Method and system for controlling pressure stability of air pressure test box

Abstract

The invention relates to the technical field of air pressure control, in particular to an air pressure test box pressure stability control method and system. The method comprises the following steps: carrying out current non-operation state monitoring on an air pressure test box so as to obtain multi-dimensional non-operation state monitoring parameters of the air pressure test box; performing non-running state time sequence change evolution on the multi-dimensional non-running state monitoring parameters so as to generate non-running state time sequence characteristics; acquiring an internal structure diagram of the air pressure test box; performing spatial topology distribution analysis on the internal structure diagram of the air pressure test box based on non-operation state time sequence characteristics, performing three-dimensional point cloud modeling, and constructing a digital twin model of the test box; obtaining a target test scene based on the test log; performing target pressure state analysis on the target test scene, and performing final test scene state mining to obtain final test scene state data; according to the invention, high-controllability and high-precision pressure control of the air pressure test box is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of air pressure control, and in particular to a method and system for controlling the pressure stability of an air pressure test chamber. Background Art

[0002] With the continuous improvement of industrial automation level, air pressure test chamber has become a key equipment in many industrial production and testing processes. Air pressure test chamber is mainly used to simulate various complex environmental conditions and perform pressure resistance, vibration resistance, temperature shock and other performance tests on products or components. In these high-pressure and high-temperature environments, the stability of the internal pressure of the air pressure test chamber is very important, which directly affects the accuracy of the test results and the reliability of the test process.

[0003] Traditional pressure control methods for air pressure test chambers often rely on manual monitoring and manual adjustment, and have problems such as low pressure control accuracy and poor controllability. As the pace of industrial production becomes faster and faster, higher requirements are placed on the pressure stability and control accuracy of air pressure test chambers. Therefore, there is an urgent need for an intelligent pressure test chamber pressure stability control method that can automatically monitor and analyze pressure change characteristics, make corresponding adjustments in a timely manner, and ensure the smooth progress of the test process. Summary of the invention

[0004] In order to solve the above technical problems, the present invention proposes a pressure stability control method and system for an air pressure test chamber to solve at least one of the above technical problems.

[0005] To achieve the above object, the present invention provides a pressure stability control method for an air pressure test chamber, comprising the following steps: Step S1: obtaining multi-dimensional non-operating state monitoring parameters of the air pressure test box; performing non-operating state time series evolution of the multi-dimensional non-operating state monitoring parameters, thereby generating non-operating state time series features; Step S2: obtaining an internal structure diagram of the air pressure test box; performing a spatial topological distribution analysis on the internal structure diagram of the air pressure test box based on the timing characteristics of the non-operating state, and constructing a digital twin model of the test box; Step S3: acquiring a target test scenario based on the test log; performing a target pressure state analysis on the target test scenario to obtain final test scenario state data; Step S4: performing spatial air pressure stability compensation calculation on the digital twin model of the test box according to the final test scene state data to obtain a spatial air pressure stability compensation value; Step S5: performing an operating state air pressure stability test on the air pressure test box based on the space air pressure stability compensation value, thereby obtaining operating state air pressure stability data; Step S6: fine-tuning the dynamic air pressure deviation on the operating air pressure stability data to generate a dynamic air pressure deviation fine-tuning strategy to execute the air pressure test chamber pressure stability control operation.

[0006] The present invention can timely discover potential problems and improve safety by monitoring the non-operating state of the air pressure test box. Generating non-operating state time series characteristics is helpful to understand the characteristic changes of the air pressure test box in different states, providing a basis for subsequent analysis. Constructing a digital twin model of the test box can realize virtual modeling of the internal structure of the air pressure test box, which helps to understand the structure and layout inside the box. Through three-dimensional point cloud modeling, the spatial topological distribution of the test box can be more intuitively presented, providing visualization support for subsequent simulation and analysis. Analyzing the state of the target test scene is helpful to understand the pressure state that needs to be achieved in the test and guide the subsequent experimental process. By mining the final test scene state data, the experimental process and results can be optimized, the test efficiency and quality can be improved, and the air pressure Filling simulation and stability compensation calculation help predict the air pressure response of the air pressure test chamber and ensure the safety and accuracy of the test. The air pressure control of the air pressure test chamber can be optimized through the spatial air pressure stability compensation value, and the air pressure stability and experimental reliability can be improved. Real-time monitoring of the operating air pressure stability data helps to ensure the stability and accuracy of the air pressure during the test. The operating air pressure stability data can be used to adjust the air pressure control in time to ensure that the test chamber operates within the normal range. Through air pressure stability delay error analysis and dynamic air pressure deviation fine-tuning, the pressure stability of the air pressure test chamber can be optimized, the controllability and accuracy of the test can be improved, and the generation of dynamic air pressure deviation fine-tuning strategy helps to achieve stability control of the air pressure test chamber and ensure the accuracy and reliability of experimental data.

[0007] Preferably, step S1 comprises the following steps: Step S11: monitoring the current non-operating state of the air pressure test box, thereby obtaining multi-dimensional non-operating state monitoring parameters of the air pressure test box, wherein the multi-dimensional non-operating state monitoring parameters include infrared thermal imaging temperature monitoring data, test box air pressure state parameters and test box humidity parameters; Step S12: performing heat distribution analysis of the test chamber on the infrared thermal imaging temperature monitoring data, and extracting the temperature distribution data of the test chamber; Step S13: performing temperature distribution fluctuation fitting on the temperature distribution data of the test chamber to obtain a temperature distribution fluctuation curve; Step S14: performing spatial pressure gradient calculation on the test chamber air pressure state parameters to generate spatial pressure gradient characteristics; Step S15: analyzing the characteristics of the air pressure balance state of the test box based on the spatial pressure gradient characteristics to obtain the characteristics of the air pressure balance state; Step S16: Perform non-operating state time series evolution on the temperature distribution fluctuation curve, the air pressure balance state characteristics and the test chamber humidity parameters, so as to generate non-operating state time series characteristics.

[0008] By analyzing the infrared thermal imaging temperature monitoring data, the present invention can understand the heat distribution inside the test box, which is helpful to find potential thermal problems. Extracting the temperature distribution data of the test box can provide a basis for subsequent temperature control and adjustment. By performing fluctuation fitting on the temperature distribution data of the test box, the temperature fluctuation can be more clearly understood, providing a reference for stabilizing the temperature. The temperature distribution fluctuation curve helps to analyze the temperature change law and provide support for formulating temperature control strategies. Generating spatial pressure gradient characteristics can help understand the pressure distribution inside the test box and provide a basis for air pressure control. By calculating the pressure gradient, the change of air pressure can be evaluated to further improve the stability of the air pressure test box. By analyzing the characteristics of the air pressure balance state, the balance of air pressure inside the test box can be evaluated, providing a reference for the formulation of air pressure control strategies. Analysis of the characteristics of the air pressure balance state helps to find the situation of pressure imbalance, thereby improving the air pressure adjustment method of the air pressure test box. By generating non-operating state timing characteristics, the changes in parameters such as temperature, pressure and humidity can be comprehensively considered, providing a comprehensive reference for the stability control of the air pressure test box. The generation of non-operational state timing characteristics helps to build a more complete state model of the pressure chamber and improve the understanding and control of the chamber performance.

[0009] Preferably, step S2 specifically comprises the following steps: Step S21: Obtaining the internal structure diagram of the air pressure test chamber; Step S22: visually identifying the component structure of the internal structure diagram of the air pressure test box, and marking multiple internal component nodes of the test box; Step S23: performing spatial topological distribution analysis on multiple internal component nodes of the test chambers to generate internal component spatial topological distribution data; Step S24: performing geometric morphological feature recognition on the internal structure diagram of the air pressure test box to obtain the morphological features of the test box; Step S25: performing three-dimensional point cloud modeling on the morphological features of the test box based on the spatial topological distribution data of the internal components to generate a three-dimensional structural model of the test box; Step S26: Dynamically map the timing characteristics of the three-dimensional structure model of the test box according to the timing characteristics of the non-operating state to construct a digital twin model of the test box.

[0010] The present invention helps to gain a deep understanding of the composition and component distribution of the air pressure test box through the acquisition of the internal structure diagram, and provides basic data for subsequent analysis and control. Through component structure visual recognition and node marking, each component inside the test box can be accurately identified, and specific component location information can be provided for subsequent spatial analysis. Analyzing the spatial topological distribution of components helps to understand the relationship between components inside the test box, and provides a basis for building a three-dimensional structural model. Generating spatial topological distribution data can help optimize component layout and improve the performance and stability of the test box. Identifying the geometric morphological features of the test box can help understand the overall structure of the test box and provide important information for subsequent modeling. Obtaining morphological features helps to evaluate the association between the external morphology and the internal structure of the test box, and provides a reference for model construction. Three-dimensional point cloud modeling based on spatial topological distribution data can more intuitively present the internal structure of the test box, and provide visual support for subsequent model construction. Generating a three-dimensional structural model helps to more comprehensively understand the internal layout and component relationship of the test box. Through dynamic timing feature mapping, the timing features of the non-operating state can be combined with the three-dimensional structural model to establish a digital twin model of the test box. Building a digital twin model helps simulate the behavior of the test chamber under different working conditions and provides real-time simulation and prediction capabilities for pressure stability control.

