An automated production-based air tightness detection line

Abstract

The application discloses a kind of air tightness detection line based on automation production, it is related to the technical field of air tightness detection, the present application aims at solving the problem of detection efficiency, the present application includes control system and execution hardware, the execution hardware includes detection mechanism, detection table, control cabinet, electrical cabinet, transfer manipulator and storage rack, the detection mechanism and control cabinet are installed on detection table.The scheme realizes the full-process automation of "workpiece transfer-positioning-sealing-air filling detection-sorting" by execution hardware, and through the MES data docking module, the detection data is uploaded to the production manufacturing execution system in real time, the association of detection data and production information is realized, the whole-process quality traceability is supported, and the optimization and quality control of production process are facilitated.

Description

Technical Field

[0001] This invention relates to the technical field of airtightness testing, specifically an airtightness testing line based on automated production. Background Technology

[0002] In the automated production of precision parts such as turbocharger housings, airtightness is a core indicator for ensuring product performance. Traditional manual or semi-automatic inspection methods suffer from low efficiency, poor accuracy, and inability to achieve full-process traceability.

[0003] Limitations of manual inspection: It relies on manual operation of inflation and observation of pressure changes, is easily affected by human factors, has poor consistency of inspection results, cannot accurately locate leaks, and has high repair costs.

[0004] Semi-automatic detection bottleneck: Some automated equipment can only perform single-dimensional judgment of pressure detection, which is easily affected by fluctuations in ambient temperature and sealing force, resulting in misjudgment. In addition, it lacks the ability to locate leaks by multi-modal data fusion, making it difficult to meet the high-precision detection needs of high-end manufacturing.

[0005] Lack of production traceability: Traditional testing methods cannot be integrated with the Manufacturing Execution System (MES), and the testing data is scattered, making it impossible to achieve full-process quality traceability from raw materials to finished products, which is not conducive to the optimization of the production process and quality control. Summary of the Invention

[0006] To address the aforementioned problems, i.e., the issues raised in the background art, this invention proposes an airtightness testing line based on automated production, comprising a control system and execution hardware. The execution hardware includes a testing mechanism, a testing table, a control cabinet, an electrical cabinet, a transfer robot, and a storage rack. The testing mechanism and control cabinet are mounted on the testing table, and the storage rack and electrical cabinet are arranged around the testing table. The electrical cabinet and control cabinet are electrically connected to the testing mechanism. The transfer robot is positioned between the testing table and the storage rack. The testing mechanism includes a slide rail mounting plate mounted on the testing table. A slide rail is positioned at the top center of the slide rail mounting plate. An N-shaped frame is mounted above the slide rail mounting plate, and the slide rail passes through a cavity below the N-shaped frame. A slide table is slidably engaged above the slide rail. A slide table cylinder is mounted above the slide rail mounting plate, and the telescopic end of the slide table cylinder is connected to the bottom of the slide table. A positioning groove is formed at the top center of the slide table, and a positioning module is detachably mounted on one side of the positioning groove.

[0007] A limit switch is provided on one side of the slide cylinder to detect whether the slide has moved to the detection station.

[0008] An industrial camera is installed on one side of the slide to detect whether the workpiece to be inspected is placed in the correct position.

[0009] The N-shaped frame is symmetrically equipped with L-shaped frames on both sides. The L-shaped frame is equipped with a nozzle cylinder. The nozzle cylinder is equipped with a nozzle mounting module on its telescopic end. The nozzle mounting module is equipped with a nozzle that can be inserted into the air passage of the workpiece to be tested on the side away from the nozzle cylinder. The nozzle mounting module has an airflow channel that can be connected to the nozzle and the air source respectively.

[0010] A capping cylinder is installed above the N-type frame, and a capping mounting plate is provided in the cavity below the N-type frame. The telescopic end of the capping cylinder extends into the cavity below the N-type frame and connects with the capping mounting plate. A guide post for limiting the movement direction of the capping mounting plate is installed above the capping mounting plate, and the guide post penetrates the N-type frame. A capping plate is provided below the capping mounting plate, and a sealing gasket capable of pressing the workpiece to be tested and sealing the opening above the workpiece to be tested is installed below the capping plate.

