An integrated design method of an air tightness detection tool and a detection system

Abstract

This invention relates to an integrated design method for airtightness testing tooling and a testing system in the field of airtightness testing equipment. The method includes: acquiring product morphology data; extracting shape, size, and material information from a product 3D model database; calculating key points of the product's outer contour using a geometric feature analysis algorithm to determine product morphology diversity parameters; decomposing the fixture, inflation system, and sorting module into independent functional units using a modular design structure algorithm; generating standardized interface protocols; and determining the physical connections and data interaction methods between modules; generating a physical fixture using 3D printing technology based on the final tooling design parameters; and integrating the fixture with the inflation and sorting modules using an automated assembly algorithm to obtain a production-ready airtightness testing system.

Description

Technical Field

[0001] This invention relates to the field of airtightness testing equipment, and more particularly to an integrated design method for airtightness testing fixtures and testing systems. Background Technology

[0002] Air tightness testing is a key technology for ensuring product quality in industrial manufacturing, widely used in industries such as batteries, valves, and medical devices. Its accuracy and efficiency directly affect product reliability and production efficiency. Traditional air tightness testing methods typically rely on separate fixtures and testing equipment, resulting in poor adaptability, insufficient sealing, and low automation. These shortcomings lead to time-consuming testing processes and high error rates, failing to meet the demands of modern manufacturing for efficient, accurate, and flexible production.

[0003] The limitations of existing solutions are mainly reflected in the following aspects: traditional fixture designs are difficult to quickly adapt to products of different shapes and sizes, requiring frequent fixture changes or adjustments, reducing production efficiency; leakage problems in the tooling itself often interfere with test results, affecting accuracy; in addition, the lack of effective integration between the testing system and the fixture makes it difficult to achieve automated operation, resulting in more manual intervention and lower efficiency. These problems are particularly prominent in high-precision or complex product testing scenarios. The core challenge lies in how to achieve an integrated design of the tooling and testing system to simultaneously meet the needs of rapid adaptation, high sealing, and automated integration. First, rapid adaptation requires the fixture to flexibly cope with diverse product forms, but existing fixture designs generally lack adaptability, making it difficult to balance versatility and stability. Second, high sealing requires the tooling to maintain a low leakage rate in complex testing environments, but traditional sealing structures are easily affected by external factors, making it difficult to ensure testing accuracy. Finally, automated integration involves the collaborative work of the fixture with inflation, testing, and sorting modules, and existing technologies lack efficient modular design and data linkage mechanisms. These unresolved technical factors lead to problems such as low testing efficiency, unstable accuracy, and insufficient production flexibility.

[0004] Therefore, the key issues of this research are how to design an airtightness testing fixture that integrates rapid adaptation, high sealing performance, and automated integration, while solving the problems of fixture adaptability to diverse products, sealing stability, and system linkage efficiency through innovative structure. Summary of the Invention

[0005] This invention provides an integrated design method for airtightness testing fixtures and testing systems, comprising the following steps:

[0006] Acquire product form data, extract shape, size and material information from the product 3D model database, calculate key points of the product's outer contour through geometric feature analysis algorithms, and determine product form diversity parameters.

[0007] Based on the product form diversity parameters, an adaptive fixture design algorithm is adopted, combined with a preset fixture universal design template, to generate a 3D fixture model suitable for various product forms, resulting in a fixture structure with enhanced rapid adaptability.

[0008] Geometric features of the contact surface are extracted from the 3D model of the fixture. The stress distribution when the fixture contacts the product is simulated by finite element analysis to determine whether the contact surface meets the high sealing requirements. If the stress distribution is uniform and there is no local stress concentration, the sealing structure of the fixture is deemed feasible.

[0009] For the fixture sealing structure, acquire data on the complexity of the testing environment, including the fluctuation range of temperature, pressure and humidity, and use a tooling leakage control algorithm to optimize the sealing material and contact surface geometry parameters to obtain a tooling design with a leakage rate lower than a preset threshold.

[0010] Through modular design structure algorithm, the fixture, inflation system and sorting module are decomposed into independent functional units, generating standardized interface protocols and determining the physical connection and data interaction methods between each module;

[0011] The system acquires operational status data of the fixture, inflation system, and sorting module, establishes a real-time data stream transmission channel using a data linkage mechanism algorithm, optimizes module collaboration efficiency through time series analysis, and obtains a system framework with improved automation integration.

[0012] For the automated integrated system framework, the efficiency of the inflation system coordination and sorting module is simulated. A dynamic scheduling algorithm is used to adjust the timing parameters of inflation and sorting, and it is determined whether the overall system operating efficiency reaches the preset threshold. If it does, the final integrated solution of tooling and detection system is determined.

[0013] The detection accuracy and stability data are extracted from the integrated solution. The variance and deviation of the detection results are calculated by statistical analysis algorithm to determine whether the detection accuracy meets the preset standard. If it does, the final airtightness testing tooling design parameters are generated.

[0014] Based on the final tooling design parameters, a solid fixture is generated using 3D printing technology. An automated assembly algorithm controls a robot to integrate the fixture with the inflation and sorting modules, resulting in a production-ready airtightness testing system.