[0011] Preferably, step S3 specifically comprises the following steps: Step S31: obtaining a target test scenario based on the test log; Step S32: performing target pressure state analysis on the target test scene and extracting target scene pressure state characteristics; Step S33: performing temperature change demand rate analysis on the target test scene, and extracting temperature change demand rate parameters of the target scene; Step S34: performing temperature spatiotemporal characteristic evolution on the temperature change demand rate parameter of the target scene to extract the temperature spatiotemporal change law of the target scene; Step S35: performing final test scene state mining on the target scene pressure state characteristics according to the temperature spatiotemporal variation law of the target scene to obtain final test scene state data.

[0012] The present invention can accurately record the environmental state and parameter changes during the test process by obtaining the target test scene through the test log, and provide a real data basis for subsequent analysis. Analyzing the pressure state of the target test scene helps to understand the target pressure requirements and provide a target reference for the pressure stability control of the test box. Extracting the pressure state characteristics can help establish a mathematical model of the target pressure state and provide support for the formulation of subsequent control strategies. Analyzing the temperature change demand rate of the target scene helps to understand the speed of temperature change and provide a reference for the formulation of temperature control strategies. Extracting the temperature change demand rate parameter can help quantify the requirements of the target scene for temperature change and provide guidance for subsequent control optimization. Analyzing the temperature spatiotemporal variation law of the target scene helps to understand the temperature variation pattern in space and time and provide a basis for the optimization of the temperature control strategy. Extracting the temperature spatiotemporal variation law can help establish a temperature evolution model of the target scene and provide support for achieving target temperature control. Through a comprehensive analysis of the temperature spatiotemporal variation law and pressure state characteristics of the target scene, the final test scene state data can be mined to provide a final basis for achieving the pressure stability control of the target scene. The acquisition of the final test scene state data helps to establish a comprehensive scene model and provides an important reference for the design and optimization of the control system.

[0013] Preferably, the specific steps of step S32 are: Calculating the spatial average pressure of the target test scene to obtain the spatial average pressure parameters of the target scene; Predicting the peak pressure of the scene based on the spatial average pressure parameter of the target scene to obtain the predicted peak pressure of the target scene; Perform pressure filling time series variation analysis on the target test scene to obtain the target scene pressure filling time series variation data; Perform pressure fluctuation amplitude analysis on the target scene pressure filling time series change data to generate the pressure fluctuation amplitude; Perform multi-period change pattern recognition on the pressure fluctuation amplitude to generate multi-period pressure change characteristics; Perform pressure stability assessment on the pressure variation characteristics in multiple time periods to obtain the pressure stability assessment value of the target scene; The target demand pressure state analysis is performed on the target scenario pressure prediction peak and the target scenario pressure stability assessment value to extract the target scenario pressure state characteristics.

[0014] The present invention helps to understand the overall pressure distribution by calculating the spatial average pressure parameters of the target test scene, and provides basic data for subsequent pressure control. Predicting the peak pressure of the target scene can help to pre-identify the extreme value of pressure changes and provide a reference for the formulation of pressure protection and control strategies. Analyzing the pressure filling timing changes of the target test scene helps to understand the pressure change trend over time and provide a basis for the formulation of pressure stability control strategies. Analyzing the pressure fluctuation amplitude of the target scene can quantify the degree of pressure fluctuation and provide an important indicator for evaluating pressure stability. Identifying the multi-period change pattern of pressure fluctuations helps to understand the law of pressure changes under different time scales and provide support for the formulation of targeted control strategies. Evaluating the pressure stability of the target scene can help judge the effectiveness and stability of pressure control and provide feedback and improvement direction for adjusting the control strategy. Extracting the pressure state characteristics of the target scene helps to deeply understand the target pressure requirements and scene characteristics, and provide a reference for optimizing pressure stability control.

[0015] Preferably, the specific steps of step S4 are: Step S41: performing a rapid air pressure filling simulation on the digital twin model of the test box, and collecting air pressure simulation response data of the test box; Step S42: identifying the air pressure spatial distribution state of the test box air pressure simulation response data to generate air pressure spatial distribution state characteristics; Step S43: performing state deviation analysis on the air pressure spatial distribution state characteristics based on the final test scene state data, thereby generating a target air pressure state deviation value; Step S44: performing a spatial air pressure stability compensation calculation on the target air pressure state deviation value to obtain a spatial air pressure stability compensation value.

[0016] The present invention can simulate the actual air pressure filling process by performing rapid air pressure filling simulation on the digital twin model of the test box, and provide a simulation data basis for subsequent analysis. Collecting the air pressure simulation response data of the test box is helpful to understand the air pressure response characteristics of the test box, and provide important data support for the pressure stability control of the air pressure test box. Identifying the spatial distribution state of the air pressure simulation response data of the test box is helpful to understand the distribution of air pressure in the test box, and provide a basis for the formulation of the pressure control strategy. Generating air pressure spatial distribution state characteristics can help quantify the characteristics of air pressure distribution, and provide a reference for subsequent pressure stability compensation calculations. Analyzing the state deviation of the air pressure spatial distribution state characteristics is helpful to understand the difference between the actual air pressure distribution and the target scene, and provide a basis for the adjustment of pressure stability control. Generating a target air pressure state deviation value can quantify the difference between the actual air pressure and the target air pressure, and provide a specific numerical basis for subsequent compensation calculations. Performing a spatial air pressure stability compensation calculation is helpful to formulate a compensation strategy according to the target air pressure state deviation value, and improve the pressure stability of the air pressure test box. Obtaining the spatial air pressure stability compensation value can help adjust the air pressure control parameters, so that the air pressure of the test box reaches the target value more stably, and improves the performance and reliability of the test box.

[0017] Preferably, the specific steps of step S5 are: Step S51: optimizing the air pressure balance of the air pressure space distribution state characteristics based on the spatial air pressure stability compensation value to obtain air pressure simulation balance optimization parameters; Step S52: operating the air pressure test box in real time according to the air pressure simulation balance optimization parameters, and collecting air pressure state parameters at multiple time points; Step S53: calculating the air pressure fluctuation amplitudes at adjacent points on the air pressure state parameters at multiple time points to obtain the air pressure fluctuation amplitudes between multiple time points; Step S54: Performing an operating state air pressure stability test based on the air pressure fluctuation amplitudes between multiple time points, thereby obtaining operating state air pressure stability data.

[0018] The present invention helps to adjust the air pressure distribution by optimizing the air pressure balance based on the spatial air pressure stability compensation value, so that the air pressure is more balanced and stable, and the air pressure control accuracy and stability of the test box are improved. In real-time operation, the air pressure test box can be operated according to the air pressure simulation balance optimization parameters to verify the air pressure balance optimization effect and ensure the air pressure stability in actual operation. Collecting the air pressure state parameters at multiple time points is helpful to understand the dynamic change trend of the air pressure and provide data support for subsequent analysis. Calculating the air pressure fluctuation amplitude of adjacent points can quantify the degree of change of the air pressure between different time points, help evaluate the air pressure stability and fluctuation, and provide a reference for stability control. Performing operating air pressure stability detection based on the air pressure fluctuation amplitude between multiple time points is helpful to monitor the air pressure stability in real time, discover abnormal air pressure fluctuations in time, and ensure that the test box works in a stable state. Obtaining the operating air pressure stability data can help evaluate the actual operating state of the air pressure test box, guide subsequent adjustments and optimizations, and ensure that the air pressure test box meets the expected pressure stability requirements.

[0019] Preferably, the specific steps of step S6 are: Step S61: performing air pressure stabilization delay error analysis on the running air pressure stabilization data to generate an air pressure stabilization delay error value; Step S62: performing error optimization based on the air pressure stabilization delay error value to generate error-optimized air pressure stabilization data; Step S63: performing secondary air pressure deviation calculation on the error-optimized air pressure stabilization data based on the final test scene state data to generate a secondary air pressure deviation parameter; Step S64: fine-tuning the dynamic air pressure deviation of the air pressure test box based on the secondary air pressure deviation parameter to generate a dynamic air pressure deviation fine-tuning strategy to execute the pressure stability control operation of the air pressure test box.

