and heat test chamber to solve at least one of the above technical problems.

[0006] To achieve the above object, the present invention provides a humidity gradient compensation method for an alternating damp heat test chamber, comprising the following steps: Step S1: Acquire the test chamber state monitoring parameters based on the multi-dimensional sensor array; perform spatial humidity gradient distribution analysis on the test chamber state monitoring parameters, and perform discrete interpolation fitting to construct a three-dimensional humidity gradient trend network; Step S2: performing internal dynamic airflow diffusion analysis on the alternating humidity and heat test chamber, thereby generating dynamic airflow diffusion data of the test chamber; Step S3: mining the dynamic humidity diffusion path of the three-dimensional humidity gradient trend network based on the dynamic airflow diffusion data of the test chamber, and constructing a dynamic humidity diffusion twin model; Step S4: Acquire external environment monitoring parameters of the test chamber; perform environmental change correlation mining on the three-dimensional humidity gradient trend network based on the external environment monitoring parameters of the test chamber, thereby generating humidity gradient change correlation data under environmental fluctuations; Step S5: According to the humidity gradient change correlation data under environmental fluctuations, the dynamic humidity diffusion twin model is subjected to humidity compensation flow simulation and humidity gradient compensation diffusion evolution, thereby generating a humidity gradient compensation diffusion law under environmental fluctuations; Step S6: Based on the diffusion law of humidity gradient compensation under environmental fluctuations, regional adaptive humidity gradient compensation is performed on multiple regional twin models to construct an intelligent humidity compensation strategy.

[0007] The present invention obtains the state monitoring parameters of the test box through a multi-dimensional sensor array, and can fully understand the humidity distribution characteristics inside the test box. The construction of a three-dimensional humidity gradient trend network is helpful to reveal the spatial characteristics of humidity distribution, and provides a basis for subsequent humidity compensation. The internal dynamic airflow diffusion analysis can reveal the dynamic characteristics of humidity changes inside the test box, and provide dynamic airflow diffusion data. These data are crucial for understanding the propagation path and speed of humidity inside the test box, and lay the foundation for the establishment of a humidity compensation model. Through the dynamic humidity diffusion path mining, a dynamic humidity diffusion twin model can be constructed to help simulate the humidity propagation process inside the test box. This model helps to understand the law of humidity diffusion and provides a basis for subsequent humidity compensation strategies. By analyzing the external environmental monitoring parameters, we can explore the relationship between the environment and the humidity gradient change, and generate humidity gradient change correlation data. These data help to understand the impact of the external environment on the humidity of the test chamber and provide more comprehensive information for the humidity compensation model. Through humidity compensation flow simulation and humidity gradient compensation diffusion evolution, we can generate the humidity gradient compensation diffusion law under environmental fluctuations, understand the change law of humidity under environmental fluctuations, and provide a basis for formulating humidity compensation strategies. Through the study of regional adaptive humidity gradient compensation, we can construct an intelligent humidity compensation strategy to improve the humidity compensation effect of the test chamber. The formulation of intelligent strategies can dynamically adjust the humidity according to real-time environmental changes, thereby improving the humidity control accuracy and efficiency of the test chamber.

[0008] Preferably, step S1 comprises the following steps: Step S11: Acquire test chamber status monitoring parameters based on a multi-dimensional sensor array; Step S12: Calculate the temperature change of the test chamber status monitoring parameters and identify the temperature change data of the test chamber; Step S13: performing spatial humidity gradient distribution analysis on the test chamber state monitoring parameters to obtain three-dimensional humidity gradient distribution characteristics; Step S14: mining humidity change trend of the three-dimensional humidity gradient distribution characteristics according to the test chamber temperature change data, thereby obtaining humidity gradient change trend data; Step S15: Perform discrete interpolation fitting on the humidity gradient change trend data to construct a three-dimensional humidity gradient trend network.

[0009] The present invention obtains the test box state monitoring parameters through a multi-dimensional sensor array, and can fully understand the parameters such as temperature and humidity inside the test box. These data are the basis for subsequent analysis and provide necessary information for humidity gradient compensation. Identifying the temperature change data of the test box is helpful to understand the dynamic change of the temperature inside the test box. The temperature change data provides an important reference for subsequent analysis and provides temperature support for the formulation of humidity gradient compensation strategies. Through spatial humidity gradient distribution analysis, the three-dimensional humidity gradient distribution characteristics inside the test box can be obtained. These characteristics help to understand the distribution of humidity inside the test box and provide a basis for subsequent humidity gradient change trend analysis. According to the temperature change data of the test box, the humidity gradient distribution characteristics are mined for humidity change trends, and humidity gradient change trend data can be obtained. These data help to understand the changing law of humidity at different temperatures and provide important information for the establishment of a humidity compensation model. Through discrete interpolation fitting, a three-dimensional humidity gradient trend network is constructed, which can more intuitively display the spatial distribution characteristics of the humidity gradient. This network helps to deeply understand the changing trend of the humidity gradient and provides visualization support for the formulation of humidity compensation strategies.

[0010] Preferably, the specific steps of step S13 are: Extract all sensor nodes based on multi-dimensional sensor array; Calculate the spatial position of all sensor nodes to obtain the spatial position coordinates of each node; Perform sensor node distribution analysis on the spatial position coordinates of each node to obtain sensor node distribution data; Based on the sensor node distribution data, the regional parameter segmentation and identification of the test chamber state monitoring parameters are performed to obtain multiple test chamber regional monitoring parameters; Calculate the humidity of each area of ​​the multiple test chambers for each monitoring parameter, and extract the humidity parameters of each test chamber area; Calculate the humidity difference between the regions for the humidity parameters of each test chamber area to generate the humidity difference value between the regions; Conduct humidity difference gradient analysis on humidity difference values ​​between regions to generate humidity difference gradient data; The humidity difference gradient data is subjected to three-dimensional humidity gradient distribution analysis to obtain the three-dimensional humidity gradient distribution characteristics.

[0011] The present invention ensures that each key position in the test box has monitoring coverage by extracting all sensor nodes, and establishes the accurate position of the sensor node in three-dimensional space by calculating the spatial position coordinates of each sensor node, which provides a spatial reference for subsequent regional parameter segmentation and humidity difference analysis. By analyzing the spatial position distribution of the sensor nodes, the density and distribution of the sensor nodes in the test box can be understood, and the uniformity of the monitoring coverage can be evaluated, which provides a basis for further parameter segmentation. By identifying the monitoring parameters of different regions, the monitoring and distinction of different regions inside the test box are realized, which provides basic information for humidity compensation strategies for different regions. The humidity parameters of each test box region are extracted, so that the humidity control and adjustment for each region become, which provides data support for more refined humidity compensation. Generating humidity difference values ​​between regions helps to understand the difference in humidity between different regions, which provides a basis for humidity gradient analysis and compensation, making humidity control more accurate. By analyzing the humidity difference gradient data, the gradient of humidity changes between regions can be understood, which provides more in-depth data support for the formulation of humidity compensation strategies, and obtaining three-dimensional humidity gradient distribution characteristics helps to fully understand the spatial distribution of humidity inside the test box, which provides an important reference basis for formulating more effective humidity compensation schemes.

[0012] Preferably, the specific steps of step S2 are: Step S21: performing internal geometric analysis on the alternating damp heat test chamber to obtain internal geometric data of the test chamber; Step S22: performing spatial topological structure recognition on the internal geometric data of the test box to extract spatial topological structure data; Step S23: performing three-dimensional topological point cloud modeling on the spatial topological structure data to construct a three-dimensional structure model of the test box; Step S24: performing internal air flow mining on the three-dimensional structure model of the test box based on the test box state monitoring parameters, thereby extracting the internal air flow characteristics of the test box; Step S25: Perform dynamic airflow diffusion analysis on the air flow characteristics inside the test box, thereby generating dynamic airflow diffusion data of the test box.

[0013] The present invention can obtain the geometric data of the inside of the test box, including the spatial layout and structure, through geometric morphology analysis. Obtaining the geometric data of the inside of the test box is helpful to understand the spatial characteristics of the inside of the test box, and provides basic data for subsequent analysis. Through spatial topological structure recognition, the spatial topological structure data of the inside of the test box can be extracted, including the connection and relationship between the various components. Extracting the spatial topological structure data is helpful to understand the organization of the internal structure of the test box, and provides a basis for modeling and analysis. Through three-dimensional topological point cloud modeling, a three-dimensional structural model of the test box can be constructed to show the spatial layout and morphology of the inside of the test box. Constructing the three-dimensional structural model is helpful to visualize the internal structure of the test box, and provides visualization support for subsequent analysis and optimization. Through air flow mining, the air flow characteristics inside the test box can be analyzed, and the flow conditions and paths of the air inside the test box can be understood. Extracting the air flow characteristics is helpful to optimize the air flow inside the test box and improve the uniformity and stability of the test environment. Through air flow diffusion analysis, the dynamic diffusion process of the air inside the test box can be simulated to generate dynamic air flow diffusion data. Generating air flow diffusion data is helpful to understand the propagation and change of humidity in the test box, and provides an important reference for humidity gradient compensation.