[0011] The detection mechanism is equipped with a sensor assembly, which includes a temperature sensor, a multi-point pressure sensor, and an acoustic imager. The temperature sensor is located inside the N-type frame. The multiple sensing points of the multi-point pressure sensor are respectively located on the pressure cap and the air nozzle. The multiple sensing points of the acoustic imager are evenly distributed on the inner wall of the positioning groove inside the slide.

[0012] A further feature of the present invention is that the top view structure of the air nozzle mounting module is a two-stage stepped shape, the air nozzle is mounted on the second step of the two-stage stepped shape, and a top rod capable of abutting against the side wall of the positioning module is installed on the first step of the two-stage stepped shape.

[0013] A further feature of the present invention is that a sliding groove is provided below the pressure cover mounting plate, a slider is slidably engaged inside the sliding groove, a bolt capable of abutting the slider is installed on one side of the sliding groove, and the slider is fixedly installed above the pressure cover.

[0014] A further configuration of the present invention is as follows: the control system includes an HMI interaction layer, a decision algorithm layer, and a control execution layer. The HMI interaction layer includes a leak point visualization module that integrates a 3D model of the workpiece to be inspected and can intuitively display the three-dimensional coordinates of the leak point; a detection parameter setting module that can customize the detection pressure threshold, detection sensitivity, and compensation coefficient; and an MES data interface module that can interface with the execution hardware system.

[0015] The decision algorithm layer includes a multimodal fusion localization algorithm module that integrates acoustic cloud maps and pressure gradient data to locate leaks through cross-validation algorithm, an intelligent threshold adaptive algorithm module that can introduce compensation parameters, and a data filtering module that uses FFT spectrum analysis technology to filter out equipment operating noise and environmental interference signals.

[0016] The multimodal fusion localization algorithm module acquires leakage ultrasonic signals in the 20kHz-100kHz frequency band using an acoustic imager, extracts leakage feature signals through FFT spectrum analysis, generates an acoustic hotspot cloud map, initially locates the leakage area, acquires internal pressure changes of the shell using multi-point pressure sensors at a sampling rate of 0.1Hz, calculates the pressure attenuation gradient of each monitoring point, filters out areas where the pressure drop rate exceeds a threshold, cross-validates with the acoustic hotspot area, narrows the leakage range to a single detection point, and calculates the three-dimensional spatial coordinates of the leakage point using triangulation by combining the positioning data of the detection slide and the installation position of the air nozzle.

[0017] The intelligent threshold adaptive algorithm module collects three core compensation parameters in real time: ambient temperature, gland sealing force, and shell material expansion coefficient. It then establishes a multivariate linear compensation model and adjusts the pressure attenuation threshold based on the model's calculation results. The multivariate linear compensation model formula is P. 阈值 =P 基础 +k1×ΔT+k2×ΔF+k3×ΔE where, P 阈值 P is the dynamically adjusted pressure threshold. 基础 The preset basic threshold is defined as k1, k2, and k3, which are the corresponding compensation coefficients. ΔT, ΔF, and ΔE are the deviation values ​​of temperature, sealing force, and material expansion, respectively.

[0018] The control execution layer includes a PLC core responsible for receiving HMI commands, processing sensor data, and controlling and executing actions; a sensor data acquisition module for simultaneously collecting detection data from various sensors; and a communication gateway that enables data exchange between different types of settings.

[0019] The beneficial technical effects of this invention are as follows: This solution automates the entire process of "workpiece transfer - positioning - sealing - inflation detection - sorting" through hardware execution. Simultaneously, through the MES data interface module, the detection data is uploaded to the manufacturing execution system in real time, realizing the correlation between detection data and production information, supporting full-process quality traceability, facilitating production process optimization and quality control. A closed-loop compensation mechanism of "environmental parameter acquisition - compensation model calculation - dynamic threshold adjustment" is constructed through the intelligent threshold adaptive algorithm module. The pressure attenuation threshold is dynamically adjusted through a multivariate linear compensation model, adapting to the detection needs of different environments and shell materials. This system addresses the issue of misjudgment caused by thermal expansion and contraction and inadequate sealing, improving the versatility of testing. After cross-validation of data from the multimodal fusion positioning algorithm module, it calculates 3D coordinates by combining slide positioning and nozzle position information, effectively avoiding misjudgment from a single testing method. It provides maintenance personnel with accurate leak location references. The testing mechanism adopts a modular design, and the positioning module can be flexibly adjusted according to the workpiece's air passage position to adapt to the testing needs of different housing models. Through collaborative operation of automated equipment, the testing cycle of a single workpiece is significantly shortened, and the testing process requires no manual intervention, reducing human error and adapting to the cycle time requirements of large-scale automated production. Attached Figure Description

[0020] Figure 1 A top-view structural diagram of the present design is shown.