[0015] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

[0016] This invention discloses an integrated design method for airtightness testing fixtures and systems. By acquiring product morphology data and analyzing geometric features, an adaptive fixture model suitable for various products is generated. Finite element analysis is used to optimize the sealing structure, and leakage control of the fixture is optimized based on the complexity of the testing environment. A modular design integrates the fixture, inflation, and sorting systems, establishing a data linkage mechanism to improve automation. Dynamic scheduling algorithms optimize system operating efficiency. Finally, the testing accuracy is verified, and the fixture is manufactured using 3D printing and automated assembly technologies. This invention can quickly adapt to various product forms, improve sealing performance and testing accuracy, realize the intelligent design and manufacturing of airtightness testing fixtures, and effectively improve product quality control. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating an integrated design method for an airtightness testing fixture and testing system according to the present invention.

[0018] Figure 2 This is a schematic diagram of an integrated design method for an airtightness testing fixture and testing system according to the present invention.

[0019] Figure 3 This is another schematic diagram of an integrated design method for an airtightness testing fixture and testing system according to the present invention. Detailed Implementation

[0020] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] like Figure 1-3 The integrated design method of airtightness testing fixture and testing system in this embodiment may specifically include:

[0022] Step S101: Obtain product form data, extract shape, size and material information from the product 3D model database, calculate key points of the product's outer contour through geometric feature analysis algorithm, and determine product form diversity parameters.

[0023] Shape, dimension, and material data are obtained from a product 3D model database, and a structured dataset is generated using data extraction techniques. The structured dataset is processed using a geometric feature analysis algorithm to extract geometric features from the shape and dimension data, resulting in a geometric feature set. A keypoint detection algorithm is used to extract outer contour keypoints from the geometric feature set. If the number of keypoints is below a preset threshold, the geometric feature extraction parameters are adjusted to obtain an outer contour keypoint set. Based on the outer contour keypoint set, the distance and angle features between keypoints are calculated, and a clustering analysis algorithm is used to generate morphological diversity parameters. Surface attributes are extracted from the material data. If the surface attributes do not match a preset standard, the morphological diversity parameters are adjusted based on the geometric feature set to obtain adjusted morphological diversity parameters. By comparing the adjusted morphological diversity parameters with a preset morphological template, it is determined whether the product morphology meets the diversity requirements, resulting in a product morphological classification result. Based on the product morphological classification result, a digital description of the product morphology is generated, and the final product morphological parameters are determined.

[0024] For example, when extracting shape information from a product 3D model database, STEP file parsing based on boundary representation can be used. For instance, when parsing a mobile phone casing model, geometric parameters such as a length of 120 mm, a width of 65 mm, and a surface radius of 2.5 mm can be extracted. When calculating the model's surface area using the BRep_Tool algorithm from the OpenCascade library, the surface area of ​​the ABS plastic material was measured to be 9850 square millimeters. Simultaneously, the material property of a density of 1.05 grams per cubic centimeter was extracted using the Material attribute tree. In the geometric feature analysis stage, an improved Alpha-Shape algorithm (α = 1.2) was used to reconstruct the outer contour of the point cloud data, identifying 18 key feature points from 25600 vertices, including 4 rounded corner transition points and 2 USB interface positioning points. When calculating product morphological diversity parameters using principal component analysis, cluster analysis was performed on the aspect ratio data of 300 similar products, resulting in a morphological distribution matrix with a coefficient of variation of 0.15. The eigenvalue λ1 = 0.82 indicates that the length direction is the main dimension of morphological variation. In the dimensional tolerance analysis stage, Monte Carlo simulation was used to conduct 10,000 samplings. It was calculated that when the assembly clearance pass rate reaches 98.7%, the corresponding critical dimension tolerance zone should be controlled within ±0.2 mm.

[0025] Step S102: Based on the product form diversity parameters, an adaptive fixture design algorithm is adopted, combined with a preset fixture universal design template, to generate a 3D fixture model suitable for various product forms, resulting in a fixture structure with enhanced rapid adaptability.

[0026] Product form data is acquired, and key geometric features are extracted from the diverse parameters of the product form data to generate a design parameter set. An adaptive algorithm is used to process the design parameter set, combined with a general template, to generate an initial 3D model of the fixture. If the adaptation error between the initial 3D model of the fixture and the product form data exceeds a preset threshold, the parameters of the adaptive algorithm are adjusted, and the 3D model of the fixture is regenerated. Key geometric features of the fixture structure are extracted from the optimized 3D model of the fixture to generate a fixture structure description file. Based on the fixture structure description file, a structural optimization algorithm is used to adjust the fixture geometric parameters to obtain a quickly adaptable fixture structure. Using the quickly adaptable fixture structure, final 3D model data of the fixture is generated, and a fixture design scheme is output. If the adaptation performance of the final 3D model data meets a preset threshold, the fixture design scheme is determined; otherwise, the process returns to the step of processing the design parameter set, and the 3D model of the fixture is regenerated.