[0014] Preferably, step S3 specifically comprises the following steps: Step S31: performing humidity diffusion simulation on the three-dimensional humidity gradient distribution characteristics based on the dynamic airflow diffusion data of the test chamber to generate humidity diffusion simulation data of the test chamber; Step S32: Tracking the spatiotemporal changes of the test chamber humidity diffusion simulation data to generate a spatiotemporal change trajectory of humidity diffusion; Step S33: mining the dynamic humidity diffusion path of the spatiotemporal change trajectory of humidity diffusion, thereby obtaining dynamic humidity diffusion path data; Step S34: Based on the dynamic humidity diffusion path data, the three-dimensional humidity gradient trend network is dynamically rendered to construct a dynamic humidity diffusion twin model.

[0015] The present invention can generate humidity diffusion simulation data in a test box based on dynamic airflow diffusion data through humidity diffusion simulation, and simulate the distribution of humidity inside the test box. The generated humidity diffusion simulation data is helpful to understand the changing trend and distribution characteristics of humidity in the test box, and provides an important reference for humidity gradient compensation. Through time-space change tracking, the time-space change trajectory of humidity diffusion can be generated to track the changing process of humidity inside the test box. The generated time-space change trajectory is helpful to understand the dynamic change of humidity diffusion, and provides time series data support for subsequent analysis and optimization. Through humidity diffusion path mining, dynamic humidity diffusion path data can be extracted from the humidity diffusion trajectory to reveal the propagation path of humidity in the test box. Extracting humidity diffusion path data is helpful to understand the propagation mode of humidity inside the test box, and provides support for humidity control and regulation. Through humidity diffusion rendering, a three-dimensional humidity gradient trend network can be rendered based on dynamic humidity diffusion path data to construct a dynamic humidity diffusion twin model. Constructing the dynamic humidity diffusion twin model is helpful to visualize the propagation path and trend of humidity inside the test box, and provides visualization support for the formulation and optimization of humidity gradient compensation strategies.

[0016] Preferably, the specific steps of step S4 are: Step S41: Acquire external environment monitoring parameters of the test chamber; Step S42: performing environmental parameter change analysis on the external environmental monitoring parameters of the test chamber to generate environmental parameter change data; Step S43: Perform time series variation fitting on the environmental parameter variation data to construct an environmental parameter time series variation curve; Step S44: identifying parameter mutation points on the environmental parameter time series variation curve, and extracting multiple parameter mutation points; Step S45: Perform environmental change association mining on the three-dimensional humidity gradient trend network based on multiple parameter mutation points, thereby generating humidity gradient change association data under environmental fluctuations.

[0017] The present invention can obtain data related to the external environment of the test box, such as monitoring parameters such as temperature and humidity, by acquiring external environment monitoring parameters. Acquiring external environment monitoring parameters is helpful to understand the change of the environment around the test box, and provides basic data for subsequent analysis. By analyzing the change of environmental parameters, change data of environmental parameters, such as the time series change of temperature and humidity, can be generated. The generated environmental parameter change data is helpful to understand the change trend of the external environment, and provides data support for subsequent analysis and comparison. By fitting the time series change, a time series change curve of environmental parameters can be constructed to reveal the change law of environmental parameters over time. The construction of the time series change curve is helpful to understand the trend change of environmental parameters, and provides a basis for subsequent analysis and prediction. By identifying parameter mutation points, mutation points in the environmental parameter curve, that is, time points at which the environment changes rapidly, can be extracted. Extracting parameter mutation points is helpful to identify the key moments of environmental changes, and provides important clues for subsequent analysis and formulation of response strategies. Based on multiple parameter mutation points, environmental change association mining is performed on the three-dimensional humidity gradient trend network, and humidity gradient change association data under environmental fluctuations is generated. Environmental change association mining is helpful to understand the influence of external environmental changes on humidity gradient, and provides support for optimization and adjustment of humidity gradient compensation strategy.

[0018] Preferably, the specific steps of step S5 are: Step S51: dividing the dynamic humidity diffusion twin model into regions to obtain multiple regional twin models; Step S52: performing humidity compensation flow simulation on multiple regional twin models based on the humidity gradient change correlation data under environmental fluctuations, thereby generating humidity compensation flow simulation data between multiple regions; Step S53: performing humidity gradient compensation diffusion evolution on the humidity compensation flow simulation data between multiple regions, thereby generating a humidity gradient compensation diffusion law under environmental fluctuations; Step S54: performing humidity gradient compensation diffusion evolution on the degree compensation delayed response characteristics of each area, thereby generating a humidity gradient compensation diffusion law under environmental fluctuations.

[0019] The present invention divides the dynamic humidity diffusion twin model into multiple regional twin models through regional division, and performs individual processing on different regions. The regional division is helpful to more finely study the characteristics and changing laws of the humidity diffusion model in different regions. Based on the humidity gradient change correlation data under environmental fluctuations, humidity compensation flow simulation is performed on multiple regional twin models to generate humidity compensation flow simulation data between multiple regions. The humidity compensation flow simulation helps to simulate the relationship between humidity changes between different regions, and provides data support for further analysis of humidity gradient compensation. Humidity gradient compensation diffusion evolution is performed on the humidity compensation flow simulation data between multiple regions to generate the humidity gradient compensation diffusion law under environmental fluctuations. The humidity gradient compensation diffusion evolution helps to understand the propagation mode and law of humidity compensation between different regions, and provides support for the optimization of humidity gradient compensation strategy. Humidity gradient compensation diffusion evolution is performed on the humidity compensation delayed response characteristics of each region to generate the humidity gradient compensation diffusion law under environmental fluctuations. Analysis of the humidity compensation delayed response characteristics helps to understand the humidity adjustment speed and effect of different regions, and provides a reference basis for real-time adjustment of humidity gradient compensation.

[0020] Preferably, the specific steps of step S6 are: Step S61: Calculate the current humidity distribution of multiple regional twin models and extract the humidity distribution value of each regional model; Step S62: Calculating the humidity deviation of the humidity distribution value of each regional model based on the preset test chamber humidity value, thereby generating a humidity deviation value for each region; Step S63: performing humidity compensation calculation on the humidity deviation value of each area to obtain a humidity compensation value of each area; Step S64: performing regional adaptive humidity gradient compensation on the test box based on the humidity gradient compensation diffusion law under environmental fluctuations and the humidity compensation value of each area, thereby generating adaptive humidity gradient compensation data; Step S65: performing multi-region collaborative optimization calculation on the adaptive humidity gradient compensation data to obtain adaptive humidity compensation optimization parameters; Step S66: Perform iterative compensation learning on the adaptive humidity compensation optimization parameters to construct an intelligent humidity compensation strategy.

[0021] The present invention can obtain the humidity distribution value of each regional model by calculating the current humidity distribution of multiple regions, and understand the humidity distribution of each region. Extracting the humidity distribution value helps to determine the actual situation of humidity in each region, and provides basic data for subsequent humidity compensation calculation. Through humidity deviation calculation, the humidity deviation value of each regional model can be calculated based on the preset humidity value, and the difference between the actual humidity and the preset value can be analyzed. Calculating the humidity deviation helps to understand the degree of deviation of humidity in each region, and provides a basis for the formulation of humidity compensation strategy. Through humidity compensation calculation, humidity compensation calculation can be performed on each region according to the humidity deviation value to obtain the humidity compensation value of each region to adjust the humidity distribution. Calculating the humidity compensation value helps to achieve humidity regulation for each region and improve the accuracy and stability of humidity control. Through regional adaptive humidity gradient compensation, humidity compensation can be performed on the test box according to environmental fluctuations and the humidity compensation values ​​of each region, and adaptive humidity gradient compensation data can be generated. Realizing adaptive humidity gradient compensation helps to improve the uniformity and stability of humidity in the test box and ensure the accuracy of the test environment. Through multi-region collaborative optimization calculation, adaptive humidity gradient compensation data can be optimized to obtain more accurate adaptive humidity compensation parameters. Collaborative optimization calculation helps improve the efficiency and accuracy of the humidity compensation strategy and optimize the overall performance of humidity control in the test chamber. Through iterative compensation learning, an intelligent humidity compensation strategy can be constructed based on the adaptive humidity compensation optimization parameters to achieve intelligent and continuous optimization of the humidity compensation strategy. Iterative learning helps to continuously improve the humidity compensation strategy, improve the stability and accuracy of humidity control in the test chamber, and adapt to changes in different environmental conditions.