[0021] Figure 2 A top view of the testing mechanism is shown.

[0022] Figure 3 A schematic diagram of the air nozzle mounting module structure is shown.

[0023] Figure 4 A schematic diagram of the main structure of the testing mechanism is shown.

[0024] Figure 5 A schematic diagram of the gland structure is shown.

[0025] Figure 6 The diagram shows the configuration of each unit in the control system.

[0026] Attached figures: 1. Inspection mechanism; 101. Slide rail mounting plate; 102. Slide rail; 103. L-shaped frame; 104. Air nozzle cylinder; 105. Slide table; 106. Positioning module; 107. Cover cylinder; 108. N-shaped frame; 109. Slide table cylinder; 110. Limit switch; 111. Industrial camera; 112. Air nozzle mounting module; 113. Top rod; 114. Air nozzle; 115. Guide column; 116. Cover mounting plate; 117. Cover; 2. Inspection table; 3. Control cabinet; 4. Electrical cabinet; 5. Transfer robot; 6. Storage rack. Detailed Implementation

[0027] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0028] This invention proposes an airtightness testing line based on automated production for testing the airtightness of a turbocharger housing. The testing space is enclosed on three sides by a fence, leaving one side as the entrance / exit for transport equipment. Three workpiece storage racks 6 are placed at the entrance / exit, respectively for placing workpieces to be tested, workpieces that have passed the test, and workpieces to be tested for leaks. Workers can use forklifts or other transport tools to move the storage racks 6 at the entrance / exit that is not enclosed by the fence. A transfer robot 5 is set in the middle of the testing space. A testing platform 2 and an electrical cabinet 4 are set in the testing space away from the entrance. The testing mechanism 1 and the control cabinet 3 are both set on the testing platform 2. The testing mechanism 1 is electrically connected to the control cabinet 3 and the electrical cabinet 4. Since the electrical connection and air supply method between the control cabinet 3 and the electrical cabinet 4 and the testing mechanism are known technologies, their structural composition will not be described in detail here. The transfer robot 5 picks up the workpiece to be tested from the storage rack 6 and places it on the testing mechanism 1 to test its airtightness. After the test is completed, the transfer robot 5 places the tested workpiece back on the corresponding storage rack 6 according to the test results.

[0029] Inspection Process: The transfer robot 5 places the workpiece to be inspected into the positioning groove at the center of the slide table 105. A positioning module 106 is detachably installed on one side of the positioning groove. The positioning module 106 has a notch that can lock the air passage of the housing. The positioning module 106 can change its installation position according to the left and right positions of the air passage of each batch of workpieces. For example, if the air passage of the workpiece to be inspected is on the left side of the positioning groove, the positioning module 106 is installed on the left side of the positioning groove. An industrial camera 111 is placed on one side of the slide table 105 at its initial position for visual inspection to check whether the workpiece is placed in place. At the same time, it scans the number on the housing of the workpiece to be inspected. When the industrial camera 111 detects that the workpiece is placed in place, the control system sends an inspection process start signal. The slide table 105, driven by the slide table cylinder 109, moves along the slide rail 102 to the inspection station below the pressure cover 117. A limit switch 110 is set at the inspection station to detect whether the slide table 105 has moved into place. Then, the pressure cover cylinder 107 pushes the pressure cover 117 above the inspection station. The guide post 115 moves downward on the N-type frame and closes the opening above the supercharger housing. Then, according to the set parameters, the air nozzle cylinder 104 on one side pushes the air nozzle 114 into the air passage of the housing through the air nozzle mounting module 112. At the same time, a push rod 113 is set on one side of the air nozzle 114. The air nozzle mounting module 112 is set as a stepped structure in top view. The air nozzle 114 is installed on the second step, and the push rod 113 is set on the first step. After the air nozzle 114 is inserted into the air passage, the push rod 113 can abut against the side wall of the positioning module 106 to limit the insertion depth of the air nozzle 114 and prevent the air nozzle 114 or the air passage from being inserted too deeply. The air nozzle mounting module 112 is provided with a channel connecting the air source and the air nozzle 114. Then, the air nozzle 114 is inflated for testing. After the test is completed, the pressure cover 117 is lifted, the slide table 105 slides back to the initial position, and the transfer robot 5 transfers the workpiece to the corresponding storage rack 6 for storage according to the test results.