[0027] For example, in the implementation process, the product form diversity parameters are first analyzed. For instance, principal component analysis (PCA) is used to reduce the dimensionality of the product's external dimensions, extracting key feature parameters such as length (120±5mm), width (80±2mm), and radius of curvature (R15-R50), forming a feature matrix X∈R^(n×3). Based on this, an adaptive fixture algorithm is designed, using fuzzy logic control combined with genetic algorithm optimization. The population size is set to 50, the crossover probability is 0.8, and the mutation probability is 0.1. After 100 iterations, the optimal solution is obtained, with a fitness function value of 0.92. Next, a preset fixture general design template is called. This template contains three basic clamping units (V-block, planar gripper, and arc-shaped pad) and two driving methods (pneumatic and servo motor). The feature matrix is ​​automatically matched through a parametric modeling engine. For example, when the radius of curvature R>30mm, the arc-shaped pad is selected first, and the clamping force threshold is set to 200N±5%. Finally, a fixture model was generated using the API interface of the 3D modeling software. Finite element analysis was used to verify the structural strength, with a maximum stress of 235 MPa and a safety factor of 1.8. Simultaneously, motion simulation showed that the changeover time was reduced to 45 seconds, and the adaptability was improved by 60%. The entire process was linked through a PLM system to ensure that design parameters were synchronized with production requirements in real time.

[0028] Step S103: Extract the geometric features of the contact surface from the three-dimensional model of the fixture, simulate the stress distribution when the fixture contacts the product through finite element analysis, and determine whether the contact surface meets the high sealing requirements. If the stress distribution is uniform and there is no local stress concentration, then the sealing structure of the fixture is deemed feasible.

[0029] Geometric features of the contact surface are extracted from the 3D model of the fixture using a geometric segmentation algorithm to obtain contact surface geometric data. This contact surface geometric data is then loaded using finite element analysis software, and product contact boundary conditions are set to simulate stress distribution, resulting in stress distribution data. The stress distribution data is analyzed using a mean square error (MSE) algorithm. If the MSE is below a preset threshold, the stress distribution is considered uniform, yielding a uniformity assessment result. Local stress values ​​are extracted from the stress distribution data. If the local stress values ​​are below a preset threshold, there is no local stress concentration, yielding a local stress assessment result. Based on both the uniformity assessment result and the local stress assessment result, if both conditions are met, the fixture sealing structure is determined to meet high sealing requirements, yielding a sealing performance assessment result. If the high sealing requirements are met, the fixture sealing structure is deemed feasible. Optimized 3D model data of the fixture is then generated.

[0030] For example, when extracting the geometric features of the contact surface from the 3D model of the fixture, an algorithm based on curvature analysis can be used to identify the boundary of the contact area. For instance, a Gaussian curvature threshold of 0.05 mm⁻¹ can be used to filter non-contact surfaces, and point cloud data of the contact surface can be extracted using a region growing method and fitted as a NURBS surface. In the finite element analysis stage, material parameters such as an aluminum alloy elastic modulus of 69 GPa and a Poisson's ratio of 0.33 are set. An adaptive meshing strategy is used, controlling the element size to within 0.5 mm near the contact surface. A bolt preload of 10 N·m is applied as a boundary condition, and the contact pressure distribution is calculated using a nonlinear contact algorithm. The analysis results show that the maximum contact pressure is 25 MPa, the pressure distribution uniformity index reaches 0.92 (1 for complete uniformity), and the stress concentration factor is less than 1.3. When the contact width is greater than 3 mm and the contact pressure gradient is less than 2 MPa / mm, the sealing requirements are considered met. The effect of different surface roughnesses (Ra 0.8 μm to 3.2 μm) was verified by parametric scanning. It was found that when the roughness is below 1.6 μm, the leakage rate can be controlled at 1 × 10⁻⁶. -6 Pa·m 3 / s or less. Ultimately, the contact surface profile tolerance is controlled within ±0.05mm to ensure that the pressure in more than 90% of the contact area is maintained between 15-20MPa.

[0031] Step S104: For the fixture sealing structure, acquire data on the complexity of the testing environment, including the fluctuation range of temperature, pressure and humidity, and use a tooling leakage control algorithm to optimize the sealing material and contact surface geometry parameters to obtain a tooling design with a leakage rate lower than a preset threshold.

[0032] Environmental data is acquired by collecting fluctuation range data from temperature, pressure, and humidity sensors to determine an environmental complexity feature vector, which includes temperature fluctuation range, pressure fluctuation range, and humidity fluctuation range. If the temperature fluctuation range exceeds a preset threshold, a linear regression algorithm is used to predict the aging effect of temperature on the sealing material, obtaining the material's temperature resistance parameters. Based on the material's temperature resistance parameters, materials meeting the temperature resistance requirements are matched from a preset sealing material database to determine a candidate sealing material set. If the candidate sealing material set contains at least one material, finite element analysis is used to simulate the stress distribution of the contact surface geometry due to the pressure fluctuation range, obtaining geometric optimization parameters. A genetic algorithm is used to iteratively optimize the sealing material parameters and the geometric optimization parameters to obtain a predicted leakage rate. If the predicted leakage rate is lower than a preset threshold, a tooling design scheme is generated based on the optimized sealing material parameters and contact surface geometric parameters. The tooling design scheme is virtually assembled and verified using 3D modeling software to determine whether the sealing structure performance meets the leakage rate requirements, thus determining the final tooling design.

[0033] For example, in the design process of the fixture sealing structure, temperature, pressure, and humidity data of the environment are first collected in real time through a sensor network. The temperature fluctuation range is -20℃ to 80℃, the pressure fluctuation range is 0.1MPa to 1.5MPa, and the humidity fluctuation range is 10% to 90%. This data is transmitted to a data analysis system via an IoT platform, and time series analysis is used to identify periodic changes and abnormal fluctuations in environmental parameters. Based on this data, a tooling leakage control algorithm is introduced. This algorithm combines finite element analysis and machine learning models to optimize the elastic modulus of the sealing material and the geometric parameters of the contact surface.