[0020] The present invention helps to identify the delay situation of air pressure stability by analyzing the delay error of the operating state air pressure stability data, and provides a basis for optimizing the control strategy. Generating an air pressure stability delay error value can quantify the degree of the delay error and help understand the difference between the actual air pressure response and the expected response. Error optimization based on the air pressure stability delay error value helps to improve the stability of the air pressure test box, reduce the impact of the error on the air pressure control, and improve the control accuracy. Generating error-optimized air pressure stability data can optimize the air pressure control algorithm, so that the air pressure response of the air pressure test box is more stable and accurate. Calculating the secondary air pressure deviation based on the error-optimized air pressure stability data helps to further adjust the air pressure control parameters of the air pressure test box and improve the air pressure stability. Generating the secondary air pressure deviation parameter can quantify the difference between the actual air pressure of the air pressure test box and the expected air pressure, and provide a basis for further fine-tuning. Fine-tuning the dynamic air pressure deviation based on the secondary air pressure deviation parameter helps to dynamically adjust the air pressure control strategy according to the actual situation, and ensure the stability of the air pressure test box under different working conditions. Generating a dynamic air pressure deviation fine-tuning strategy can guide the real-time control of the air pressure test chamber, so that the air pressure stability can be continuously optimized and improved, and the performance and reliability of the test chamber can be improved.

[0021] In this specification, a pressure stability control system for an air pressure test chamber is provided, which is used to execute the pressure stability control method for an air pressure test chamber as described above, and includes: A non-operating state module is used to obtain multi-dimensional non-operating state monitoring parameters of the air pressure test box; perform non-operating state time series evolution of the multi-dimensional non-operating state monitoring parameters, thereby generating non-operating state time series features; The spatial topology module is used to obtain the internal structure diagram of the air pressure test chamber; based on the timing characteristics of the non-operating state, the spatial topology distribution analysis of the internal structure diagram of the air pressure test chamber is performed to build a digital twin model of the test chamber; The test scenario module is used to obtain the target test scenario based on the test log; perform target pressure state analysis on the target test scenario to obtain the final test scenario state data; The air pressure stability compensation module is used to perform space air pressure stability compensation calculation on the digital twin model of the test box according to the final test scene state data to obtain the space air pressure stability compensation value; The operating state module is used to perform operating state air pressure stability detection on the air pressure test box based on the space air pressure stability compensation value, so as to obtain operating state air pressure stability data; The dynamic air pressure fine-tuning module is used to perform dynamic air pressure deviation fine-tuning on the operating air pressure stability data to generate a dynamic air pressure deviation fine-tuning strategy to perform pressure stability control operations in the air pressure test chamber.

[0022] The present invention helps to understand the state changes of the test box in the shutdown state by monitoring the multi-dimensional non-operating state parameters of the air pressure test box, and provides basic data for subsequent stability control. Generating non-operating state time series characteristics can reveal the characteristic changes of the air pressure test box in different non-operating states, and provide a basis for subsequent analysis and optimization. Acquiring the internal structure diagram of the air pressure test box is helpful to understand the spatial layout and structural characteristics of the test box, and provides basic data for subsequent spatial analysis. Spatial topological distribution analysis and three-dimensional point cloud modeling based on non-operating state time series characteristics can construct a digital twin model of the test box, and provide a basis for subsequent simulation and optimization. Analyzing the pressure state of the target test scene is helpful to understand the working state of the test box in different scenes, and provides a reference for subsequent pressure control. Mining the final test scene state data can provide support for determining the final test conditions and pressure requirements, and provide a basis for subsequent control strategies. The air pressure test box can provide a basis for the formulation of the test strategy. The rapid air pressure filling simulation and calculation of the space air pressure stability compensation value are helpful to optimize the air pressure distribution and improve the air pressure stability of the air pressure test box. The compensation calculation based on the final test scene state data can adjust the air pressure parameters according to actual needs to ensure the stability of the test box in different scenarios. Real-time operation and air pressure stability detection are helpful to verify the stability of the air pressure test box, and timely discover and deal with abnormal air pressure fluctuations. The operating air pressure stability data can provide real-time feedback for adjusting the control strategy and parameters to ensure the stability of the test box during operation. Delay error analysis and dynamic air pressure deviation fine-tuning of the operating air pressure stability data are helpful to optimize the air pressure control strategy, improve air pressure stability and control accuracy, and generate a dynamic air pressure deviation fine-tuning strategy to achieve fine control of the pressure stability of the air pressure test box, ensuring the stability and reliability of the test box under various working conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A schematic flow chart of the steps of a method for controlling pressure stability of an air pressure test chamber according to 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

[0024] 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.

[0025] The present application example provides a pressure stability control method and system for a pressure test chamber. The execution subject of the pressure stability control method and system for a pressure test chamber includes but is not limited to: mechanical equipment, data processing platform, cloud server node, network upload device, etc. equipped with the system can be regarded as a general computing node of the present application, and the data processing platform includes but is not limited to: at least one of an audio and image management system, an information management system, and a cloud data management system.

[0026] See also Figures 1 to 4 The present invention provides a pressure stability control method for an air pressure test box, the pressure stability control method for an air pressure test box comprising the following steps: Step S1: obtaining multi-dimensional non-operating state monitoring parameters of the air pressure test box; performing non-operating state time series evolution of the multi-dimensional non-operating state monitoring parameters, thereby generating non-operating state time series features; Step S2: obtaining an internal structure diagram of the air pressure test box; performing a spatial topological distribution analysis on the internal structure diagram of the air pressure test box based on the timing characteristics of the non-operating state, and constructing a digital twin model of the test box; Step S3: acquiring a target test scenario based on the test log; performing a target pressure state analysis on the target test scenario to obtain final test scenario state data; Step S4: performing spatial air pressure stability compensation calculation on the digital twin model of the test box according to the final test scene state data to obtain a spatial air pressure stability compensation value; Step S5: performing an operating state air pressure stability test on the air pressure test box based on the space air pressure stability compensation value, thereby obtaining operating state air pressure stability data; Step S6: fine-tuning the dynamic air pressure deviation on the operating air pressure stability data to generate a dynamic air pressure deviation fine-tuning strategy to execute the air pressure test chamber pressure stability control operation.

[0027] The present invention can timely discover potential problems and improve safety by monitoring the non-operating state of the air pressure test box. Generating non-operating state time series characteristics is helpful to understand the characteristic changes of the air pressure test box in different states, providing a basis for subsequent analysis. Constructing a digital twin model of the test box can realize virtual modeling of the internal structure of the air pressure test box, which helps to understand the structure and layout inside the box. Through three-dimensional point cloud modeling, the spatial topological distribution of the test box can be more intuitively presented, providing visualization support for subsequent simulation and analysis. Analyzing the state of the target test scene is helpful to understand the pressure state that needs to be achieved in the test and guide the subsequent experimental process. By mining the final test scene state data, the experimental process and results can be optimized, the test efficiency and quality can be improved, and the air pressure Filling simulation and stability compensation calculation help predict the air pressure response of the air pressure test chamber and ensure the safety and accuracy of the test. The air pressure control of the air pressure test chamber can be optimized through the spatial air pressure stability compensation value, and the air pressure stability and experimental reliability can be improved. Real-time monitoring of the operating air pressure stability data helps to ensure the stability and accuracy of the air pressure during the test. The operating air pressure stability data can be used to adjust the air pressure control in time to ensure that the test chamber operates within the normal range. Through air pressure stability delay error analysis and dynamic air pressure deviation fine-tuning, the pressure stability of the air pressure test chamber can be optimized, the controllability and accuracy of the test can be improved, and the generation of dynamic air pressure deviation fine-tuning strategy helps to achieve stability control of the air pressure test chamber and ensure the accuracy and reliability of experimental data.

[0028] In the embodiment of the present invention, refer to Figure 1 , is a schematic flow chart of the steps of a pressure stability control method of a pressure test chamber of the present invention. In this example, the steps of the pressure stability control method of the pressure test chamber include: Step S1: monitoring the current non-operating state of the air pressure test box, thereby obtaining multi-dimensional non-operating state monitoring parameters of the air pressure test box; performing non-operating state time series evolution of the multi-dimensional non-operating state monitoring parameters, thereby generating non-operating state time series features; In this embodiment, the monitoring target is determined mainly to obtain various parameters of the pressure test box in the non-operating state, such as ambient temperature, humidity, air pressure, equipment status, vibration, etc. These parameters will be used to understand the stability and potential problems of the equipment in the closed state. Configure a variety of sensors to collect the required non-operating state monitoring parameters: Pressure sensor: monitor the air pressure inside the test box. Temperature and humidity sensor: monitor ambient temperature and humidity. When the pressure test box is in a non-operating state, start the monitoring system and start collecting data of various parameters in real time. Set a suitable data collection frequency (such as every second, every minute) to ensure that sufficient data is obtained to analyze the non-operating state. Save the collected multi-dimensional non-operating state monitoring parameters to a database or local storage device to ensure data integrity and traceability. Select a suitable time series analysis method (such as moving average, exponential smoothing, Fourier transform, etc.) to analyze the changing trend of various parameters in the non-operating state. Summarize the calculated statistical features to form a comprehensive non-operating state time series feature data set. The data set may include timestamps, mean values, standard deviations, maximum values, minimum values, etc. of various parameters. Save the non-operating state time series characteristics to the database and generate a report to record the monitoring results and analysis conclusions for subsequent reference and decision-making. Use data visualization tools (such as Matplotlib, Tableau, or PowerBI) to visualize the non-operating state monitoring parameters and their time series characteristics. Draw a chart of the parameter changes over time to facilitate analysis and understanding of the evolution trend of each monitoring parameter in the non-operating state.