[0022] In this specification, a humidity gradient compensation device for an alternating humidity test chamber is provided, which is used to perform the humidity gradient compensation method for an alternating humidity test chamber as described above, comprising: The humidity gradient trend module is used to obtain the test chamber state monitoring parameters based on the multi-dimensional sensor array; the spatial humidity gradient distribution analysis of the test chamber state monitoring parameters is performed, and discrete interpolation fitting is performed to construct a three-dimensional humidity gradient trend network; The air flow diffusion module is used to analyze the internal dynamic air flow diffusion of the alternating humidity and heat test chamber, thereby generating dynamic air flow diffusion data of the test chamber; The humidity diffusion path module is used to mine the dynamic humidity diffusion path of the three-dimensional humidity gradient trend network based on the dynamic airflow diffusion data of the test chamber, and to build a dynamic humidity diffusion twin model; The environmental change association module is used to obtain the external environmental monitoring parameters of the test chamber; based on the external environmental monitoring parameters of the test chamber, the three-dimensional humidity gradient trend network is mined for environmental change associations, thereby generating humidity gradient change association data under environmental fluctuations; The humidity compensation diffusion module is used to simulate the humidity compensation flow and the humidity gradient compensation diffusion evolution of the dynamic humidity diffusion twin model according to the humidity gradient change correlation data under environmental fluctuations, so as to generate the humidity gradient compensation diffusion law under environmental fluctuations; The adaptive humidity compensation module is used to perform regional adaptive humidity gradient compensation for multiple regional twin models based on the diffusion law of humidity gradient compensation under environmental fluctuations, and to build an intelligent humidity compensation strategy.

[0023] The present invention obtains the state monitoring parameters of the test box through a multi-dimensional sensor array, realizes comprehensive monitoring of the internal state of the test box, performs spatial humidity gradient distribution analysis and discrete interpolation fitting, and constructs a three-dimensional humidity gradient trend network, which is helpful to understand the spatial distribution characteristics of the humidity gradient, analyze the dynamic airflow diffusion inside the test box, generate dynamic airflow diffusion data, provide a detailed understanding of the airflow movement inside the test box, optimize the airflow movement mode in the test box, improve the uniformity and stability of humidity and temperature, and based on the dynamic airflow diffusion data, the three-dimensional humidity gradient trend network is used to mine the dynamic humidity diffusion path, construct a dynamic humidity diffusion twin model, understand the propagation path of humidity in the test box, and provide a basis for the formulation of humidity compensation strategies. The external environment monitoring parameters of the test box are obtained, and the three-dimensional The humidity gradient trend network conducts environmental change correlation mining, generates humidity gradient change correlation data under environmental fluctuations, understands the impact of external environmental changes on the humidity in the test chamber, and provides a basis for adjusting the humidity compensation strategy. According to the humidity gradient change correlation data under environmental fluctuations, the dynamic humidity diffusion twin model is used to simulate the humidity compensation flow and the humidity gradient compensation diffusion evolution, and the humidity gradient compensation diffusion law under environmental fluctuations is generated to achieve real-time adjustment of the humidity gradient and ensure the stability and uniformity of the humidity in the test chamber. Based on the humidity gradient compensation diffusion law under environmental fluctuations, regional adaptive humidity gradient compensation is performed on multiple regional twin models, and an intelligent humidity compensation strategy is constructed to perform personalized humidity compensation according to the humidity requirements of different regions, thereby improving the accuracy and efficiency of humidity control in the test chamber. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A schematic flow chart of the steps of a humidity gradient compensation method for an alternating damp heat 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 example of this application provides a method and device. The execution subjects of the method and device include but are not limited to the following: 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 this 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 humidity gradient compensation method for an alternating humidity test chamber, and the humidity gradient compensation method for an alternating humidity test chamber comprises the following steps: Step S1: Acquire the test chamber state monitoring parameters based on the multi-dimensional sensor array; perform spatial humidity gradient distribution analysis on the test chamber state monitoring parameters, and perform discrete interpolation fitting to construct a three-dimensional humidity gradient trend network; Step S2: performing internal dynamic airflow diffusion analysis on the alternating humidity and heat test chamber, thereby generating dynamic airflow diffusion data of the test chamber; Step S3: mining the dynamic humidity diffusion path of the three-dimensional humidity gradient trend network based on the dynamic airflow diffusion data of the test chamber, and constructing a dynamic humidity diffusion twin model; Step S4: Acquire external environment monitoring parameters of the test chamber; perform environmental change correlation mining on the three-dimensional humidity gradient trend network based on the external environment monitoring parameters of the test chamber, thereby generating humidity gradient change correlation data under environmental fluctuations; Step S5: According to the humidity gradient change correlation data under environmental fluctuations, the dynamic humidity diffusion twin model is subjected to humidity compensation flow simulation and humidity gradient compensation diffusion evolution, thereby generating a humidity gradient compensation diffusion law under environmental fluctuations; Step S6: Based on the diffusion law of humidity gradient compensation under environmental fluctuations, regional adaptive humidity gradient compensation is performed on multiple regional twin models to construct an intelligent humidity compensation strategy.

[0028] The present invention obtains the state monitoring parameters of the test box through a multi-dimensional sensor array, and can fully understand the humidity distribution characteristics inside the test box. The construction of a three-dimensional humidity gradient trend network is helpful to reveal the spatial characteristics of humidity distribution, and provides a basis for subsequent humidity compensation. The internal dynamic airflow diffusion analysis can reveal the dynamic characteristics of humidity changes inside the test box, and provide dynamic airflow diffusion data. These data are crucial for understanding the propagation path and speed of humidity inside the test box, and lay the foundation for the establishment of a humidity compensation model. Through the dynamic humidity diffusion path mining, a dynamic humidity diffusion twin model can be constructed to help simulate the humidity propagation process inside the test box. This model helps to understand the law of humidity diffusion and provides a basis for subsequent humidity compensation strategies. By analyzing the external environmental monitoring parameters, we can explore the relationship between the environment and the humidity gradient change, and generate humidity gradient change correlation data. These data help to understand the impact of the external environment on the humidity of the test chamber and provide more comprehensive information for the humidity compensation model. Through humidity compensation flow simulation and humidity gradient compensation diffusion evolution, we can generate the humidity gradient compensation diffusion law under environmental fluctuations, understand the change law of humidity under environmental fluctuations, and provide a basis for formulating humidity compensation strategies. Through the study of regional adaptive humidity gradient compensation, we can construct an intelligent humidity compensation strategy to improve the humidity compensation effect of the test chamber. The formulation of intelligent strategies can dynamically adjust the humidity according to real-time environmental changes, thereby improving the humidity control accuracy and efficiency of the test chamber.

[0029] In the embodiment of the present invention, refer to Figure 1 , is a schematic flow chart of the steps of a humidity gradient compensation method of an alternating damp heat test chamber of the present invention. In this example, the steps of the method include: Step S1: Acquire the test chamber state monitoring parameters based on the multi-dimensional sensor array; perform spatial humidity gradient distribution analysis on the test chamber state monitoring parameters, and perform discrete interpolation fitting to construct a three-dimensional humidity gradient trend network; In this embodiment, a multi-dimensional sensor array is installed inside the test box. The sensor types may include temperature sensors, humidity sensors, air pressure sensors, etc., and the sensors are ensured to be evenly distributed so as to comprehensively monitor the environmental status in the test box. A data acquisition system is established, such as using Arduino, RaspberryPi or other microcontrollers, connecting sensors and writing programs to read sensor data at regular intervals, setting up data acquisition programs, regularly reading status monitoring parameters (such as humidity, temperature, air pressure, etc.) from sensors, and storing the data in a local database or cloud database for subsequent analysis. The collected data is preprocessed, including removing noise, processing missing values ​​and outliers, to ensure the accuracy and completeness of the data. The data can be smoothed by moving average or interpolation, and the preprocessed humidity data is organized into a structured format, such as a CSV file or a database table, containing the ID, location coordinates (such as x, y, z) and corresponding humidity values ​​of each sensor. A two-dimensional heat map of humidity distribution is drawn using a visualization tool (such as Matplotlib, Seaborn or Plotly) to intuitively display the spatial distribution of humidity in the test box, and calculate the humidity. The spatial gradient of humidity can be estimated by numerical differentiation method or interpolation method (such as finite difference method). The calculated humidity gradient data is recorded in the data set for subsequent analysis and modeling. The appropriate interpolation method is selected. Common ones are Kriging interpolation, spline interpolation or inverse distance weighted interpolation (IDW). Kriging interpolation is usually used for smoothing of geographic spatial data and is suitable for spatial interpolation of humidity data. The humidity gradient data is fitted using the selected interpolation method to generate a continuous humidity distribution model, which can be achieved through the SciPy library in Python or the gstat package in R language. Based on the interpolation results, a three-dimensional humidity gradient trend network is established, which usually involves converting the interpolation results into three-dimensional grid data and using three-dimensional modeling software (such as MATLAB, Blender or ParaView) for visualization. A visualization diagram of the three-dimensional humidity gradient trend network is generated to show the distribution trend of humidity in the test chamber, identify the pattern and abnormal area of ​​humidity distribution, and record the parameters of the constructed three-dimensional humidity gradient trend network in the data set, including the coordinates of the grid points, humidity values ​​and gradient information, which will provide a basis for subsequent analysis and decision-making.