[0034] Specifically, the algorithm iteratively calculates and adjusts the thickness of the sealing material from 0.5 mm to 2 mm and the roughness of the contact surface from Ra0.8 to Ra3.2 to ensure the stability of sealing performance under different environmental conditions. Through simulation experiments, the algorithm predicts the leakage rate under different parameter combinations and selects design schemes with leakage rates below a preset threshold of 0.01 mL / min. Finally, the optimized tooling design is verified in a laboratory environment, and the results show that its leakage rate is stable at 0.008 mL / min, meeting the design requirements.

[0035] Step S105: Through a modular design structure algorithm, the fixture, inflation system and sorting module are decomposed into independent functional units, a standardized interface protocol is generated, and the physical connection and data interaction methods between the modules are determined.

[0036] Obtain an initial design set for the modular system, including descriptions of fixture units, inflation systems, and sorting modules. Decompose the initial design set using a modular design algorithm to obtain multiple independent functional units, each including a preliminary functional description of the module. If functional duplication exists among the independent functional units, redundant functions are merged using a functional analysis algorithm to obtain a simplified functional unit set. Extract the input / output requirements of each functional unit from the simplified functional unit set to generate standardized interface specifications. If parameter conflicts exist in the standardized interface specifications, adjust the parameter definitions using a protocol optimization algorithm to obtain a unified interface protocol. Generate data interaction rules based on the unified interface protocol to determine the data flow direction and format between modules. Obtain the mechanical and electrical connection requirements of each functional unit through physical connection analysis to determine the physical connection scheme. Extract the constraints for module collaboration from the physical connection scheme to generate a module collaboration process. If timing conflicts exist in the module collaboration process, optimize the collaboration order using a timing adjustment algorithm to obtain a final collaboration scheme. Generate a communication protocol between modules based on the final collaboration scheme to determine the real-time requirements of data interaction. Analyze the communication protocol to determine whether data transmission meets the real-time constraints and obtain the communication protocol parameters. Performance metrics for module collaboration are extracted from the communication protocol parameters to generate the operational configuration of the modular system. Simulation is performed using this configuration to determine if the system meets performance requirements, resulting in an optimized system configuration. A deployment plan for the modular system is then generated based on the optimized configuration. The deployment plan is used to verify the stability of inter-module collaboration and determine the final deployment parameters.

[0037] For example, in the modular design structure algorithm, the fixture, inflation system, and sorting module are first decomposed into independent functional units. The fixture module achieves precise gripping through force sensors and position encoders. The force sensor uses a 0-10V analog signal output, and the position encoder has a resolution of 0.01mm, ensuring a gripping accuracy within ±0.05mm. The inflation system module uses a PID control algorithm, setting the air pressure range to 0-1MPa with a control accuracy of ±0.01MPa. It uses a pressure sensor to provide real-time feedback of the air pressure value and adjusts the solenoid valve opening to ensure stable inflation. The sorting module uses an image recognition algorithm to classify items, employing a convolutional neural network (CNN) model. The input image resolution is 1920×1080, achieving a recognition accuracy of 99.5% and a sorting speed of up to 200 items / minute. The modules are physically connected and interact with each other through a standardized interface protocol, using the RS485 communication protocol with a baud rate of 115200bps. The data frame format is 8 data bits, 1 stop bit, and no parity bit, ensuring reliable and real-time data transmission. The physical connection uses an M12 interface to ensure a robust connection and ease of maintenance. Data exchange utilizes the Modbus protocol with a master-slave architecture; the master station polls each slave station to ensure data synchronization and coordinated system operation. Through this design, each module can operate independently while also collaborating efficiently, improving the overall system's stability and efficiency.

[0038] Step S106: Obtain the operating status data of the fixture, inflation system and sorting module, establish a real-time data stream transmission channel using a data linkage mechanism algorithm, optimize the module collaboration efficiency through time series analysis, and obtain a system framework with improved automation integration.

[0039] The system acquires operational status data from the clamping module, inflation system, and sorting module. Operating parameters of each module are collected via sensors and stored in a pre-defined database to obtain a structured operational status dataset. An association rule mining algorithm is used to process this dataset, analyzing the correlation between operational statuses of each module, generating a data linkage model between modules, and determining real-time data stream generation rules. Based on these rules, a data stream channel is established, extracting dynamic data from the operational status dataset and transmitting it to the analysis node using message queue technology to obtain a real-time data stream. If the transmission delay of the real-time data stream exceeds a preset threshold, the priority of the message queue is adjusted, and the bandwidth of the data stream channel is reallocated to obtain a stable data stream channel. An ARIMA model is used to perform time series analysis on the real-time data stream to predict the operational trends of each module. Based on the prediction results, the coordination parameters between modules are adjusted to obtain optimized module coordination efficiency. Based on the optimized module coordination efficiency, the control logic of the system framework is adjusted, and a distributed computing architecture is used to integrate the operating instructions of the clamping module, inflation system, and sorting module, resulting in an automated, integrated, and optimized system framework. By extracting dynamic change data of module collaboration efficiency from the system framework's operation logs, K-means clustering algorithm is used to analyze the efficiency change trend and determine the optimized efficiency of the system framework.