[0029] Step S2: obtaining an internal structure diagram of the air pressure test box; performing spatial topological distribution analysis on the internal structure diagram of the air pressure test box based on the timing characteristics of the non-operating state, and performing three-dimensional point cloud modeling to construct a digital twin model of the test box; In this embodiment, the goal of spatial topological analysis is determined, such as identifying the spatial relationship, functional area division and mutual influence of each component inside the air pressure test box, selecting a suitable topological analysis method, such as graph theory, Voronoi diagram or Delaunay triangulation, which is helpful to understand the relationship between the spatial structure and components, exporting the three-dimensional model into a format suitable for analysis (such as STL or OBJ), and preparing relevant non-operating state time series characteristic data (such as temperature, pressure distribution, etc.), using analysis software (such as MATLAB, Python's SciPy library, Blender or MeshLab) to perform topological analysis on the three-dimensional model, calculate the spatial relationship and interaction between each component, use point cloud processing software (such as Cloud Compare, PCL library) to clean and process the collected point cloud data, remove noise and unnecessary data points, and use point cloud reconstruction algorithms (such as Poisson Surface Reconstruction or Alpha Shapes) converts the cleaned point cloud data into a 3D surface model, optimizes the generated 3D model, reduces the number of redundant faces, and improves rendering efficiency. Modeling software (such as Blender or MeshLab) can be used for post-processing to integrate the 3D internal structure model with the point cloud model to ensure data consistency and integrity between the two. Select a suitable digital twin platform (such as Siemens Mind Sphere, PTC Thing Worx or other industrial IoT platforms) to build and deploy the digital twin model, upload the integrated 3D model to the digital twin platform, and configure relevant parameters (such as sensor data stream, real-time monitoring indicators, etc.), connect the real-time monitoring data to the digital twin model through API or data communication protocol, ensure that the model can reflect the actual operating status of the equipment, verify the digital twin model to ensure that it accurately reflects the physical characteristics and behavior of the air pressure test box, and adjust and optimize it when necessary to improve the accuracy and practicality of the model.

[0030] Step S3: acquiring a target test scenario based on the test log; performing a target pressure state analysis on the target test scenario, and performing final test scenario state mining to obtain final test scenario state data; In this embodiment, the source of the test log is determined, which usually includes the control system of the test box, sensor records, manual input by the user, and any automatically generated log files. The collected test logs are organized into a unified format (such as CSV or JSON), ensuring that each record contains key information such as timestamp, test type, target pressure, actual pressure, environmental parameters, etc. According to the test log, the definition of the target test scene is determined. The target test scene usually includes set pressure values, temperature, humidity and other parameters, as well as corresponding operating conditions. Use data analysis tools (such as Pandas, R or SQL) to filter out records related to the target test scene from the test log. Conditions can be set, such as: selecting test records within a specific time period. Filter data according to the set target pressure range. Aggregate the filtered data to form a data set for the target test scene, including all relevant parameters and status information. Select a suitable analysis method, such as statistical analysis, regression analysis, time series analysis, etc., to evaluate the stability and change trend of the target pressure state. Analyze the pressure data in the target test scene and extract the following features: Mean: the average value of the target pressure. Standard deviation: an indicator reflecting the degree of pressure fluctuation. Maximum and minimum values: indicators of the pressure range. Select appropriate data mining tools and algorithms (such as K-means clustering, decision trees, or neural networks) to mine the final test scenario status. Perform feature selection and processing on the target test scenario data to ensure that the data input into the data mining model can effectively reflect the state of the test scenario. Use historical data to train the selected data mining model and validate the model to ensure its accuracy and reliability. Methods such as cross-validation can be used to evaluate model performance.

[0031] Step S4: Perform a rapid air pressure filling simulation on the digital twin model of the test box, and collect the test box air pressure simulation response data; perform a spatial air pressure stability compensation calculation on the test box air pressure simulation response data according to the final test scene state data to obtain a spatial air pressure stability compensation value; In this embodiment, according to the final test scene state data, the initial conditions and boundary conditions of the air pressure filling are set, including the target pressure, environmental conditions (such as temperature, humidity) and filling rate. Select a suitable air pressure filling simulation algorithm. Common methods include: Finite element analysis (FEA): suitable for complex airflow dynamic simulation. Computational fluid dynamics (CFD): used to simulate the flow and pressure distribution of gas inside the test box. Start the air pressure filling simulation and monitor the change process of air pressure inside the test box. Record the air pressure response data at each moment during the simulation. During the simulation, the air pressure response data is recorded in real time, including the air pressure value of each measuring point and its change trend. Ensure that the data storage format is unified (such as CSV, JSON). Use data analysis tools (such as Pandas or MATLAB) to perform preliminary analysis on the collected air pressure response data and identify key response characteristics (such as peak value, steady-state value, response time). Select a suitable compensation calculation method. Linear or nonlinear compensation algorithms can be used, for example: PID control algorithm: used to dynamically adjust air pressure. Kalman filter: used to estimate and compensate for system uncertainty. Prepare the final test scene state data and air pressure simulation response data to ensure that the data format is consistent for easy calculation. According to the selected compensation algorithm, the spatial air pressure stability compensation calculation is performed on the air pressure simulation response data. The calculated spatial air pressure stability compensation value is recorded in the database to form a compensation value data set for subsequent analysis and application.

[0032] Step S5: operating the air pressure test box in real time based on the space air pressure stability compensation value, and performing an air pressure stability test in an operating state, thereby obtaining air pressure stability data in an operating state; In this embodiment, the operating program of the air pressure test box is started to ensure that the system enters the real-time monitoring mode. At this time, the control system will dynamically adjust the air pressure according to the set target air pressure and compensation value, and use the sensor to monitor the air pressure state in real time. The air pressure sensor will continuously feedback the current air pressure value. The system should be able to update and display these data in real time. During the operation of the test box, the operating air pressure data is regularly collected, including the pressure value of each measuring point and related environmental parameters (such as temperature and humidity). According to the experimental requirements, a suitable sampling frequency is set, such as collecting data once per second or once per minute, so as to obtain enough samples for subsequent analysis. The collected air pressure data is imported into the data analysis software (such as Python, MATLAB or Excel) and organized into a structured data format. formula, which is convenient for subsequent analysis. Selection of stability detection indicators: Select appropriate stability detection indicators, such as: mean: reflects the average value of air pressure, standard deviation: reflects the degree of fluctuation of air pressure, maximum and minimum values: reflect the range of change of air pressure, Fast Fourier Transform (FFT): used for frequency domain analysis to identify possible periodic fluctuations, perform stability calculations on operating air pressure data, and use statistical methods to evaluate the stability of air pressure. If the standard deviation exceeds the preset threshold, further analysis of the cause may be required. The operating air pressure stability data and analysis results are stored in the database to ensure the integrity and traceability of the data. Based on the results of the stability test, a detailed analysis report is generated to record the operating air pressure stability data and its characteristics, including the mean, standard deviation, fluctuations, etc.

[0033] Step S6: performing air pressure stabilization delay error analysis on the operating air pressure stabilization data, and performing dynamic air pressure deviation fine-tuning to generate a dynamic air pressure deviation fine-tuning strategy to execute the air pressure test chamber pressure stability control operation.

[0034] In this embodiment, after the air pressure test box reaches a stable operating state, the pressure data sequence is continuously collected to ensure that the data collection frequency is high enough to reflect the dynamic characteristics of pressure changes. The collected pressure data sequence is subjected to time series analysis, the deviation between the pressure value and the expected pressure value is calculated, the variation trend of the deviation over time is analyzed, and the delay error characteristics under the stable state are identified. Based on the above delay error analysis results, a dynamic model of the pressure deviation is established. Time series analysis methods such as the autoregressive moving average (ARIMA) model can be used. The model can describe the dynamic characteristics of the pressure deviation over time. Using the dynamic deviation model, a feedback control strategy is designed to fine-tune the pressure. Control algorithms such as PID and ModelPredictiveControl can be used. Optimize the control parameters so that the pressure can quickly converge to the expected value. Apply the above optimized control strategy to the real-time pressure control of the air pressure test chamber, continuously monitor the pressure data, and perform dynamic deviation fine-tuning in real time to ensure that the pressure is stable near the expected value and meet the test requirements.