[0030] Step S2: performing internal dynamic airflow diffusion analysis on the alternating humidity and heat test chamber, thereby generating dynamic airflow diffusion data of the test chamber; In this embodiment, a 3D model of the test box is established using CAD or 3D modeling software (such as AutoCAD, SolidWorks or Blender) to ensure that the model accurately reflects the internal structure of the test box (such as vents, fan positions, internal partitions, etc.). According to the actual operating conditions of the test box, boundary conditions are set, including the flow rate of the air inlet, the pressure of the air outlet, the ambient temperature and humidity, etc., and appropriate computational fluid dynamics (CFD) software is selected for dynamic airflow diffusion analysis, such as ANSYS Fluent, COMSOL Multiphysics or OpenFOAM. In the CFD software, the physical properties of the fluid (such as the density and viscosity of the air) are set, and a suitable turbulence model (such as the k-ε model or the LES model) is selected to better simulate the behavior of the airflow. The established 3D model is meshed to ensure that the mesh is fine enough to accurately capture the changes in the airflow. The meshing tool provided by the software is used to select an appropriate mesh type (such as a structured mesh or an unstructured mesh). The quality of the generated mesh, including the distortion, uniformity and refinement of the mesh, is checked to ensure that the mesh is suitable for numerical simulation. Set the initial conditions, including the initial temperature, humidity and flow rate of the internal air, select a suitable solver (such as a steady-state or transient solver), and set the solution parameters (such as convergence criteria, time step, etc.), start the simulation, and the software will calculate the diffusion of the airflow inside the test chamber according to the set boundary conditions and initial conditions, monitor the key parameters (such as pressure, flow rate and temperature) during the simulation, and ensure the stability and convergence of the simulation. After the simulation is completed, extract the airflow diffusion data from the CFD software, including velocity field, pressure field and temperature field, etc. These data can be exported in multiple formats (such as CSV, VTK), and use visualization tools (such as ParaView, Tecplot or MATLAB) to visualize the airflow diffusion results, display the flow path, velocity distribution and temperature changes of the airflow, analyze the dynamic characteristics of the airflow, identify the main channels, stagnation areas and turbulent areas of the airflow, evaluate the efficiency and uniformity of the airflow diffusion, and record the generated dynamic airflow diffusion data in the database, including key parameters such as airflow velocity, pressure and temperature, summarize the analysis results, write a report, and provide conclusions and suggestions for the airflow diffusion analysis to guide the design improvement or operation optimization of the test chamber.

[0031] Step S3: mining the dynamic humidity diffusion path of the three-dimensional humidity gradient trend network based on the dynamic airflow diffusion data of the test chamber, and constructing a dynamic humidity diffusion twin model; In this embodiment, dynamic airflow diffusion data, including flow rate, pressure, temperature and humidity distribution, etc., are extracted from the previous steps. These data will serve as the basis for analysis. The extracted data are sorted and cleaned to ensure data integrity and accuracy, remove noise and outliers, and prepare for further analysis. A suitable path mining algorithm is selected, such as a particle tracking method based on fluid dynamics, dynamic time warping (DTW) or a shortest path algorithm. These algorithms can effectively identify the diffusion path of humidity. The dynamic airflow diffusion data is analyzed using the selected algorithm to identify the key path of humidity diffusion. The specific steps include: combining humidity data with airflow data, calculating the change of humidity over time and space, tracking the change path of humidity through an algorithm, identifying the main diffusion channels and retention areas, and recording the mined dynamic humidity diffusion path data in a data set, including the starting point, end point, humidity value and change of the path. A suitable dynamic model is selected to express the humidity diffusion process. A model based on fluid dynamics or a machine learning model (such as a recursive neural network RNN, a long short-term memory network LSTM) is usually used, and necessary parameters are set in the model. , such as diffusion coefficient, boundary conditions and initial conditions, to ensure that the model can accurately simulate the dynamic behavior of humidity, use the recorded dynamic humidity diffusion path data to train the model, adjust the model parameters to improve its prediction accuracy, and use methods such as cross-validation to evaluate the performance of the model. Design the framework of the dynamic humidity diffusion twin model, compare and verify the actual humidity distribution with the simulated humidity diffusion path, combine the real-time monitoring data with the existing dynamic model to ensure that the twin model can reflect the humidity changes in the test chamber in real time, verify the constructed dynamic humidity diffusion twin model, compare the differences between the simulation results and the actual monitoring data, and perform necessary model optimization. Record the parameters and results of the dynamic humidity diffusion twin model in the database, including humidity distribution, diffusion path and model performance indicators, summarize the results of humidity diffusion path mining and twin model construction, write a report, provide suggestions and improvement directions for the humidity control of the test chamber, and use visualization tools (such as ParaView or Matplotlib) to display the results of the dynamic humidity diffusion path and twin model to facilitate analysis and understanding of the dynamic behavior of humidity.

[0032] Step S4: Acquire external environment monitoring parameters of the test chamber; perform environmental change correlation mining on the three-dimensional humidity gradient trend network based on the external environment monitoring parameters of the test chamber, thereby generating humidity gradient change correlation data under environmental fluctuations; In this embodiment, a variety of environmental monitoring devices are installed outside the test box, including temperature sensors, humidity sensors, air pressure sensors, light sensors, etc., to comprehensively monitor environmental changes. A microcontroller (such as Arduino or RaspberryPi) or a data acquisition system is used to connect the monitoring equipment and write a program to collect data of various parameters, ensuring that the device can record data in real time and has data storage or transmission functions. The acquisition frequency is set, and the external environmental monitoring parameters are read regularly. The data is stored in a local database or a cloud database for subsequent analysis. The collected environmental monitoring data is preprocessed, including denoising, processing missing values ​​and outliers, to ensure the accuracy and completeness of the data. Moving average or interpolation method can be used for smoothing. The preprocessed external environmental monitoring parameters are organized into a structured format (such as CSV or database table), including the timestamp, value and related position of each parameter. The three-dimensional humidity gradient trend network constructed in the previous step is used to ensure that the network can reflect Changes in humidity inside the test chamber, combining external environmental parameters with the humidity gradient trend network for association analysis, selecting appropriate association mining methods, such as correlation analysis, regression analysis, time series analysis or machine learning methods (such as random forests, support vector machines, etc.) to mine the relationship between changes in the external environment and changes in the humidity gradient, using the selected method to analyze the association between external environmental monitoring parameters and changes in humidity gradients, for example: calculating the correlation coefficient between environmental parameters and humidity gradients, identifying external factors that significantly affect humidity, using regression analysis modeling to explore the impact of external environmental changes on the humidity gradient inside the test chamber, recording the analysis results, related parameters and model performance indicators in data sets and reports for subsequent use, summarizing the impact of environmental changes on humidity gradients, writing reports, providing suggestions and improvement directions for test chamber humidity management, and formulating corresponding humidity control strategies based on the results of association analysis to cope with changes in the external environment and improve the stability and reliability of humidity control in the test chamber.

[0033] Step S5: According to the humidity gradient change correlation data under environmental fluctuations, the dynamic humidity diffusion twin model is subjected to humidity compensation flow simulation and humidity gradient compensation diffusion evolution, thereby generating a humidity gradient compensation diffusion law under environmental fluctuations; In this embodiment, from the humidity gradient change associated data under environmental fluctuations, these data include information on the impact of the external environment on the humidity gradient, which provides a basis for subsequent simulations, ensures that the dynamic humidity diffusion twin model has been constructed, and can reflect the dynamic characteristics of humidity changes in the test box. The model should be able to receive external environmental data and humidity gradient information, select suitable computational fluid dynamics (CFD) software for humidity compensation flow simulation, such as ANSYS Fluent, COMSOL Multiphysics or OpenFOAM, input the humidity gradient change associated data into the CFD software, set initial conditions and boundary conditions, which include: the initial state of humidity distribution, external environmental parameters (such as temperature, humidity, air flow velocity, etc.), start the humidity compensation flow simulation, and observe the flow of humidity inside the test box. During the simulation process, the following aspects should be paid attention to: humidity compensation flow path and velocity distribution, humidity changes in different areas, identify the main humidity flow channels, record simulation results, extract humidity compensation flow data, including humidity values ​​and flow conditions in different areas, so as to facilitate subsequent analysis and select appropriate mathematical models. The model is used to describe the evolution of humidity gradient compensation diffusion. Common models include diffusion equation, convection diffusion equation or heat conduction equation. Necessary parameters are set in the diffusion model, such as diffusion coefficient (determined according to humidity and airflow characteristics), boundary conditions (such as solid boundary, convection boundary, etc.), and numerical methods (such as finite difference method, finite element method) are used to simulate the evolution of humidity gradient compensation diffusion. The specific steps include: taking the results of humidity compensation flow simulation as initial conditions, inputting them into the diffusion evolution model, running the simulation, observing the dynamic process of humidity compensation diffusion, recording the evolution of humidity in different areas, analyzing the generated humidity gradient compensation diffusion data, identifying the diffusion rate and range, generating visualization charts (such as heat maps, three-dimensional distribution charts), intuitively displaying the law of humidity diffusion, recording the key data of the humidity gradient compensation diffusion law in the database, including diffusion rate, humidity distribution and influencing factors, summarizing the results of humidity compensation flow simulation and compensation diffusion evolution, writing a detailed report, providing suggestions and improvement directions for the humidity management of the test chamber, and formulating corresponding humidity control strategies based on the analysis results to improve the efficiency and stability of humidity management in the test chamber.