[0030] The pressure cap 117 is a baffle with a removable sealing gasket at the bottom. The top of the baffle is mounted on the pressure cap mounting plate 116 via a slider groove. A bolt is installed on one side of the groove to tighten the slider and restrict its movement after installation. A guide post 115 is installed above the pressure cap mounting plate 116. The guide post 115 is inserted into the N-shaped frame 108 to limit the sliding direction. The pressure cap cylinder 107 is installed at the top of the N-shaped frame 108. The telescopic end passes through the N-shaped frame and is connected to the pressure cap mounting plate 116. The nozzle cylinder 104 is installed on both sides of the N-shaped frame 108 via an L-shaped frame. The N-shaped frame has an opening for the telescopic movement of the nozzle mounting module 112. The telescopic end of the nozzle cylinder 104 is connected to the nozzle mounting module 112. The slide cylinder 109 is installed on the slide rail mounting plate 101. The telescopic end is connected to the bottom of the slide 105 and is used to drive the slide 105 to slide on the slide rail 102.

[0031] The sensor assembly consists of a temperature sensor, a multi-point pressure sensor, and an acoustic imager. The temperature sensor is located inside the N-type frame 108 near the detection station and is used to detect the ambient temperature of the detection station. The multiple sensing points of the multi-point pressure sensor are respectively set on the pressure cap and the air nozzle to monitor the pressure changes inside the workpiece in real time. The multiple points of the acoustic imager are evenly distributed on the inner wall of the positioning groove in the center of the slide.

[0032] The control system consists of an HMI interaction layer, a decision algorithm layer, and a control execution layer. The HMI interaction layer consists of a leak point 3D visualization module, a detection parameter setting module, and an MES data interface module. The decision algorithm layer consists of a multimodal fusion positioning algorithm module, an intelligent threshold adaptive algorithm module, and a data filtering module. The control execution layer consists of a PLC core, a sensor data acquisition module, and a communication gateway.

[0033] Leakage 3D Visualization Module: Integrates a 3D model of the workpiece shell to be inspected, which can intuitively display the three-dimensional coordinates of the leak. It supports zooming in and rotating to view the leak location, making it easier for maintenance personnel to accurately locate the problem.

[0034] Detection parameter setting module: Allows users to customize core detection parameters such as pressure threshold, acoustic detection sensitivity, and compensation coefficient to meet the detection needs of different housing models.

[0035] MES Data Integration Module: Enables seamless integration with the Manufacturing Execution System (MES), supporting real-time uploading of inspection data, production traceability, and data statistical analysis.

[0036] Multimodal fusion positioning algorithm module: It integrates acoustic cloud maps and pressure gradient data, and accurately locates leaks through cross-validation algorithms, controlling the leak location accuracy to the centimeter level. Through cross-validation of multi-source data, it effectively avoids misjudgment by single detection methods, such as acoustic signals being affected by environmental noise and pressure detection being affected by the expansion of the shell material, thereby improving positioning accuracy.

[0037] Algorithm logic:

[0038] 1. Initial screening using acoustic cloud map: The acoustic imager acquires leakage ultrasonic signals in the 20kHz-100kHz frequency band, extracts leakage characteristic signals through FFT spectrum analysis, generates an acoustic hotspot cloud map, and initially locates the leakage area (accuracy to 10cm level).

[0039] 2. Pressure gradient verification: Multi-point pressure sensors collect pressure changes inside the housing at a sampling rate of 0.1Hz, calculate the pressure attenuation gradient at each monitoring point, screen out areas where the pressure drop rate exceeds the threshold, and cross-verify with acoustic hotspot areas to narrow down the leakage range to a single detection point.

[0040] 3. 3D coordinate fitting: Combining the positioning data of the detection slide and the installation position of the air nozzle, the three-dimensional spatial coordinates of the leak point are calculated by triangulation, and the positioning accuracy can reach 1cm level.