[0035] 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: monitoring the current non-operating state of the air pressure test box, thereby obtaining multi-dimensional non-operating state monitoring parameters of the air pressure test box, wherein the multi-dimensional non-operating state monitoring parameters include infrared thermal imaging temperature monitoring data, test box air pressure state parameters and test box humidity parameters; Step S12: performing heat distribution analysis of the test chamber on the infrared thermal imaging temperature monitoring data, and extracting the temperature distribution data of the test chamber; Step S13: performing temperature distribution fluctuation fitting on the temperature distribution data of the test chamber to obtain a temperature distribution fluctuation curve; Step S14: performing spatial pressure gradient calculation on the test chamber air pressure state parameters to generate spatial pressure gradient characteristics; Step S15: analyzing the characteristics of the air pressure balance state of the test box based on the spatial pressure gradient characteristics to obtain the characteristics of the air pressure balance state; Step S16: Perform non-operating state time series evolution on the temperature distribution fluctuation curve, the air pressure balance state characteristics and the test chamber humidity parameters, so as to generate non-operating state time series characteristics.

[0036] In this embodiment, an infrared thermal imager is installed in the air pressure test box to monitor the temperature distribution in the test box in real time, a high-precision air pressure sensor is installed to continuously monitor the air pressure changes in the test box, and a humidity sensor is installed to obtain humidity data in the test box. When the test box is not in operation, all sensors are started and a data acquisition system is configured to regularly record various parameters. The recorded data includes temperature data from infrared thermal imaging, readings from air pressure sensors, and outputs from humidity sensors. These data will be stored in a database of the data acquisition system for subsequent analysis. During the monitoring process, the sensors are ensured to work normally, and are regularly calibrated to maintain data accuracy. Through data monitoring, reliable basic data can be provided for subsequent analysis. The temperature data obtained by the imager is organized into a two-dimensional matrix to represent the temperature at different points inside the test chamber, ensuring data integrity, handling missing values ​​and outliers, and using thermal imaging analysis software to analyze the temperature data. The temperature distribution inside the test chamber is displayed through a heat map, and hot spots and cold areas in the temperature distribution are identified to evaluate the heat distribution of the equipment when it is not in operation. Based on the temperature distribution results, the uniformity of heat and possible heat accumulation problems are analyzed to provide suggestions for the design and use of the test chamber. By performing a time series analysis on the temperature data, the temperature changes over time are calculated, and significant fluctuation patterns are identified. Statistical methods (such as polynomial fitting or spline interpolation) are used to fit the temperature fluctuations, generate a fluctuation curve of the temperature distribution, and evaluate the fit. The accuracy and applicability of the curve are ensured to reflect the actual temperature change trend. The data of the air pressure sensor is organized into a format suitable for analysis, usually including a timestamp and the corresponding pressure value. The air pressure values ​​at different locations in the test chamber are calculated. The air pressure distribution is analyzed and the spatial pressure gradient is calculated. This can be achieved by comparing the air pressure readings at different locations. The trend of pressure change can be identified. By drawing a pressure distribution diagram, the spatial change of pressure can be more clearly seen. The pressure gradient obtained by analysis can be used to evaluate the sealing and air pressure control capabilities of the test chamber to ensure its safety and stability under operation. By analyzing the air pressure gradient data, it is determined whether the air pressure is in a balanced state. Usually, the characteristics of the air pressure balance state can be obtained by comparing the pressure mean and the standard The pressure difference is used for evaluation. If the pressure change is small and uniform, the air pressure can be considered to be in a balanced state. A threshold is defined to analyze the air pressure stability. If the standard deviation is lower than this value, the air pressure is considered to be in a balanced state. This analysis helps to understand the air pressure stability of the test chamber when it is not in operation. According to the analysis results of the air pressure balance state characteristics, corresponding maintenance strategies are formulated to ensure the safety and stability of the test chamber during operation. The temperature distribution fluctuation curve, air pressure balance state characteristics and humidity parameters are comprehensively integrated to form a complete time series data set to ensure that these data can be correlated with each other for subsequent analysis. The time series analysis method is used to evaluate the change trend of different parameters over time in the non-operating state. This can be achieved by observing the change chart of each parameter.To identify potential trends and periodic changes, the analysis results can reveal the performance changes of the test chamber under different environmental conditions and provide data support for optimized design and maintenance.

[0037] 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: Obtaining the internal structure diagram of the air pressure test chamber; Step S22: visually identifying the component structure of the internal structure diagram of the air pressure test box, and marking multiple internal component nodes of the test box; Step S23: performing spatial topological distribution analysis on multiple internal component nodes of the test chambers to generate internal component spatial topological distribution data; Step S24: performing geometric morphological feature recognition on the internal structure diagram of the air pressure test box to obtain the morphological features of the test box; Step S25: performing three-dimensional point cloud modeling on the morphological features of the test box based on the spatial topological distribution data of the internal components to generate a three-dimensional structural model of the test box; Step S26: Dynamically map the timing characteristics of the three-dimensional structure model of the test box according to the timing characteristics of the non-operating state to construct a digital twin model of the test box.

[0038] In this embodiment, obtain the internal structure diagram of the air pressure test box from the design department, engineers or related documents to ensure that the drawing accurately shows the position and connection relationship of all internal components. This can be a CAD file, PDF file or scanned drawing. Check the format of the drawing to ensure that it can be recognized by subsequent image processing or CAD software. If necessary, convert the drawing into a suitable format (such as DWG or JPG). Clean and optimize the drawing to remove any unnecessary marks or noise to improve the accuracy of subsequent processing. Select appropriate image processing software, such as OpenCV, MATLAB or CAD software, for visual recognition. Use edge detection algorithms (such as Canny edge detection) to identify edges in the image. This step It will help to distinguish the boundaries of each component. Use template matching technology to identify specific components. You can use pre-trained machine learning models to identify components of specific shapes or labels, mark the identified components, record the coordinates and type of each component node, and form a data set containing all component information. The data set should include the component ID, type, coordinate position, etc. Organize the marked component nodes into a structured data format, including node ID, coordinate position (x, y, z) and component type, select a suitable topology analysis tool or library (such as NetworkX or MATLAB) for spatial topology analysis, and use spatial distance and connection relationship algorithms (such as Delaunay triangulation) to analyze the spatial relationship between components. The generated topological map should be able to reflect the connectivity and relative positions between components. Output the topological distribution data to form a topological map, which includes the connection information of each component node. Use CAD software (such as AutoCAD, SolidWorks) or geometric analysis library (such as OpenSCAD) to extract geometric features. Extract the outer contour of the air pressure test box and the geometric features of the internal components from the internal structure diagram, identify the main geometric shapes, such as rectangles, cylinders, pipes, etc., record the geometric parameters of each component, including length, width, height, diameter, curvature, etc., to form a geometric feature data set, use point cloud processing software (such as PCL, Blender or Rhino) to prepare for 3D modeling, and extract the geometric features of the external contour and internal components of the air pressure test box from the internal structure diagram. The three-dimensional coordinates of each node correspond to the position of the component to form a complete three-dimensional structure. The generated point cloud is optimized to remove redundant points and noise to ensure the accuracy and quality of the model. The three-dimensional structural model of the test box is constructed using the point cloud data to ensure that the model accurately reflects the design intent. The generated non-operating state timing characteristics (such as temperature, humidity, air pressure, etc.) are integrated into a data set to ensure the integrity of the data. A suitable dynamic mapping tool (such as Unity, UnrealEngine or dedicated visualization software) is selected to map the timing characteristics to the three-dimensional model. The integrated timing characteristic data is applied to the three-dimensional model to generate a digital twin model. The model should be able to reflect the changes in timing characteristics in real time.For example, the temperature and humidity changes in different time periods can verify the accuracy of the digital twin model to ensure that it can effectively reflect the state changes of the pressure test chamber. The digital twin model can be displayed using visualization tools to facilitate analysis and decision support. An interactive interface can be created to allow users to view and analyze the state and dynamic changes of the test chamber in real time.

[0039] In this embodiment, refer to Figure 4 , is a flowchart of detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include: Step S31: obtaining a target test scenario based on the test log; Step S32: performing target pressure state analysis on the target test scene and extracting target scene pressure state characteristics; Step S33: performing temperature change demand rate analysis on the target test scene, and extracting temperature change demand rate parameters of the target scene; Step S34: performing temperature spatiotemporal characteristic evolution on the temperature change demand rate parameter of the target scene to extract the temperature spatiotemporal change law of the target scene; Step S35: performing final test scene state mining on the target scene pressure state characteristics according to the temperature spatiotemporal variation law of the target scene to obtain final test scene state data.