[0034] Step S6: Based on the diffusion law of humidity gradient compensation under environmental fluctuations, regional adaptive humidity gradient compensation is performed on multiple regional twin models to construct an intelligent humidity compensation strategy.

[0035] In this embodiment, it is ensured that the humidity twin models of multiple regions have been constructed and can reflect the changes in the actual environment, and are ready for adaptive humidity gradient compensation. A suitable adaptive control algorithm is selected, such as fuzzy control, PID control or adaptive gain control. These algorithms can automatically adjust the humidity compensation strategy according to environmental changes, determine the input parameters required for the compensation algorithm, including: current humidity value, preset humidity target value, external environmental parameters (such as temperature, humidity, air flow speed, etc.), formulate a regional adaptive humidity gradient compensation strategy, ensure that the compensation operation of each region can be carried out independently and coordinate work at the same time, for example: increase the compensation intensity in areas with large humidity deviations, and reduce the compensation in areas where the humidity is close to the target value. The humidity values ​​and external environmental parameters of each area are monitored in real time by sensors, and the real-time data is input into the adaptive compensation algorithm. Gradient compensation strategy, start the corresponding humidity control equipment (such as humidifiers, dehumidifiers, fans, etc.) to perform compensation operations, implement dynamic adjustments in each area to ensure that the humidity can quickly respond to environmental changes, record the effect of each compensation operation, including humidity changes, equipment operating status and environmental parameters, for subsequent analysis and optimization, and select suitable machine learning algorithms (such as neural networks, decision trees or reinforcement learning) to build intelligent humidity compensation strategies. This strategy can automatically optimize the compensation plan based on historical data and real-time feedback, organize historical humidity compensation data, including compensation values, humidity changes and environmental conditions, and use it to train intelligent algorithms. Use prepared data sets to train intelligent algorithms and optimize model parameters to improve the accuracy and response speed of humidity compensation. Verify the model through cross-validation and other methods to ensure its effectiveness under different environmental conditions.

[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: Acquire test chamber status monitoring parameters based on a multi-dimensional sensor array; Step S12: Calculate the temperature change of the test chamber status monitoring parameters and identify the temperature change data of the test chamber; Step S13: performing spatial humidity gradient distribution analysis on the test chamber state monitoring parameters to obtain three-dimensional humidity gradient distribution characteristics; Step S14: mining humidity change trend of the three-dimensional humidity gradient distribution characteristics according to the test chamber temperature change data, thereby obtaining humidity gradient change trend data; Step S15: Perform discrete interpolation fitting on the humidity gradient change trend data to construct a three-dimensional humidity gradient trend network.

[0037] In this embodiment, a multi-dimensional sensor array is arranged in the test box. These sensors include temperature sensors, humidity sensors, air pressure sensors, and light sensors, etc., to ensure that the sensors are evenly distributed at different locations to obtain comprehensive monitoring data. A suitable data acquisition system (such as Arduino, RaspberryPi, or a dedicated monitoring device) is selected to collect and process sensor signals. The data acquisition software is configured, the sampling frequency and data storage format are set, the data acquisition system is started, and the state monitoring parameters of the test box, including temperature, humidity, air pressure, etc., are obtained in real time. The data is recorded for subsequent analysis, and the obtained temperature monitoring data is organized into time series data to ensure the integrity and consistency of the data. The temperature change rate is calculated, ΔT=T(t)−T(t−1), where T(t) is the temperature at the current moment and T(t−1) is the temperature at the previous moment. The trend of the temperature change data is identified, and a temperature change data set is generated, including statistical information such as the maximum value, the minimum value, and the change amplitude. The humidity data obtained by the humidity sensor is organized into a data set in a three-dimensional coordinate system to ensure that the data can reflect the humidity levels at different locations. A suitable spatial analysis method is selected, such as the Kriging interpolation method or the inverse distance weighted method (I DW) to generate a spatial distribution model of humidity, use the selected method to analyze the humidity data, generate a three-dimensional humidity gradient distribution feature map, which can be visualized using GIS software (such as ArcGIS or QGIS) or scientific computing software (such as MATLAB, Python), select appropriate time series analysis methods, such as moving average, exponential smoothing or ARIMA model, to explore the trend of humidity changes, use the selected method to analyze the humidity gradient distribution feature data, extract humidity change trend data, including rising, falling or stable trends, record humidity gradient change trend data, generate visualization charts to help understand the dynamic characteristics of humidity changes, select a suitable discrete interpolation method, such as cubic spline interpolation or radial basis function interpolation (RBF), fit the humidity gradient change trend data, input the humidity gradient change trend data into the selected interpolation method, construct a three-dimensional humidity gradient trend network, generate a humidity change model, verify the accuracy of the fitting model, compare it with the actual measured data, make necessary adjustments, and use visualization tools (such as Matplotlib, Plotly or three-dimensional graphics software) to display the three-dimensional humidity gradient trend network to ensure that it is intuitive and easy to understand.

[0038] In this embodiment, the specific steps of step S13 are: Extract all sensor nodes based on multi-dimensional sensor array; Calculate the spatial position of all sensor nodes to obtain the spatial position coordinates of each node; Perform sensor node distribution analysis on the spatial position coordinates of each node to obtain sensor node distribution data; Based on the sensor node distribution data, the regional parameter segmentation and identification of the test chamber state monitoring parameters are performed to obtain multiple test chamber regional monitoring parameters; Calculate the humidity of each area of ​​the multiple test chambers for each monitoring parameter, and extract the humidity parameters of each test chamber area; Calculate the humidity difference between the regions for the humidity parameters of each test chamber area to generate the humidity difference value between the regions; Conduct humidity difference gradient analysis on humidity difference values ​​between regions to generate humidity difference gradient data; The humidity difference gradient data is subjected to three-dimensional humidity gradient distribution analysis to obtain the three-dimensional humidity gradient distribution characteristics.

[0039] In this embodiment, it is ensured that the multi-dimensional sensor array has been correctly installed in the test box. The sensor types include temperature, humidity, air pressure, etc. A data acquisition system (such as Arduino or RaspberryPi) is used to extract real-time monitoring data from each sensor node, including node identification, sensor type and its measurement value. The extracted sensor node information is organized into a structured data format (such as CSV or database), ensuring that the basic information of each node is complete, including the location identification and sensor type. The geometric layout of the sensor array is determined. The spatial coordinates of the sensor are usually determined according to the physical size of the test box. The known sensor installation position and spatial coordinate system (such as Cartesian) are used to obtain the real-time monitoring data. The spatial coordinates of each sensor node are calculated using a coordinate system, and the spatial coordinates of each node are recorded in a data set to form a node coordinate list. A suitable distribution analysis method is selected, such as statistical analysis, visualization tools (such as heat maps), or spatial analysis software (such as GIS). The spatial coordinates of each sensor node are analyzed using the selected method to generate a distribution feature map of the sensor nodes, identify concentrated and sparse areas of sensors, and generate sensor node distribution data, including the number of nodes, density distribution, and their spatial layout in the test box. According to the sensor node distribution data and the physical structure of the test box, the test box is divided into multiple areas. For example, it can be divided based on node density or functional areas. , divide the state monitoring parameters (such as temperature and humidity) of the test chamber into regions, ensure that the parameters in each region can be analyzed independently, generate a monitoring parameter data set for each region, ensure that it contains the region identifier and its corresponding state monitoring parameters, extract humidity parameters from the sensor nodes of each divided region, ensure that the humidity data of each region is complete, calculate the average humidity value of each region, record the calculated humidity parameters of each region in the data set, calculate the humidity difference between each region: humidity difference = humidity of region A − humidity of region B, calculate the humidity difference for each pair of regions, generate a list of humidity difference values ​​between regions, and select a suitable gradient analysis method, such as numerical differentiation Or smooth interpolation method is used to calculate the spatial gradient of humidity difference. The gradient of humidity difference is calculated through the calculated humidity difference value, and the areas with large humidity changes are identified. A humidity difference gradient data set is generated, and the gradient values ​​of each area are recorded. Suitable three-dimensional analysis and visualization tools (such as MATLAB, Python's Matplotlib or Mayavi) are selected to generate a three-dimensional distribution map. The humidity difference gradient data is displayed using a three-dimensional visualization method. A three-dimensional humidity gradient distribution characteristic map is generated to show the distribution of humidity in the test chamber. The generated three-dimensional humidity gradient distribution characteristic map is recorded, and the results are interpreted and analyzed to provide a basis for subsequent research or experiments.

[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 internal geometric analysis on the alternating damp heat test chamber to obtain internal geometric data of the test chamber; Step S22: performing spatial topological structure recognition on the internal geometric data of the test box to extract spatial topological structure data; Step S23: performing three-dimensional topological point cloud modeling on the spatial topological structure data to construct a three-dimensional structure model of the test box; Step S24: performing internal air flow mining on the three-dimensional structure model of the test box based on the test box state monitoring parameters, thereby extracting the internal air flow characteristics of the test box; Step S25: Perform dynamic airflow diffusion analysis on the air flow characteristics inside the test box, thereby generating dynamic airflow diffusion data of the test box.