[0040] For example, clamping force data is collected by pressure sensors deployed on the fixture, with a sampling frequency of 100Hz. A sliding window algorithm is used to calculate the standard deviation of the force value over 10 seconds. When the standard deviation exceeds 5N, an abnormal alarm is triggered. Simultaneously, real-time data is pushed to a Kafka message queue via the MQTT protocol. The inflation system uses a PID control algorithm to regulate air pressure, with a target pressure value set at 0.6MPa. Kalman filtering is used to process pressure sensor noise, and the control cycle is 50ms. When the actual pressure fluctuation exceeds ±0.02MPa, the opening of the solenoid valve is automatically adjusted. The sorting module uses a YOLOv5 model to identify workpieces on the conveyor belt in real time, with a detection frame rate of 30fps. Combined with the Hungarian algorithm, multi-target tracking is achieved. When the sorting accuracy is below 98%, a model retraining mechanism is triggered. A stream processing platform based on Apache FLIX is established, with a time window set to 1 minute. The Dynamic Time Warping (DTW) algorithm is used to calculate the temporal correlation of the three modules. When the collaborative delay exceeds 200ms, the task scheduling strategy is automatically adjusted. By predicting the load trends of each module using the ARIMA model, elastic expansion is initiated in advance when the backlog in the prediction queue exceeds 50 items, ultimately increasing the overall system throughput by 35% and reducing the fault response time to less than 500ms.

[0041] Step S107: For the automated integrated system framework, simulate the efficiency of the inflation system coordination and sorting module, use a dynamic scheduling algorithm to adjust the timing parameters of inflation and sorting, and determine whether the overall system operating efficiency reaches the preset threshold. If it does, determine the final integrated solution of tooling and detection system.

[0042] Real-time operational data from the inflation system and sorting module are acquired to construct a dynamic dataset containing timing parameters. A particle swarm optimization algorithm is used to adjust the task scheduling order, resulting in an optimized timing parameter configuration. Based on this optimized configuration, the collaborative operation of the inflation system and sorting module is simulated, and the collaborative efficiency index is calculated to obtain the overall system operating efficiency value. If the overall system operating efficiency value reaches a preset threshold, a preliminary configuration scheme for the tooling system is generated based on the optimized timing parameters, resulting in a tooling system parameter set. The tooling system parameter set is then quality-verified using a detection system. Verification results are obtained to determine if the integrated solution requirements are met, resulting in a tooling parameter set that passes the inspection. A genetic algorithm is used to iteratively optimize the tooling parameter set that passes the inspection, resulting in the final tooling parameter set. By fusing the final tooling parameter set with the detection system data, an integrated solution for the automated integrated system is generated, determining the final configuration of the system framework. Based on the final configuration, the timing parameters of the inflation system and sorting module are dynamically updated, and a rule-based judgment method is used to verify the system operating efficiency, obtaining the operational efficiency confirmation result of the integrated solution.

[0043] For example, in an automated integrated system framework, when simulating the collaborative efficiency of the inflation system and the sorting module, inflation pressure data is first collected in real time by sensors (e.g., a target pressure value of 0.5 MPa with an allowable error of ±0.02 MPa), and the throughput data of the sorting module (e.g., processing 1200 items per hour) is input into a dynamic scheduling algorithm. The algorithm uses an improved genetic algorithm (population size 50, iterations 100, crossover probability 0.8, mutation probability 0.1) to optimize timing parameters. The objective function is to minimize the cycle time T = inflation time t1 (default 2 seconds) plus sorting delay t2 (default 1.5 seconds). Through simulation analysis, when the algorithm converges to T ≤ 3.2 seconds (preset threshold), the system efficiency meets the target. At this point, the inflation valve opening is adjusted based on fuzzy PID control (proportional coefficient Kp = 1.2, integral time Ti = 0.5 seconds), while the sorting module uses a priority queue (high-priority item response time ≤ 0.3 seconds) to ensure collaborative stability. The reliability of the integrated solution was finally verified through Monte Carlo simulation (10,000 samples). The tooling positioning accuracy needed to be ≤0.1mm, and the false judgment rate of the detection system needed to be <0.05%. Data fusion was achieved using Kalman filtering (process noise Q=0.01, observation noise R=0.005) to synchronize multi-sensor data. When all parameters met the constraints, the system automatically generated the CAD parameters of the tooling fixture (e.g., clamping force 20N±5%, stroke 50mm) and the vision detection path planning (scanning speed 200mm / s, repeatability ±0.05mm).

[0044] Step S108: Extract the detection accuracy stability data from the integrated solution, calculate the variance and deviation of the detection results through statistical analysis algorithms, and determine whether the detection accuracy meets the preset standard. If it does, generate the final airtightness testing fixture design parameters.

[0045] The system obtains detection accuracy and stability data from the integrated solution, removes outliers using data cleaning techniques, and obtains the first dataset. Statistical analysis algorithms are then applied to this first dataset to calculate the variance and bias of the detection results, yielding accuracy statistical indicators. If both the variance and bias in the accuracy statistical indicators are below preset standards, the detection accuracy is deemed to meet the requirements, generating an accuracy judgment result. Based on the accuracy judgment result, key feature parameters are extracted from the compliant detection data to obtain an airtightness feature set. A regression analysis algorithm is used to model the airtightness feature set, generating tooling design parameters and obtaining a preliminary design parameter set. A geometric optimization algorithm is then used to adjust the preliminary design parameter set, resulting in the final airtightness detection tooling design parameters. Core parameters are extracted from the final airtightness detection tooling design parameters to generate a digital model of the airtightness detection tooling.