[0041] Intelligent threshold adaptive algorithm module: Incorporating compensation parameters such as ambient temperature, gland sealing force, and shell material expansion coefficient, the detection threshold is dynamically adjusted to avoid misjudgment. For different environments and different shell materials, the detection threshold is automatically adapted to avoid misjudgment caused by factors such as thermal expansion and contraction and poor sealing, thus improving the versatility of detection.

[0042] Algorithm logic: Construct a closed-loop compensation mechanism of "environmental parameter acquisition - compensation model calculation - threshold dynamic adjustment".

[0043] 1. Environmental parameter acquisition: Real-time acquisition of three core compensation parameters: ambient temperature, gland sealing force, and shell material expansion coefficient. Temperature acquisition accuracy is ±0.1℃, and sealing force acquisition accuracy is ±1N.

[0044] 2. Compensation Model Calculation: Establish a multivariate linear compensation model, the formula is: P 阈值 =P 基础 +k1×ΔT+k2×ΔF+k3×ΔE where, P 阈值 P is the dynamically adjusted pressure threshold. 基础 The preset basic threshold is defined as k1, k2, and k3, which are the corresponding compensation coefficients. ΔT, ΔF, and ΔE are the deviation values ​​of temperature, sealing force, and material expansion, respectively.

[0045] 3. Dynamic Threshold Adjustment: Based on the calculation results of the compensation model, the pressure attenuation threshold is automatically adjusted. For example, for every 5°C change in temperature, the pressure threshold is automatically adjusted by ±0.02MPa; for every 10N change in sealing force, the threshold is adjusted by ±0.01MPa.

[0046] Data filtering module: Employs FFT spectrum analysis technology to filter out equipment operating noise and environmental interference signals, thereby improving the accuracy of detection data.

[0047] Algorithm logic: It adopts "spectrum analysis + signal amplification".

[0048] 1. Spectrum Analysis Separation: Through FFT spectrum analysis, the frequency band differences between leakage ultrasonic signals (20kHz-100kHz) and equipment operating noise (less than 20kHz) and environmental interference signals (greater than 100kHz) are distinguished, and leakage characteristic signals are extracted.

[0049] 2. Adaptive signal amplification: The amplification factor is automatically adjusted according to the intensity of the leakage signal. Weak leakage signals are amplified by 10-20 times, and strong leakage signals are amplified by 1-5 times, thereby improving detection sensitivity.

[0050] The core of the PLC adopts a redundant Ethernet architecture, coupled with I / O expansion modules, which is responsible for receiving HMI commands, processing sensor data, and controlling the execution of actions, ensuring the stability and real-time performance of the system.

[0051] Sensor data acquisition module: Supports AI×8 / DI×4 / DO×4 channel expansion, and can simultaneously acquire detection data from multiple pressure sensors, acoustic imagers and temperature sensors.

[0052] Communication Gateway: Supports multiple communication protocols such as Modbus TCP and OPC UA, enabling data interoperability between devices of different brands and types.

[0053] Although the invention has been described with reference to preferred embodiments, various modifications can be made thereto and components can be replaced with equivalents without departing from the scope of the invention. In particular, the technical features mentioned in the various embodiments can be combined in any manner, provided there is no structural conflict. The invention is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

[0054] In the description of this invention, terms such as "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," which indicate direction or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. These are used merely for ease of description and do not indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation; therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0055] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0056] The term "comprising" or any other similar term is intended to cover non-exclusive inclusion, such that a process, article, or apparatus / device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to those processes, articles, or apparatus / devices.