[0041] In this embodiment, a laser scanner, a three-dimensional measuring instrument or a photogrammetry technique is used to obtain geometric data inside the test box. These devices can generate high-precision three-dimensional point cloud data. The obtained raw geometric data is cleaned and preprocessed, including noise removal, data alignment and coordinate conversion, to ensure the accuracy and consistency of the data. The cleaned geometric data is organized into a structured format (such as an XYZ coordinate file or a grid format), and the geometric features inside the test box are recorded, including size, shape and surface features. The topological structural features inside the test box are determined, including channels, cavities and connection points, etc., and topological data analysis (TDA) tools or algorithms (such as Alpha shape, Voro noi map) to identify and extract spatial topological structure data, use the selected method to analyze the geometric data, extract the spatial topological structure of the test box, identify different areas and their interconnection relationships, record the extracted topological structure data in the database, including the properties and connection information of each topological element, convert the extracted spatial topological structure data into a 3D point cloud model, use point cloud processing software (such as CloudCompare or Meshlab) for processing, select suitable 3D modeling software (such as Blender, AutoCAD, SolidWorks) to model the topological point cloud, and in the selected software, according to the processed point cloud data Construct a 3D structural model of the test chamber to ensure the accuracy and visualization of the model. Optimize the generated 3D model, including simplifying the mesh, smoothing the surface, and ensuring geometric accuracy, so as to facilitate subsequent analysis and simulation. Integrate the state monitoring parameters of the test chamber, including temperature, humidity, air flow velocity, and pressure, so as to conduct a comprehensive analysis of the air flow. Select computational fluid dynamics (CFD) software (such as ANSYS Fluent, COMSOL Multiphysics, or OpenFOAM) to explore the internal air flow. Import the constructed 3D structural model into the CFD software, set the boundary conditions and initial conditions, including the inflow and outflow positions, flow velocity, and Physical properties, run air flow simulation, observe the air flow distribution and flow characteristics inside the test chamber, extract data such as air flow velocity, pressure change and flow direction, organize the air flow characteristic data obtained from CFD simulation, including time series data, for dynamic analysis, select appropriate analysis methods, such as Laplace equation, diffusion model or particle tracking method, to analyze the diffusion characteristics of airflow in the test chamber, perform diffusion analysis on dynamic airflow data, generate diffusion path, velocity distribution and concentration change diagram of airflow in the test chamber, record the generated dynamic airflow diffusion data, including diffusion coefficient, diffusion range and dynamic change trend, and visualize it to help understand airflow behavior.

[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: performing humidity diffusion simulation on the three-dimensional humidity gradient distribution characteristics based on the dynamic airflow diffusion data of the test chamber to generate humidity diffusion simulation data of the test chamber; Step S32: Tracking the spatiotemporal changes of the test chamber humidity diffusion simulation data to generate a spatiotemporal change trajectory of humidity diffusion; Step S33: mining the dynamic humidity diffusion path of the spatiotemporal change trajectory of humidity diffusion, thereby obtaining dynamic humidity diffusion path data; Step S34: Based on the dynamic humidity diffusion path data, the three-dimensional humidity gradient trend network is dynamically rendered to construct a dynamic humidity diffusion twin model.

[0043] In this embodiment, the dynamic airflow diffusion data of the test box generated before are collected, including air flow characteristics and related parameters (such as air flow velocity, pressure distribution, etc.). Suitable numerical simulation software (such as COMSOL Multiphysics, ANSYS Fluent or MATLAB) is selected to simulate humidity diffusion. In the selected simulation software, a physical model including humidity diffusion is established, airflow diffusion data is input, and boundary conditions and initial conditions of humidity diffusion are set. Run the simulation, observe the diffusion process of humidity inside the test box, and record the humidity diffusion simulation data, including humidity distribution and changes. The humidity diffusion simulation data is sorted into time series data to ensure that the data includes the humidity distribution at each time point. Determine an algorithm for tracking humidity changes, such as using an interpolation method or a time series analysis technique to analyze the humidity distribution at different time points. Track the spatiotemporal changes in the humidity diffusion simulation data, generate the spatiotemporal change trajectory of humidity diffusion, and record the changes of humidity in different regions and time points. Use visualization tools (such as Matplotlib, Plotly or 3D visualization software) to display the spatiotemporal change trajectory of humidity diffusion for easy understanding and analysis. Select a suitable path mining algorithm, such as dynamic time warping (DTW), the shortest path algorithm, or a path tracking algorithm based on fluid dynamics. According to the spatiotemporal variation trajectory of humidity diffusion, use the selected algorithm to mine the dynamic humidity diffusion path and identify the main paths and characteristics of humidity diffusion. Record the mined dynamic humidity diffusion path data in the data set, including the starting point, end point, and humidity values ​​of each key node of the path. Use visualization tools to display the dynamic humidity diffusion path to help understand the flow and diffusion characteristics of humidity in the test chamber. Integrate the dynamic humidity diffusion path data with the three-dimensional humidity gradient trend network to ensure that the data can be correlated. Select a suitable rendering engine or visualization software (such as Unity, Blender, or UnrealEngine) to render the dynamic humidity diffusion. Construct a three-dimensional humidity gradient trend network in the rendering tool and set the rendering parameters of the dynamic humidity diffusion path, including color, transparency, and dynamic effects. Run the rendering program to display the dynamic humidity diffusion process in real time and generate a dynamic humidity diffusion twin model to facilitate the observation and analysis of humidity diffusion changes. Verify the consistency of the rendering results with the actual data and optimize the rendering effect based on feedback and actual observation results.

[0044] In this embodiment, step S4 includes the following steps: Step S42: performing environmental parameter change analysis on the external environmental monitoring parameters of the test chamber to generate environmental parameter change data; Step S43: Perform time series variation fitting on the environmental parameter variation data to construct an environmental parameter time series variation curve; Step S44: identifying parameter mutation points on the environmental parameter time series variation curve, and extracting multiple parameter mutation points; Step S45: Perform environmental change association mining on the three-dimensional humidity gradient trend network based on multiple parameter mutation points, thereby generating humidity gradient change association data under environmental fluctuations.

[0045] In this embodiment, environmental monitoring parameter data outside the test box are collected, including temperature, humidity, air pressure, light, etc. It can be obtained through a sensor array or a monitoring system. The collected environmental monitoring parameters are organized into a structured data format (such as CSV or a database) to ensure that the data of each parameter is complete and the timestamp is consistent. The change amount of each environmental parameter is calculated, and basic statistical analysis methods (such as mean and variance) are used to evaluate the fluctuation of the parameters. Generate environmental parameter change data, including the change trend and amplitude of each parameter in a specific time period. The environmental parameter change data is organized into time series data to ensure that the data is arranged in chronological order and contains timestamps. Select a suitable fitting method, such as linear regression, local weighted regression, or spline interpolation, to construct a time series change curve of the environmental parameters. Use the selected fitting method to analyze the time series data of the environmental parameters and generate a time series change curve of the environmental parameters. This can be achieved by using data analysis software (such as Python's SciPy, R, or MATLAB). Visualize the fitting results and generate a time series change curve graph to facilitate the observation of the change trend of each environmental parameter. Select a suitable algorithm for mutation point identification, such as CUSUM (Cumulative Sum Control Chart), Bayesian Change Point Detection, or Moving Average. Input the time series change data of environmental parameters into the selected algorithm to analyze the mutation points. Run the algorithm to identify the mutation points in the environmental parameter change curve. These mutation points indicate significant changes in environmental conditions, such as a sudden increase in temperature or a decrease in humidity. Record the multiple identified parameter mutation points in the data set, including the location (time) of the mutation point and its corresponding environmental parameter value. Select a suitable association mining method, such as association rule learning, time series association analysis, or regression analysis, to study the relationship between the mutation point and the change in humidity gradient. Arrange the data of the humidity gradient trend network, including the change in humidity gradient and the corresponding environmental parameter change data, for association analysis. Run the selected association mining algorithm to analyze the relationship between multiple parameter mutation points and humidity gradient changes, and generate association data of humidity gradient changes under environmental fluctuations. Record the generated environmental fluctuation and humidity gradient change association data, and use visualization tools (such as Matplotlib, Seaborn, or PowerBI) to display the association results for in-depth analysis and understanding.

[0046] In this embodiment, step S5 includes the following steps: Step S51: dividing the dynamic humidity diffusion twin model into regions to obtain multiple regional twin models; Step S52: performing humidity compensation flow simulation on multiple regional twin models based on the humidity gradient change correlation data under environmental fluctuations, thereby generating humidity compensation flow simulation data between multiple regions; Step S53: performing humidity gradient compensation diffusion evolution on the humidity compensation flow simulation data between multiple regions, thereby generating a humidity gradient compensation diffusion law under environmental fluctuations; Step S54: performing humidity gradient compensation diffusion evolution on the degree compensation delayed response characteristics of each area, thereby generating a humidity gradient compensation diffusion law under environmental fluctuations.