[0046] For example, in the integrated solution, 100 sets of test accuracy data were first extracted from the airtightness testing system. These data covered test results under different pressure conditions. The variance and bias of these data were calculated using a statistical analysis algorithm. Specifically, the variance formula σ was used. 2 =Σ(xi-μ) 2 / N, where xi is each measured value, μ is the average value, and N is the total number of data points, the variance is calculated to be 0.05. Simultaneously, using the deviation formula Bias=Σ(xi-T) / N, where T is the preset standard value, the deviation is calculated to be 0.02. According to the preset standard, the variance should be less than 0.1, and the deviation should be less than 0.05, therefore the detection accuracy meets the requirements. Based on this, the final airtightness testing fixture design parameters were generated, including a pressure range of 0.5 to 1.5 MPa, a detection accuracy of ±0.02 MPa, stainless steel fixture material, and fluororubber sealing ring material to ensure the stability and reliability of the detection.

[0047] Step S109: Based on the final tooling design parameters, a solid fixture is generated using 3D printing technology. The robot is then controlled by an automated assembly algorithm to integrate the fixture with the inflation and sorting modules, resulting in an airtightness testing system ready for production.

[0048] Obtain tooling design parameters and generate a fixture entity using 3D printing technology to obtain a high-precision fixture. Based on the high-precision fixture, apply an automated assembly algorithm to generate robot control instructions and determine the assembly path. Using the robot control instructions, drive the robot to integrate the fixture and the inflation module to obtain a preliminary integrated component. If the preliminary integrated component meets a preset inflation module position deviation threshold, then the robot performs sorting module integration to obtain a complete integrated component. For the complete integrated component, obtain airtightness test data and determine the system's functional integrity by comparing it with preset airtightness standards. Based on the airtightness test data, adjust the integration control logic and optimize the robot assembly parameters to obtain a production-ready airtightness testing system. Perform modular design verification using the production-ready airtightness testing system.

[0049] For example, based on the final tooling design parameters, a solid fixture is generated using 3D printing technology. First, a 3D model of the fixture is designed using CAD software. The model dimensions are 200mm × 150mm × 100mm, with a wall thickness of 3mm. Nylon 12 is selected as the material to ensure sufficient strength and lightweight. After the design is completed, SLS (Selective Laser Sintering) technology is used for printing. The laser power is 50W, the layer thickness is 0.1mm, and the printing speed is 20mm / s. During the printing process, a real-time monitoring system ensures that the printing accuracy is within ±0.05mm. After printing, post-processing is performed, including removing the support structure and surface polishing, to improve the surface finish of the fixture. Next, an automated assembly algorithm controls a robot to integrate the fixture with the inflation and sorting modules. The algorithm uses vision-based path planning. The robot arm is 800mm long, has a load capacity of 5kg, and a motion accuracy of ±0.02mm. The vision system captures the positional information of the fixtures and modules using a camera with a resolution of 1280×1024 pixels and a frame rate of 30fps. Image processing algorithms identify the precise positions of the fixtures and modules, with an error controlled within ±0.1mm. The robot assembles the components according to a planned path. During assembly, force sensors monitor the assembly force in real time, ensuring it remains between 10N and 20N to avoid overload or underload. After assembly, an airtightness test is performed using a differential pressure method. The test pressure is 0.5MPa, and the test time is 10s. Pressure sensors monitor pressure changes in real time, with pressure fluctuations controlled within ±0.01MPa to ensure the system's airtightness meets production requirements. The final airtightness testing system is ready for production use. The overall system dimensions are 1000mm×800mm×600mm, the weight is 50kg, and the testing accuracy is ±0.02MPa, meeting the high-efficiency and high-precision requirements of the production line.

[0050] The above description is merely an embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. An integrated design method for airtightness testing fixtures and testing systems, characterized in that, The method includes the following steps: S101. Obtain product form data, extract shape, size and material information from the product 3D model database, calculate key points of the product's outer contour through geometric feature analysis algorithm, and determine product form diversity parameters. S102. Based on the product form diversity parameters, an adaptive fixture design algorithm is adopted, combined with a preset fixture universal design template, to generate a 3D fixture model suitable for various product forms, resulting in a fixture structure with enhanced rapid adaptability. S103. Extract the geometric features of the contact surface from the 3D model of the fixture, simulate the stress distribution when the fixture contacts the product through finite element analysis, and determine whether the contact surface meets the high sealing requirements. If the stress distribution is uniform and there is no local stress concentration, then the sealing structure of the fixture is deemed feasible. S104. For the fixture sealing structure, acquire data on the complexity of the testing environment, including the fluctuation range of temperature, pressure and humidity, and use the tooling leakage control algorithm to optimize the sealing material and contact surface geometry parameters to obtain a tooling design with a leakage rate lower than the preset threshold. S105. Through modular design structure algorithm, the fixture, inflation system and sorting module are decomposed into independent functional units, a standardized interface protocol is generated, and the physical connection and data interaction method between each module is determined. S106. Obtain the operating status data of the fixture, inflation system and sorting module, adopt the data linkage mechanism algorithm, establish a real-time data stream transmission channel, optimize the module collaboration efficiency through time series analysis, and obtain a system framework with improved automation integration. S107. For the automated integrated system framework, simulate the efficiency of the inflation system coordination and sorting module, use a dynamic scheduling algorithm to adjust the timing parameters of inflation and sorting, and determine whether the overall system operating efficiency reaches the preset threshold. If it does, determine the final integrated solution of tooling and detection system. S108. Extract the detection accuracy and stability data from the integrated solution, calculate the variance and deviation of the detection results through statistical analysis algorithms, and determine whether the detection accuracy meets the preset standard. If it does, generate the final airtightness testing tooling design parameters. S109. Based on the final tooling design parameters, a solid fixture is generated using 3D printing technology. The robot is then controlled by an automated assembly algorithm to integrate the fixture with the inflation and sorting modules, resulting in a production-ready airtightness testing system.