[0040] In this embodiment, the source of the test log is confirmed, which usually includes an experimental record database, a test management system or a real-time monitoring system, and it is ensured that all logs are the latest and complete versions. The relevant test logs are extracted from the database using SQL query or data extraction tools, which should include fields such as timestamp, test type, environmental conditions (temperature, humidity, etc.), set pressure, real-time records, etc. The extracted log data is converted into a unified format (such as CSV or JSON) to ensure that the data structure is consistent and convenient for subsequent analysis. Missing values ​​or outliers in the data are checked, and they are filled, deleted or retained as appropriate. The mean filling method or interpolation method can be used to process missing data. According to the test requirements, screening conditions are set, such as a specific pressure range, temperature conditions, and test type (such as startup, shutdown), and records that meet the conditions are screened to extract relevant parameters of the target scenario to form a data set of the target test scenario. The records should include key information such as pressure, temperature, humidity, and test number. The data set related to the target test scenario is extracted from the data set. All pressure-related data, including timestamps, set pressures, and real-time pressures, are processed and analyzed using data analysis tools, such as the Pandas library in Python, R language, or MATLAB. Descriptive statistical indicators of the target scenario pressure data are calculated, including: mean: represents the central trend of pressure, standard deviation: reflects the degree of pressure fluctuation, maximum and minimum values: identify extreme values ​​of pressure, peak and valley values: identify peaks and valleys of pressure changes, and by drawing a trend graph of pressure changes over time, identify the change patterns of pressure states, such as stability, volatility, and anomalies, and record key features. Extract temperature data from the target test scenario, ensure that the timestamps of the temperature data are aligned with the pressure data for synchronous analysis, and select an appropriate calculation method, such as the difference method, to calculate the temperature change demand rate. For consecutive time points t and t+1, calculate the temperature difference: ΔT=T(t+1)−T(t), calculate the time interval: Δt=t+1−t, and calculate the temperature change rate: temperature change rate = , record the temperature change rate at each time point, extract the main features, such as the highest rate, the lowest rate and the average rate, combine the temperature change rate data with the time and space parameters to form a spatiotemporal data set. The data set should contain the timestamp, spatial location (such as sensor location) and the corresponding temperature change rate. Select appropriate spatiotemporal analysis methods, such as time series analysis (ARIMA model), spatial interpolation (Kriging interpolation), etc., analyze the evolution law of the temperature change demand rate, identify the evolution law of the temperature change rate under different time and space conditions, and extract key spatiotemporal features, such as periodic changes, significant fluctuations, etc. You can use visualization tools (such as Matplotlib, Seaborn) to display the results for easy understanding. The pressure in step S32 The state characteristics (such as stability and volatility) are integrated with the spatiotemporal variation law of temperature extracted in step S34 to form a comprehensive data set, which should include pressure characteristics, temperature change rate, timestamp and other relevant parameters. An appropriate data mining algorithm (such as cluster analysis, association rule learning, decision tree or random forest) is selected to analyze the comprehensive data set, identify potential patterns and relationships, and apply the selected mining algorithm to perform data analysis to reveal the final state characteristics of the target scenario. For example, the relationship between the temperature change rate and the pressure state is analyzed, and the pressure change pattern under specific conditions is identified. The final test scenario state data is generated, including key state parameters and feature descriptions. The results are recorded in a database, and an analysis report is generated to support subsequent decision-making and optimization.

[0041] In this embodiment, the specific steps of step S32 are: Calculating the spatial average pressure of the target test scene to obtain the spatial average pressure parameters of the target scene; Predicting the peak pressure of the scene based on the spatial average pressure parameter of the target scene to obtain the predicted peak pressure of the target scene; Perform pressure filling time series variation analysis on the target test scene to obtain the target scene pressure filling time series variation data; Perform pressure fluctuation amplitude analysis on the target scene pressure filling time series change data to generate the pressure fluctuation amplitude; Perform multi-period change pattern recognition on the pressure fluctuation amplitude to generate multi-period pressure change characteristics; Perform pressure stability assessment on the pressure variation characteristics in multiple time periods to obtain the pressure stability assessment value of the target scene; The target demand pressure state analysis is performed on the target scenario pressure prediction peak and the target scenario pressure stability assessment value to extract the target scenario pressure state characteristics.

[0042] In this embodiment, all relevant pressure sensor data are extracted from the target test scene, including the real-time pressure value of each sensor and its corresponding spatial position (such as coordinates), and the spatial average pressure is calculated using a statistical method. Code (such as Python using the NumPy library) is written to calculate the average pressure values ​​of all sensors and the results are recorded. The spatial average pressure data is organized into a time series format for predictive analysis. Time series prediction methods such as ARIMA, SARIMA or LSTM (Long Short-Term Memory Network) can be used to input the time series data into a selected model for training, and historical data is used to predict future pressure peaks. The prediction results are recorded, the predicted pressure peaks are extracted, and the relevant confidence intervals are output to ensure the integrity of the pressure data. Interpolation methods (such as linear interpolation or spline interpolation) are used to fill in missing pressure values ​​to form continuous pressure time series data. Trend analysis methods (such as moving average, exponential smoothing) are used to identify the time series change trend of pressure. A chart of pressure changes over time can be drawn to intuitively display data changes. The analysis results are recorded in a database to generate a pressure-filled time series change data set, and the pressure fluctuation amplitude (such as maximum and minimum) is calculated. The difference in values ​​is as follows: A=Pmax−Pmin. Statistical analysis tools are used to calculate the fluctuation amplitude in the pressure filling time series data and record the results. The pressure data is divided into multiple time periods (such as hours, days or weeks) by time to prepare for subsequent analysis. Cluster analysis (such as K-means clustering) or pattern recognition algorithms (such as dynamic time warping DTW) are used to identify the changing pattern of pressure fluctuations. The pressure fluctuation amplitude of each time period is analyzed to identify similar fluctuation patterns and generate a multi-time period pressure change feature report. Stability assessment indicators such as standard deviation and coefficient of variation (CV) are defined to reflect the stability of pressure. The pressure fluctuation amplitude data calculated previously is used to calculate the stability index of each time period. The assessment values ​​are recorded in the database to form a pressure stability assessment report for subsequent analysis. The pressure prediction peak in step 2 is integrated with the pressure stability assessment value in step 6 to form a comprehensive data set. Appropriate analysis methods (such as decision trees and regression analysis) are selected to evaluate the target demand pressure state. The selected analysis methods are applied to conduct in-depth analysis of the integrated data to extract the pressure state characteristics of the target scenario, including the recommended pressure setting range, potential safety risks, etc.

[0043] In this embodiment, step S4 includes the following steps: Step S41: performing a rapid air pressure filling simulation on the digital twin model of the test box, and collecting air pressure simulation response data of the test box; Step S42: identifying the air pressure spatial distribution state of the test box air pressure simulation response data to generate air pressure spatial distribution state characteristics; Step S43: performing state deviation analysis on the air pressure spatial distribution state characteristics based on the final test scene state data, thereby generating a target air pressure state deviation value; Step S44: performing a spatial air pressure stability compensation calculation on the target air pressure state deviation value to obtain a spatial air pressure stability compensation value.

[0044] In this embodiment, computational fluid dynamics (CFD) software (such as ANSYS Fluent or OpenFOAM) is used to build a digital twin model of the test box to ensure that the model can accurately reflect the geometric structure and air pressure conditions of the test box, configure model parameters, including gas type, initial air pressure, temperature, and boundary conditions, to ensure that the simulation environment is consistent with the actual test conditions, run an air pressure filling simulation, and observe the change process of the air pressure in the test box. During the simulation, dynamic grid or time step control can be used to improve the calculation efficiency. During the simulation, the air pressure response data of each point in the test box is collected in real time, including the time series of pressure changes. The collected air pressure simulation response data is formatted and saved in an appropriate file format (such as CSV or HDF5) for subsequent processing and analysis. The collected air pressure response data is denoised to remove outliers and noise to ensure data quality. An interpolation method (such as Kriging interpolation or inverse distance weighted method) is used to convert the discrete air pressure data into a continuous air pressure spatial distribution map to generate a gas pressure data map. The characteristic diagram of the spatial distribution state of air pressure, including the high and low points, uniformity and gradient changes of the air pressure distribution, etc., is displayed graphically by using visualization tools (such as Matplotlib or ParaView) to facilitate intuitive understanding and analysis of the air pressure distribution characteristics. The state data of the final test scene is collected and integrated, including the actually measured air pressure values ​​and the air pressure spatial distribution state characteristics generated by simulation. The deviation values ​​are statistically analyzed, and the average deviation, standard deviation and maximum deviation are calculated to evaluate the accuracy of the air pressure distribution. The calculated air pressure state deviation values ​​are recorded in the database, and relevant reports are generated for subsequent analysis. The air pressure state deviation is calculated by using a compensation algorithm (such as PID control or model predictive control MPC) to achieve stable compensation of the air pressure. According to the calculated air pressure deviation value, the stable compensation calculation of the air pressure is performed, the results of the compensation calculation are recorded, and a data set of stable compensation values ​​of the air pressure is formed. By comparing the air pressure states before and after compensation, the effect of compensation is evaluated to ensure that the target air pressure state meets the expected stability requirements.