[0047] In this embodiment, the existing dynamic humidity diffusion twin model is analyzed to identify different regions in the model. These regions are based on physical properties (such as size, shape) or functional properties (such as different humidity environments). The criteria for regional division are determined, such as based on humidity distribution, air flow path or temperature gradient, to ensure that the division can reflect the characteristics of the actual environment. Regional division is performed in the dynamic humidity diffusion twin model, and multiple regional twin models are generated using modeling software (such as Blender, Unity or MATLAB). The twin model information of each region is recorded in a database, including region identification, geometric features and initial humidity conditions. Suitable CFD simulation software (such as ANSYS Fluent, COMSOL Multiphysics) is selected for humidity compensated flow simulation, and multiple regional twin models are imported into the CFD software. Initial conditions and boundary conditions are set, and humidity gradient change correlation data under environmental fluctuations is input. The humidity compensated flow simulation is run to observe the humidity flow between different regions, record the humidity compensated flow simulation data, including humidity changes and flow paths, organize the simulation results, and generate humidity between multiple regions. Compensated flow data set, including humidity distribution and changes between different regions. Based on humidity compensated flow simulation data, a humidity gradient compensated diffusion evolution model is established. A suitable mathematical model (such as diffusion equation or convection diffusion equation) is selected. The compensated diffusion evolution simulation is run to observe the diffusion evolution process of humidity gradient in different regions. The humidity gradient compensated diffusion data is recorded. The generated humidity gradient compensated diffusion law is analyzed. The diffusion process is displayed using visualization tools to ensure that the results are intuitive and easy to understand. The humidity gradient compensated diffusion law is recorded in the data set, including the diffusion rate, range and influencing factors. The delayed response characteristics of humidity gradient compensation are determined, including humidity response time, compensation effect and mutual influence between regions. A suitable dynamic response model (such as time-lag model, linear or nonlinear dynamic system model) is selected. The compensated delayed response analysis of the humidity gradient in each region is performed. The delayed response characteristics of humidity gradient compensation are analyzed for each region. The relationship between humidity change and time is recorded. Humidity gradient compensation response data is generated. The analysis results are sorted out. A visualization chart of the delayed response characteristics of humidity gradient compensation is generated to help understand the response characteristics of different regions under environmental fluctuations.

[0048] In this embodiment, step S6 includes the following steps: Step S61: Calculate the current humidity distribution of multiple regional twin models and extract the humidity distribution value of each regional model; Step S62: Calculating the humidity deviation of the humidity distribution value of each regional model based on the preset test chamber humidity value, thereby generating a humidity deviation value for each region; Step S63: performing humidity compensation calculation on the humidity deviation value of each area to obtain a humidity compensation value of each area; Step S64: performing regional adaptive humidity gradient compensation on the test box based on the humidity gradient compensation diffusion law under environmental fluctuations and the humidity compensation value of each area, thereby generating adaptive humidity gradient compensation data; Step S65: performing multi-region collaborative optimization calculation on the adaptive humidity gradient compensation data to obtain adaptive humidity compensation optimization parameters; Step S66: Perform iterative compensation learning on the adaptive humidity compensation optimization parameters to construct an intelligent humidity compensation strategy.

[0049] In this embodiment, the current humidity state data is extracted from the twin model of each region, including the humidity values ​​of simulation or real-time monitoring. The humidity of each region is calculated using numerical calculation tools (such as MATLAB, Python's NumPy library) to generate a humidity distribution value. The calculated humidity distribution value of each region is organized into a structured data format (such as a table or database) for subsequent analysis. Determine the preset humidity value of the test chamber, which can be based on standard operating conditions or experimental requirements. Humidity deviation = current humidity value − preset humidity value, calculate the humidity deviation of the current humidity distribution value of each region, and generate the humidity deviation value of each region. The generated humidity deviation value is recorded in the data set for subsequent compensation calculation. Select a suitable humidity compensation model, such as linear compensation, proportional control or PID control algorithm, to calculate the humidity compensation value of each region. Apply the compensation model according to the humidity deviation value, calculate the humidity compensation value of each region, and record the humidity compensation value of each region in the data set, ready for subsequent regional adaptive humidity adjustment. According to the diffusion law of humidity gradient compensation under environmental fluctuations, the humidity compensation values ​​of each region are integrated to generate a regional adaptive compensation scheme. Select a suitable adaptive control algorithm (such as fuzzy control, PID control, or adaptive gain adjustment) to implement humidity gradient compensation. Apply adaptive humidity gradient compensation in the test chamber and adjust the humidity of each zone according to the calculated humidity compensation value. Record the adaptive humidity gradient compensation data, including the adjusted humidity value and the corresponding control parameters. Select a suitable optimization algorithm (such as genetic algorithm, particle swarm optimization, or gradient descent) to achieve collaborative optimization of multiple zones. Use the adaptive humidity gradient compensation data and the humidity compensation values ​​of each zone as input for optimization calculation. Run the collaborative optimization algorithm to calculate the adaptive humidity compensation optimization parameters to ensure that the humidity adjustments of each zone are coordinated with each other. Record the humidity compensation optimization parameters obtained after optimization and analyze them to verify the optimization effect. Select a suitable machine learning algorithm (such as reinforcement learning, supervised learning, or neural network) to learn and optimize humidity compensation. Organize historical humidity compensation data, including compensation values, deviations, and environmental conditions, to train the learning model. In an iterative manner, continuously adjust the compensation strategy and optimize the humidity compensation model to adapt to different environmental conditions. Based on the learning results, build an intelligent humidity compensation strategy to ensure that the humidity compensation can be automatically adjusted when the environment fluctuates to achieve optimal humidity control. Verify the constructed intelligent humidity compensation strategy, collect feedback and make necessary optimization adjustments to ensure its effectiveness and reliability.

[0050] In this embodiment, a humidity gradient compensation device for an alternating humidity test chamber is provided, which is used to perform the humidity gradient compensation method for an alternating humidity test chamber as described above, including: The humidity gradient trend module is used to obtain the test chamber state monitoring parameters based on the multi-dimensional sensor array; the spatial humidity gradient distribution analysis of the test chamber state monitoring parameters is performed, and discrete interpolation fitting is performed to construct a three-dimensional humidity gradient trend network; The air flow diffusion module is used to analyze the internal dynamic air flow diffusion of the alternating humidity and heat test chamber, thereby generating dynamic air flow diffusion data of the test chamber; The humidity diffusion path module is used to mine the dynamic humidity diffusion path of the three-dimensional humidity gradient trend network based on the dynamic airflow diffusion data of the test chamber, and to build a dynamic humidity diffusion twin model; The environmental change association module is used to obtain the external environmental monitoring parameters of the test chamber; based on the external environmental monitoring parameters of the test chamber, the three-dimensional humidity gradient trend network is mined for environmental change associations, thereby generating humidity gradient change association data under environmental fluctuations; The humidity compensation diffusion module is used to simulate the humidity compensation flow and the humidity gradient compensation diffusion evolution of the dynamic humidity diffusion twin model according to the humidity gradient change correlation data under environmental fluctuations, so as to generate the humidity gradient compensation diffusion law under environmental fluctuations; The adaptive humidity compensation module is used to perform regional adaptive humidity gradient compensation for multiple regional twin models based on the diffusion law of humidity gradient compensation under environmental fluctuations, and to build an intelligent humidity compensation strategy.

[0051] The present invention obtains the state monitoring parameters of the test box through a multi-dimensional sensor array, realizes comprehensive monitoring of the internal state of the test box, performs spatial humidity gradient distribution analysis and discrete interpolation fitting, and constructs a three-dimensional humidity gradient trend network, which is helpful to understand the spatial distribution characteristics of the humidity gradient, analyze the dynamic airflow diffusion inside the test box, generate dynamic airflow diffusion data, provide a detailed understanding of the airflow movement inside the test box, optimize the airflow movement mode in the test box, improve the uniformity and stability of humidity and temperature, and based on the dynamic airflow diffusion data, the three-dimensional humidity gradient trend network is used to mine the dynamic humidity diffusion path, construct a dynamic humidity diffusion twin model, understand the propagation path of humidity in the test box, and provide a basis for the formulation of humidity compensation strategies. The external environment monitoring parameters of the test box are obtained, and the three-dimensional The humidity gradient trend network conducts environmental change correlation mining, generates humidity gradient change correlation data under environmental fluctuations, understands the impact of external environmental changes on the humidity in the test chamber, and provides a basis for adjusting the humidity compensation strategy. According to the humidity gradient change correlation data under environmental fluctuations, the dynamic humidity diffusion twin model is used to simulate the humidity compensation flow and the humidity gradient compensation diffusion evolution, and the humidity gradient compensation diffusion law under environmental fluctuations is generated to achieve real-time adjustment of the humidity gradient and ensure the stability and uniformity of the humidity in the test chamber. Based on the humidity gradient compensation diffusion law under environmental fluctuations, regional adaptive humidity gradient compensation is performed on multiple regional twin models, and an intelligent humidity compensation strategy is constructed to perform personalized humidity compensation according to the humidity requirements of different regions, thereby improving the accuracy and efficiency of humidity control in the test chamber.