2. The integrated design method of airtightness testing fixture and testing system according to claim 1, characterized in that, S101 includes: Shape data, size data, and material data are obtained from the product's 3D model database, and a structured dataset is generated using data extraction techniques. The structured dataset is processed by a geometric feature analysis algorithm to extract geometric features from the shape and size data, resulting in a set of geometric features. A key point detection algorithm is used to extract key points of the outer contour from the geometric feature set. If the number of key points is lower than a preset threshold, the geometric feature extraction parameters are adjusted to obtain the set of key points of the outer contour. Based on the set of key points of the outer contour, calculate the distance and angle features between the key points, and use a clustering analysis algorithm to generate morphological diversity parameters; Surface properties are extracted from the material data. If the surface properties do not match the preset standard, the morphological diversity parameter is adjusted according to the geometric feature set to obtain the adjusted morphological diversity parameter. By comparing the adjusted morphological diversity parameters with the preset morphological template, it is determined whether the product morphology meets the diversity requirements, and the product morphology classification result is obtained. Based on the product form classification results, a digital description of the product form is generated, and the final product form parameters are determined.

3. The integrated design method of airtightness testing fixture and testing system according to claim 1, characterized in that, S102 includes: Acquire product form data, extract key geometric features from the diverse parameters of the product form data, and generate a set of design parameters; An adaptive algorithm is used to process the set of design parameters, and combined with a general template, an initial 3D model of the fixture is generated. If the adaptation error between the initial fixture 3D model and the product form data exceeds a preset threshold, the parameters of the adaptive algorithm are adjusted, and the fixture 3D model is regenerated. Key geometric features of the fixture structure are extracted from the optimized 3D model of the fixture to generate a fixture structure description file; Based on the fixture structure description file, the fixture geometric parameters are adjusted using a structural optimization algorithm to obtain a fast-adaptive fixture structure; The final 3D model data of the fixture is generated through the rapidly adaptable fixture structure, and the fixture design scheme is output. If the adaptation performance of the final fixture 3D model data meets the preset threshold, then the fixture design scheme is determined. If the preset threshold is not met, return to the step of processing the set of design parameters and regenerate the 3D model of the fixture.

4. The integrated design method of an airtightness testing fixture and testing system according to any one of claims 1-3, characterized in that, S103 includes: Geometric features of the contact surface are extracted from the 3D model of the fixture using a geometric segmentation algorithm to obtain contact surface geometric data; The contact surface geometry data is loaded using finite element analysis software, the product contact boundary conditions are set, stress distribution is simulated, and stress distribution data is obtained. The stress distribution data is analyzed using a mean square error algorithm. If the mean square error is lower than a preset threshold, the stress distribution is judged to be uniform, and a uniformity judgment result is obtained. Local stress values ​​are extracted from the stress distribution data. If the local stress value is lower than a preset threshold, it is determined that there is no local stress concentration, and a local stress judgment result is obtained. Based on the uniformity judgment result and the local stress judgment result, if both conditions are met, it is determined that the clamp sealing structure meets the high sealing requirements, and the sealing judgment result is obtained. Based on the sealing performance assessment results, if the high sealing performance requirements are met, then the clamp sealing structure is deemed feasible. Generate optimized 3D model data for the fixture.

5. The integrated design method of an airtightness testing fixture and testing system according to any one of claims 1-3, characterized in that, S104 includes: Environmental data is acquired by collecting fluctuation range data from temperature, pressure, and humidity sensors to determine an environmental complexity feature vector, which includes temperature fluctuation range, pressure fluctuation range, and humidity fluctuation range. If the temperature fluctuation range exceeds a preset threshold, the aging effect of temperature on the sealing material is predicted by a linear regression algorithm to obtain the material's temperature resistance parameters. Based on the temperature resistance parameters of the material, materials that meet the temperature resistance requirements are matched from a preset sealing material database to determine a set of candidate sealing materials; If the candidate sealing material set includes at least one material, then the stress distribution of the contact surface geometry under the pressure fluctuation range is simulated by finite element analysis to obtain the geometric optimization parameters; A genetic algorithm is used to iteratively optimize the sealing material parameters and the geometric optimization parameters to obtain the predicted leakage rate. If the predicted leakage rate is lower than the preset threshold, a tooling design scheme is generated based on the optimized sealing material parameters and contact surface geometric parameters. The tooling design scheme is virtually assembled and verified using 3D modeling software to determine whether the sealing structure performance meets the leakage rate requirements and to finalize the tooling design.