[0045] In this embodiment, step S5 includes the following steps: Step S51: optimizing the air pressure balance of the air pressure space distribution state characteristics based on the spatial air pressure stability compensation value to obtain air pressure simulation balance optimization parameters; Step S52: operating the air pressure test box in real time according to the air pressure simulation balance optimization parameters, and collecting air pressure state parameters at multiple time points; Step S53: calculating the air pressure fluctuation amplitudes at adjacent points on the air pressure state parameters at multiple time points to obtain the air pressure fluctuation amplitudes between multiple time points; Step S54: Performing an operating state air pressure stability test based on the air pressure fluctuation amplitudes between multiple time points, thereby obtaining operating state air pressure stability data.

[0046] In this embodiment, the pressure stability compensation value calculated in step S44 is collected and combined with the characteristics of the pressure spatial distribution state (such as pressure distribution diagram, uniformity index, etc.) to prepare for the optimization of pressure balance. According to the characteristics of the pressure distribution, a suitable optimization algorithm is selected, such as genetic algorithm, particle swarm optimization or simulated annealing. The goal is to optimize the pressure distribution to make it more uniform and reduce fluctuations. Define the optimization objective function, which can be the uniformity or fluctuation amplitude of the pressure distribution, input the pressure stability compensation value and the current pressure distribution characteristics, run the selected optimization algorithm, and calculate the optimized pressure simulation balance parameters. This process may require multiple iterations to ensure that the best results are achieved. The optimized pressure simulation balance parameters (such as setting pressure targets, adjustment strategies, etc.) are recorded in the database for subsequent use and verification. According to the pressure simulation balance optimization parameters obtained in step S51, the control system of the test box (such as PLC, SCADA system) is configured to ensure that it can respond and adjust the air pressure in real time. Start the air pressure system of the test box for real-time air pressure regulation. The system needs to automatically adjust the air pressure according to the optimization parameters to ensure that the air pressure during operation meets the preset target. Set the sampling frequency (such as every second, every minute) according to the experimental requirements, and collect air pressure state parameters at multiple time points. The monitoring system should record the air pressure value, timestamp and related environmental parameters (such as temperature and humidity) at each time point. Monitor the air pressure state in real time through sensors to ensure the accuracy and timeliness of the data. Extract the air pressure state parameters at multiple time points from the database to ensure that the data format is unified (such as timestamp, air pressure value) for subsequent calculations. For any two adjacent time points t and t+1, calculate the air pressure fluctuation amplitude. The calculation formula is: = |P(t+1)−P(t)|, is the fluctuation amplitude at the i-th time point, and P(t) and P(t+1) are the air pressure values ​​at two adjacent time points respectively. Traverse all time points, calculate the air pressure fluctuation amplitude between all adjacent points, and store the results in a list or array for subsequent analysis. Select appropriate indicators to evaluate the stability of the air pressure, such as the standard deviation, mean, maximum and minimum values ​​of the fluctuation amplitude. Perform statistical analysis on the air pressure fluctuation amplitude data obtained in step S53, and calculate the mean, standard deviation and maximum value of the fluctuation amplitude to evaluate the stability of the air pressure. Set the air pressure stability threshold according to industry standards or experimental requirements (for example, if the standard deviation exceeds a certain value, the air pressure is considered unstable). Record the results of the stability test in the database, and generate relevant reports, including operating air pressure stability data and evaluation conclusions. This will provide a basis for subsequent decision-making and optimization.

[0047] In this embodiment, step S6 includes the following steps: Step S61: performing air pressure stabilization delay error analysis on the running air pressure stabilization data to generate an air pressure stabilization delay error value; Step S62: performing error optimization based on the air pressure stabilization delay error value to generate error-optimized air pressure stabilization data; Step S63: performing secondary air pressure deviation calculation on the error-optimized air pressure stabilization data based on the final test scene state data to generate a secondary air pressure deviation parameter; Step S64: fine-tuning the dynamic air pressure deviation of the air pressure test box based on the secondary air pressure deviation parameter to generate a dynamic air pressure deviation fine-tuning strategy to execute the pressure stability control operation of the air pressure test box.

[0048] In this embodiment, the operating state air pressure stability data is extracted from the database, including timestamps, air pressure values, and any relevant environmental parameters, to ensure that the data is complete and accurate, determine the delay difference between the target value of air pressure stability (such as the set stable air pressure) and the actual measured air pressure, traverse all time data, calculate the delay error at each time, and record it in a list. The Pandas library in Python can be used to process the data for easy calculation and analysis. The delay error data is statistically analyzed to calculate the mean, standard deviation, and maximum value, and the distribution characteristics of the error are identified, which helps to understand the overall performance and fluctuation of the error. According to the characteristics and distribution of the error, a suitable optimization method, such as gradient descent method, least squares method, etc., is selected to reduce the delay error. The optimization goal is set to minimize the error value, input the delay error data, run the selected optimization algorithm, and generate optimized air pressure stability data, which may include adjusting the air pressure control strategy or optimizing the control parameters. The generated error-optimized air pressure stability data is recorded in the database, and a relevant report is generated for subsequent verification and use. The final test scene state data is collected, including the final set air pressure target and the optimized air pressure stability data, and the secondary air pressure deviation is calculated by the following formula: Deviation value = − , is the optimized air pressure stability parameter, For the target air pressure set for the test, all relevant data points are traversed, the secondary deviation of each point is calculated, and the results are recorded. According to the secondary air pressure deviation parameters, a dynamic air pressure deviation fine-tuning strategy is formulated. The PID control or fuzzy control method in control theory can be used to achieve fine-tuning of the air pressure. Select a suitable algorithm to perform dynamic fine-tuning, such as the PID control algorithm, to ensure that the air pressure can respond quickly and stabilize within the set range. Apply the fine-tuning strategy to the control system of the air pressure test chamber, adjust the air pressure in real time to eliminate the deviation, and the monitoring system needs to feedback the air pressure status in real time to ensure the adjustment effect. During the adjustment process, continuously monitor the air pressure status to ensure that it is within the preset stable range. Record the air pressure status after fine-tuning and compare it with the status before fine-tuning to evaluate the effect of the adjustment. You can draw an air pressure change chart to intuitively display the impact of fine-tuning. The results and evaluation conclusions of the dynamic air pressure deviation fine-tuning are recorded in the database, and relevant reports are generated to support subsequent decision-making and operations.

[0049] In this embodiment, a pressure stability control system for an air pressure test chamber is provided, which is used to execute the pressure stability control method for an air pressure test chamber as described above, and includes: A non-operating state module is used to obtain multi-dimensional non-operating state monitoring parameters of the air pressure test box; perform non-operating state time series evolution of the multi-dimensional non-operating state monitoring parameters, thereby generating non-operating state time series features; The spatial topology module is used to obtain the internal structure diagram of the air pressure test chamber; based on the timing characteristics of the non-operating state, the spatial topology distribution analysis of the internal structure diagram of the air pressure test chamber is performed to build a digital twin model of the test chamber; The test scenario module is used to obtain the target test scenario based on the test log; perform target pressure state analysis on the target test scenario to obtain the final test scenario state data; The air pressure stability compensation module is used to perform space air pressure stability compensation calculation on the digital twin model of the test box according to the final test scene state data to obtain the space air pressure stability compensation value; The operating state module is used to perform operating state air pressure stability detection on the air pressure test box based on the space air pressure stability compensation value, so as to obtain operating state air pressure stability data; The dynamic air pressure fine-tuning module is used to perform dynamic air pressure deviation fine-tuning on the operating air pressure stability data to generate a dynamic air pressure deviation fine-tuning strategy to perform pressure stability control operations in the air pressure test chamber.

[0050] The present invention helps to understand the state changes of the test box in the shutdown state by monitoring the multi-dimensional non-operating state parameters of the air pressure test box, and provides basic data for subsequent stability control. Generating non-operating state time series characteristics can reveal the characteristic changes of the air pressure test box in different non-operating states, and provide a basis for subsequent analysis and optimization. Acquiring the internal structure diagram of the air pressure test box is helpful to understand the spatial layout and structural characteristics of the test box, and provides basic data for subsequent spatial analysis. Spatial topological distribution analysis and three-dimensional point cloud modeling based on non-operating state time series characteristics can construct a digital twin model of the test box, and provide a basis for subsequent simulation and optimization. Analyzing the pressure state of the target test scene is helpful to understand the working state of the test box in different scenes, and provides a reference for subsequent pressure control. Mining the final test scene state data can provide support for determining the final test conditions and pressure requirements, and provide a basis for subsequent control strategies. The air pressure test box can provide a basis for the formulation of the test strategy. The rapid air pressure filling simulation and calculation of the space air pressure stability compensation value are helpful to optimize the air pressure distribution and improve the air pressure stability of the air pressure test box. The compensation calculation based on the final test scene state data can adjust the air pressure parameters according to actual needs to ensure the stability of the test box in different scenarios. Real-time operation and air pressure stability detection are helpful to verify the stability of the air pressure test box, and timely discover and deal with abnormal air pressure fluctuations. The operating air pressure stability data can provide real-time feedback for adjusting the control strategy and parameters to ensure the stability of the test box during operation. Delay error analysis and dynamic air pressure deviation fine-tuning of the operating air pressure stability data are helpful to optimize the air pressure control strategy, improve air pressure stability and control accuracy, and generate a dynamic air pressure deviation fine-tuning strategy to achieve fine control of the pressure stability of the air pressure test box, ensuring the stability and reliability of the test box under various working conditions.