[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 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 humidity gradient compensation method for an alternating damp heat test chamber, characterized in that: The following steps are involved: Step S1: Acquire the test chamber state monitoring parameters based on the multi-dimensional sensor array; perform spatial humidity gradient distribution analysis on the test chamber state monitoring parameters, and perform discrete interpolation fitting to construct a three-dimensional humidity gradient trend network; Step S2: performing internal dynamic airflow diffusion analysis on the alternating humidity and heat test chamber, thereby generating dynamic airflow diffusion data of the test chamber; Step S3: mining the dynamic humidity diffusion path of the three-dimensional humidity gradient trend network based on the dynamic airflow diffusion data of the test chamber, and constructing a dynamic humidity diffusion twin model; Step S4: Acquire external environment monitoring parameters of the test chamber; perform environmental change correlation mining on the three-dimensional humidity gradient trend network based on the external environment monitoring parameters of the test chamber, thereby generating humidity gradient change correlation data under environmental fluctuations; Step S5: According to the humidity gradient change correlation data under environmental fluctuations, the dynamic humidity diffusion twin model is subjected to humidity compensation flow simulation and humidity gradient compensation diffusion evolution, thereby generating a humidity gradient compensation diffusion law under environmental fluctuations; Step S6: Based on the diffusion law of humidity gradient compensation under environmental fluctuations, regional adaptive humidity gradient compensation is performed on multiple regional twin models to construct an intelligent humidity compensation strategy.

2. The humidity gradient compensation method of the alternating damp heat test chamber according to claim 1, characterized in that: The specific steps of step S1 are: Step S11: Acquire test chamber status monitoring parameters based on a multi-dimensional sensor array; Step S12: Calculate the temperature change of the test chamber status monitoring parameters and identify the temperature change data of the test chamber; Step S13: performing spatial humidity gradient distribution analysis on the test chamber state monitoring parameters to obtain three-dimensional humidity gradient distribution characteristics; Step S14: mining humidity change trend of the three-dimensional humidity gradient distribution characteristics according to the test chamber temperature change data, thereby obtaining humidity gradient change trend data; Step S15: Perform discrete interpolation fitting on the humidity gradient change trend data to construct a three-dimensional humidity gradient trend network.

3. The humidity gradient compensation method of the alternating damp heat test chamber according to claim 2, characterized in that: The specific steps of step S13 are: Extract all sensor nodes based on multi-dimensional sensor array; Calculate the spatial position of all sensor nodes to obtain the spatial position coordinates of each node; Perform sensor node distribution analysis on the spatial position coordinates of each node to obtain sensor node distribution data; Based on the sensor node distribution data, the regional parameter segmentation and identification of the test chamber state monitoring parameters are performed to obtain multiple test chamber regional monitoring parameters; Calculate the humidity of each area of ​​the multiple test chambers for each monitoring parameter, and extract the humidity parameters of each test chamber area; Calculate the humidity difference between the regions for the humidity parameters of each test chamber area to generate the humidity difference value between the regions; Conduct humidity difference gradient analysis on humidity difference values ​​between regions to generate humidity difference gradient data; The humidity difference gradient data is subjected to three-dimensional humidity gradient distribution analysis to obtain the three-dimensional humidity gradient distribution characteristics.

4. The humidity gradient compensation method of the alternating damp heat test chamber according to claim 1, characterized in that: The specific steps of step S2 are: Step S21: performing internal geometric analysis on the alternating damp heat test chamber to obtain internal geometric data of the test chamber; Step S22: performing spatial topological structure recognition on the internal geometric data of the test box to extract spatial topological structure data; Step S23: performing three-dimensional topological point cloud modeling on the spatial topological structure data to construct a three-dimensional structure model of the test box; Step S24: performing internal air flow mining on the three-dimensional structure model of the test box based on the test box state monitoring parameters, thereby extracting the internal air flow characteristics of the test box; Step S25: Perform dynamic airflow diffusion analysis on the air flow characteristics inside the test box, thereby generating dynamic airflow diffusion data of the test box.

5. The humidity gradient compensation method of the alternating damp heat test chamber according to claim 1, characterized in that: The specific steps of step S3 are: Step S31: performing humidity diffusion simulation on the three-dimensional humidity gradient distribution characteristics based on the dynamic airflow diffusion data of the test chamber to generate humidity diffusion simulation data of the test chamber; Step S32: Tracking the spatiotemporal changes of the test chamber humidity diffusion simulation data to generate a spatiotemporal change trajectory of humidity diffusion; Step S33: mining the dynamic humidity diffusion path of the spatiotemporal change trajectory of humidity diffusion, thereby obtaining dynamic humidity diffusion path data; Step S34: Based on the dynamic humidity diffusion path data, the three-dimensional humidity gradient trend network is dynamically rendered to construct a dynamic humidity diffusion twin model.

6. The humidity gradient compensation method of the alternating damp heat test chamber according to claim 1, characterized in that: The specific steps of step S4 are: Step S41: Acquire external environment monitoring parameters of the test chamber; Step S42: performing environmental parameter change analysis on the external environmental monitoring parameters of the test chamber to generate environmental parameter change data; Step S43: Perform time series variation fitting on the environmental parameter variation data to construct an environmental parameter time series variation curve; Step S44: identifying parameter mutation points on the environmental parameter time series variation curve, and extracting multiple parameter mutation points; Step S45: Perform environmental change association mining on the three-dimensional humidity gradient trend network based on multiple parameter mutation points, thereby generating humidity gradient change association data under environmental fluctuations.

7. The humidity gradient compensation method of the alternating damp heat test chamber according to claim 1, characterized in that: The specific steps of step S5 are: Step S51: dividing the dynamic humidity diffusion twin model into regions to obtain multiple regional twin models; Step S52: performing humidity compensation flow simulation on multiple regional twin models based on the humidity gradient change correlation data under environmental fluctuations, thereby generating humidity compensation flow simulation data between multiple regions; Step S53: performing humidity gradient compensation diffusion evolution on the humidity compensation flow simulation data between multiple regions, thereby generating a humidity gradient compensation diffusion law under environmental fluctuations; Step S54: performing humidity gradient compensation diffusion evolution on the degree compensation delayed response characteristics of each area, thereby generating a humidity gradient compensation diffusion law under environmental fluctuations.

8. The humidity gradient compensation method of the alternating damp heat test chamber according to claim 1, characterized in that: The specific steps of step S6 are: Step S61: Calculate the current humidity distribution of multiple regional twin models and extract the humidity distribution value of each regional model; Step S62: Calculating the humidity deviation of the humidity distribution value of each regional model based on the preset test chamber humidity value, thereby generating a humidity deviation value for each region; Step S63: performing humidity compensation calculation on the humidity deviation value of each area to obtain a humidity compensation value of each area; Step S64: performing regional adaptive humidity gradient compensation on the test box based on the humidity gradient compensation diffusion law under environmental fluctuations and the humidity compensation value of each area, thereby generating adaptive humidity gradient compensation data; Step S65: performing multi-region collaborative optimization calculation on the adaptive humidity gradient compensation data to obtain adaptive humidity compensation optimization parameters; Step S66: Perform iterative compensation learning on the adaptive humidity compensation optimization parameters to construct an intelligent humidity compensation strategy.

9. A humidity gradient compensation device for an alternating damp heat test chamber, characterized in that: The method for performing the humidity gradient compensation method of the alternating damp heat test chamber as claimed in claim 1 comprises: The humidity gradient trend module is used to obtain the test chamber state monitoring parameters based on the multi-dimensional sensor array; the spatial humidity gradient distribution analysis of the test chamber state monitoring parameters is performed, and discrete interpolation fitting is performed to construct a three-dimensional humidity gradient trend network; The air flow diffusion module is used to analyze the internal dynamic air flow diffusion of the alternating humidity and heat test chamber, thereby generating dynamic air flow diffusion data of the test chamber; The humidity diffusion path module is used to mine the dynamic humidity diffusion path of the three-dimensional humidity gradient trend network based on the dynamic airflow diffusion data of the test chamber, and to build a dynamic humidity diffusion twin model; The environmental change association module is used to obtain the external environmental monitoring parameters of the test chamber; based on the external environmental monitoring parameters of the test chamber, the three-dimensional humidity gradient trend network is mined for environmental change associations, thereby generating humidity gradient change association data under environmental fluctuations; The humidity compensation diffusion module is used to simulate the humidity compensation flow and the humidity gradient compensation diffusion evolution of the dynamic humidity diffusion twin model according to the humidity gradient change correlation data under environmental fluctuations, so as to generate the humidity gradient compensation diffusion law under environmental fluctuations; The adaptive humidity compensation module is used to perform regional adaptive humidity gradient compensation for multiple regional twin models based on the diffusion law of humidity gradient compensation under environmental fluctuations, and to build an intelligent humidity compensation strategy.

Images