6. The integrated design method of an airtightness testing fixture and testing system according to any one of claims 1-3, characterized in that, S105 includes: Obtain an initial design set for the modular system, which includes description information for fixture units, inflation systems, and sorting modules; The initial design set is decomposed by a modular design algorithm to obtain multiple independent functional units, each of which includes a preliminary functional description of each module. If there is functional duplication in the independent functional units, redundant functions are merged through functional analysis algorithm to obtain a simplified set of functional units; Extract the input and output requirements of each functional unit from the simplified functional unit set to generate standardized interface specifications; If there are parameter conflicts in the standardized interface specification, the parameter definitions are adjusted through a protocol optimization algorithm to obtain a unified interface protocol; Data interaction rules are generated based on the unified interface protocol to determine the data flow direction and format between modules; The mechanical and electrical connection requirements of each functional unit are obtained through physical connection analysis, and the physical connection scheme is determined. Extract the constraints for module collaboration from the physical connection scheme and generate the module collaboration process; If there are timing conflicts in the module collaboration process, the collaboration order is optimized through a timing adjustment algorithm to obtain the final collaboration solution. Based on the final collaboration scheme, the communication protocol between the modules is generated, and the real-time requirements for data interaction are determined. By analyzing the communication protocol, we can determine whether the data transmission meets the real-time constraints and obtain the communication protocol parameters. The performance indicators of module collaboration are extracted from the communication protocol parameters to generate the operating configuration of the modular system. The system is simulated using the aforementioned operating configuration to determine whether it meets performance requirements, and an optimized system configuration is obtained. A deployment plan for the modular system is generated based on the optimized system configuration; The deployment scheme is used to verify whether the collaboration between modules is stable, and to determine the final deployment parameters.

7. The integrated design method of an airtightness testing fixture and testing system according to any one of claims 1-3, characterized in that, S106 includes: The system acquires operational status data from the clamping module, inflation system, and sorting module. It collects operational parameters from each module using sensors and stores them in a pre-set database to obtain a structured operational status dataset. The running status dataset is processed using an association rule mining algorithm to analyze the correlation between the running status of each module, generate a data linkage model between modules, and determine the rules for generating real-time data streams. A data stream channel is established based on the real-time data stream generation rules. Dynamic data is extracted from the running status dataset and transmitted to the analysis node using message queue technology to obtain a real-time data stream. If the transmission delay of the real-time data stream exceeds a preset threshold, the priority of the message queue is adjusted, and the bandwidth of the data stream channel is reallocated to obtain a stable data stream channel. The ARIMA model is used to perform time series analysis on the real-time data stream to predict the operating trend of each module. Based on the prediction results, the coordination parameters between modules are adjusted to obtain the optimized module coordination efficiency. Based on the optimized module collaboration efficiency, the control logic of the system framework is adjusted, and the operating instructions of the clamp module, inflation system and sorting module are integrated using a distributed computing architecture to obtain an automated integrated and optimized system framework. By extracting dynamic change data of module collaboration efficiency from the system framework's operation logs, K-means clustering algorithm is used to analyze the efficiency change trend and determine the optimized efficiency of the system framework.

8. The integrated design method of an airtightness testing fixture and testing system according to any one of claims 1-3, characterized in that, S107 includes: Acquire real-time operational data from the inflation system and sorting module to construct a dynamic dataset containing time-series parameters; The task scheduling order is adjusted using the particle swarm optimization algorithm to obtain the optimized timing parameter configuration; Based on the optimized timing parameter configuration, the collaborative operation process of the inflation system and the sorting module is simulated, the collaborative efficiency index is calculated, and the overall system operating efficiency value is obtained. If the overall system operating efficiency reaches the preset threshold, a preliminary configuration scheme for the tooling system is generated based on the optimized timing parameters, and the tooling system parameter set is obtained. The tooling system parameter set is quality verified by the testing system, the verification result data is obtained, and it is determined whether it meets the requirements of the integrated solution, thus obtaining the tooling parameter set that has passed the test. A genetic algorithm is used to iteratively optimize the tooling parameter set that has passed the inspection, so as to obtain the final tooling parameter set; By integrating the final tooling parameter set with the detection system data, an integrated solution for the automated integrated system is generated, and the final configuration of the system framework is determined. Based on the final configuration, the timing parameters of the inflation system and sorting module are dynamically updated, and the system operating efficiency is verified using a rule-based judgment method to obtain the operating efficiency confirmation result of the integrated solution.

9. The integrated design method of an airtightness testing fixture and testing system according to any one of claims 1-3, characterized in that, S108 includes: Data on detection accuracy and stability are obtained from the integrated solution. Outliers are removed using data cleaning techniques to obtain the first dataset. The first dataset is processed using statistical analysis algorithms to calculate the variance and bias of the detection results and obtain accuracy statistics. If the variance and deviation in the accuracy statistics are both lower than the preset standard, the detection accuracy is determined to meet the requirements, and an accuracy judgment result is generated. Based on the accuracy determination results, key feature parameters are extracted from the qualified test data to obtain the airtightness feature set; The airtightness feature set is modeled using a regression analysis algorithm to generate tooling design parameters, thus obtaining a preliminary design parameter set; The preliminary design parameter set was adjusted using a geometric optimization algorithm to obtain the final airtightness testing tooling design parameters; Core parameters are extracted from the final airtightness testing fixture design parameters to generate a digital model of the airtightness testing fixture.

Images