[0051] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0052] 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 pressure stability control method for an air pressure test chamber, characterized in that: The following steps are involved: Step S1: obtaining multi-dimensional non-operating state monitoring parameters of the air pressure test chamber; Performing non-operating state time series change evolution on the multi-dimensional non-operating state monitoring parameters, thereby generating non-operating state time series features; Step S2: obtaining an internal structure diagram of the air pressure test box; performing a spatial topological distribution analysis on the internal structure diagram of the air pressure test box based on the timing characteristics of the non-operating state, and constructing a digital twin model of the test box; Step S3: Obtaining a target test scenario based on the test log; Perform target pressure state analysis on the target test scene to obtain final test scene state data; Step S4: performing spatial air pressure stability compensation calculation on the digital twin model of the test box according to the final test scene state data to obtain a spatial air pressure stability compensation value; Step S5: performing an operating state air pressure stability test on the air pressure test box based on the space air pressure stability compensation value, thereby obtaining operating state air pressure stability data; Step S6: fine-tuning the dynamic air pressure deviation on the operating air pressure stability data to generate a dynamic air pressure deviation fine-tuning strategy to execute the air pressure test chamber pressure stability control operation.

2. The pressure stability control method of the air pressure test chamber according to claim 1, characterized in that: The specific steps of step S1 are: Step S11: monitoring the current non-operating state of the air pressure test box, thereby obtaining multi-dimensional non-operating state monitoring parameters of the air pressure test box, wherein the multi-dimensional non-operating state monitoring parameters include infrared thermal imaging temperature monitoring data, test box air pressure state parameters and test box humidity parameters; Step S12: performing heat distribution analysis of the test chamber on the infrared thermal imaging temperature monitoring data, and extracting the temperature distribution data of the test chamber; Step S13: performing temperature distribution fluctuation fitting on the temperature distribution data of the test chamber to obtain a temperature distribution fluctuation curve; Step S14: performing spatial pressure gradient calculation on the test chamber air pressure state parameters to generate spatial pressure gradient characteristics; Step S15: analyzing the characteristics of the air pressure balance state of the test box based on the spatial pressure gradient characteristics to obtain the characteristics of the air pressure balance state; Step S16: Perform non-operating state time series evolution on the temperature distribution fluctuation curve, the air pressure balance state characteristics and the test chamber humidity parameters, so as to generate non-operating state time series characteristics.

3. The pressure stability control method of the air pressure test chamber according to claim 1, characterized in that: The specific steps of step S2 are: Step S21: Obtaining the internal structure diagram of the air pressure test chamber; Step S22: visually identifying the component structure of the internal structure diagram of the air pressure test box, and marking multiple internal component nodes of the test box; Step S23: performing spatial topological distribution analysis on multiple internal component nodes of the test chambers to generate internal component spatial topological distribution data; Step S24: performing geometric morphological feature recognition on the internal structure diagram of the air pressure test box to obtain the morphological features of the test box; Step S25: performing three-dimensional point cloud modeling on the morphological features of the test box based on the spatial topological distribution data of the internal components to generate a three-dimensional structural model of the test box; Step S26: Dynamically map the timing characteristics of the three-dimensional structure model of the test box according to the timing characteristics of the non-operating state to construct a digital twin model of the test box.

4. The pressure stability control method of the air pressure test chamber according to claim 1, characterized in that: The specific steps of step S3 are: Step S31: obtaining a target test scenario based on the test log; Step S32: performing target pressure state analysis on the target test scene and extracting target scene pressure state characteristics; Step S33: performing temperature change demand rate analysis on the target test scene, and extracting temperature change demand rate parameters of the target scene; Step S34: performing temperature spatiotemporal characteristic evolution on the temperature change demand rate parameter of the target scene to extract the temperature spatiotemporal change law of the target scene; Step S35: performing final test scene state mining on the target scene pressure state characteristics according to the temperature spatiotemporal variation law of the target scene to obtain final test scene state data.

5. The pressure stability control method of the air pressure test chamber according to claim 4, characterized in that: The specific steps of step S32 are: Calculating the spatial average pressure of the target test scene to obtain the spatial average pressure parameters of the target scene; Predicting the peak pressure of the scene based on the spatial average pressure parameter of the target scene to obtain the predicted peak pressure of the target scene; Perform pressure filling time series variation analysis on the target test scene to obtain the target scene pressure filling time series variation data; Perform pressure fluctuation amplitude analysis on the target scene pressure filling time series change data to generate the pressure fluctuation amplitude; Perform multi-period change pattern recognition on the pressure fluctuation amplitude to generate multi-period pressure change characteristics; Perform pressure stability assessment on the pressure variation characteristics in multiple time periods to obtain the pressure stability assessment value of the target scene; The target demand pressure state analysis is performed on the target scenario pressure prediction peak and the target scenario pressure stability assessment value to extract the target scenario pressure state characteristics.

6. The pressure stability control method of the air pressure test chamber according to claim 1, characterized in that: The specific steps of step S4 are: Step S41: performing a rapid air pressure filling simulation on the digital twin model of the test box, and collecting air pressure simulation response data of the test box; Step S42: identifying the air pressure spatial distribution state of the test box air pressure simulation response data to generate air pressure spatial distribution state characteristics; Step S43: performing state deviation analysis on the air pressure spatial distribution state characteristics based on the final test scene state data, thereby generating a target air pressure state deviation value; Step S44: performing a spatial air pressure stability compensation calculation on the target air pressure state deviation value to obtain a spatial air pressure stability compensation value.

7. The pressure stability control method of the air pressure test chamber according to claim 1, characterized in that: The specific steps of step S5 are: Step S51: optimizing the air pressure balance of the air pressure space distribution state characteristics based on the spatial air pressure stability compensation value to obtain air pressure simulation balance optimization parameters; Step S52: operating the air pressure test box in real time according to the air pressure simulation balance optimization parameters, and collecting air pressure state parameters at multiple time points; Step S53: calculating the air pressure fluctuation amplitudes at adjacent points on the air pressure state parameters at multiple time points to obtain the air pressure fluctuation amplitudes between multiple time points; Step S54: Performing an operating state air pressure stability test based on the air pressure fluctuation amplitudes between multiple time points, thereby obtaining operating state air pressure stability data.

8. The pressure stability control method of the air pressure test chamber according to claim 1, characterized in that: The specific steps of step S6 are: Step S61: performing air pressure stabilization delay error analysis on the running air pressure stabilization data to generate an air pressure stabilization delay error value; Step S62: performing error optimization based on the air pressure stabilization delay error value to generate error-optimized air pressure stabilization data; Step S63: performing secondary air pressure deviation calculation on the error-optimized air pressure stabilization data based on the final test scene state data to generate a secondary air pressure deviation parameter; Step S64: fine-tuning the dynamic air pressure deviation of the air pressure test box based on the secondary air pressure deviation parameter to generate a dynamic air pressure deviation fine-tuning strategy to perform a pressure stability control operation of the air pressure test box.

9. A pressure stability control system for an air pressure test chamber, characterized in that: The method for controlling the pressure stability of the air pressure test chamber according to claim 1 comprises: A non-operating state module is used to obtain multi-dimensional non-operating state monitoring parameters of the air pressure test box; perform non-operating state time series evolution of the multi-dimensional non-operating state monitoring parameters, thereby generating non-operating state time series features; The spatial topology module is used to obtain the internal structure diagram of the air pressure test chamber; based on the timing characteristics of the non-operating state, the spatial topology distribution analysis of the internal structure diagram of the air pressure test chamber is performed to build a digital twin model of the test chamber; The test scenario module is used to obtain the target test scenario based on the test log; perform target pressure state analysis on the target test scenario to obtain the final test scenario state data; The air pressure stability compensation module is used to perform space air pressure stability compensation calculation on the digital twin model of the test box according to the final test scene state data to obtain the space air pressure stability compensation value; The operating state module is used to perform operating state air pressure stability detection on the air pressure test box based on the space air pressure stability compensation value, so as to obtain operating state air pressure stability data; The dynamic air pressure fine-tuning module is used to perform dynamic air pressure deviation fine-tuning on the operating air pressure stability data to generate a dynamic air pressure deviation fine-tuning strategy to perform pressure stability control operations in the air pressure test chamber.

Images