[0057] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. An airtightness testing line based on automated production, comprising a control system and execution hardware, wherein the execution hardware includes a testing mechanism (1), a testing table (2), a control cabinet (3), an electrical cabinet (4), a transfer robot (5), and a storage rack (6), wherein the testing mechanism (1) and the control cabinet (3) are mounted on the testing table (2), the storage rack (6) and the electrical cabinet (4) are arranged around the testing table (2), the electrical cabinet (4) and the control cabinet (3) are electrically connected to the testing mechanism (1), and the transfer robot (5) is arranged between the testing table (2) and the storage rack (6), characterized in that: The testing mechanism (1) includes a slide rail mounting plate (101) installed on the testing table (2). A slide rail (102) is provided in the middle of the upper part of the slide rail mounting plate (101). An N-type frame (108) is installed above the slide rail mounting plate (101), and the slide rail (102) passes through the cavity below the N-type frame (108). A slide table (105) is slidably connected above the slide rail (102). A slide table cylinder (109) is installed on the slide rail mounting plate (101), and the telescopic end of the slide table cylinder (109) is connected to the lower part of the slide table (105). A positioning groove is provided at the center of the upper part of the slide table (105), and a positioning module (106) is detachably installed on one side of the positioning groove. A limit switch (110) is provided on one side of the slide cylinder (109) for detecting whether the slide (105) has moved to the detection station. An industrial camera (111) is provided on one side of the slide (105) for detecting whether the workpiece to be tested is placed in the correct position. The N-shaped frame (108) is symmetrically equipped with L-shaped frames (103) on both sides. The L-shaped frame (103) is equipped with a nozzle cylinder (104). The nozzle cylinder (104) is equipped with a nozzle mounting module (112) on its telescopic end. The nozzle mounting module (112) is equipped with a nozzle (114) that can be inserted into the air passage of the workpiece to be tested on the side away from the nozzle cylinder (104). The nozzle mounting module (112) has an airflow channel that can be connected to the nozzle (114) and the air source respectively. A capping cylinder (107) is installed above the N-type frame (108), and a capping mounting plate (116) is provided in the cavity below the N-type frame (108). The telescopic end of the capping cylinder (107) extends into the cavity below the N-type frame (108) and connects with the capping mounting plate (116). A guide post (115) for limiting the movement direction of the capping mounting plate (116) is installed above the capping mounting plate (116), and the guide post (115) penetrates the N-type frame (108). A capping plate (117) is provided below the capping mounting plate (116), and a sealing gasket capable of pressing the workpiece to be tested and sealing the opening above the workpiece to be tested is installed below the capping plate (117). The detection mechanism (1) is equipped with a sensor assembly, which includes a temperature sensor, a multi-point pressure sensor and an acoustic imager. The temperature sensor is located inside the N-type frame (108). The multiple sensing points of the multi-point pressure sensor are respectively located on the pressure cap (117) and the air nozzle (114). The multiple sensing points of the acoustic imager are evenly distributed on the inner wall of the positioning groove inside the slide (105).

2. The airtightness testing line based on automated production according to claim 1, characterized in that: The air nozzle mounting module (112) has a top view structure of a two-stage stepped shape. The air nozzle (114) is set on the second step of the two-stage stepped shape. A top rod (113) that can abut against the side wall of the positioning module (106) is installed on the first step of the two-stage stepped shape.

3. The airtightness testing line based on automated production according to claim 1, characterized in that: A sliding groove is provided below the pressure cover mounting plate (116), and a slider is slidably engaged inside the sliding groove. A bolt capable of pressing against the slider is installed on one side of the sliding groove, and the slider is fixedly installed above the pressure cover (117).

4. The airtightness testing line based on automated production according to claim 1, characterized in that: The control system includes an HMI interaction layer, a decision algorithm layer, and a control execution layer. The HMI interaction layer includes a leak point visualization module that integrates a 3D model of the workpiece to be inspected to intuitively display the three-dimensional coordinates of the leak point, a detection parameter setting module that allows for custom settings of the detection pressure threshold, detection sensitivity, and compensation coefficient, and an MES data interface module that can interface with the execution hardware system. The decision algorithm layer includes a multimodal fusion localization algorithm module that integrates acoustic cloud maps and pressure gradient data to locate leaks through cross-validation algorithm, an intelligent threshold adaptive algorithm module that can introduce compensation parameters, and a data filtering module that uses FFT spectrum analysis technology to filter out equipment operating noise and environmental interference signals. The multimodal fusion localization algorithm module acquires leakage ultrasonic signals in the 20kHz-100kHz frequency band using an acoustic imager, extracts leakage feature signals through FFT spectrum analysis, generates an acoustic hotspot cloud map, initially locates the leakage area, acquires internal pressure changes of the shell using multi-point pressure sensors at a sampling rate of 0.1Hz, calculates the pressure attenuation gradient of each monitoring point, filters out areas where the pressure drop rate exceeds a threshold, cross-validates with the acoustic hotspot area, narrows the leakage range to a single detection point, and calculates the three-dimensional spatial coordinates of the leakage point using triangulation by combining the positioning data of the detection slide and the installation position of the air nozzle. The intelligent threshold adaptive algorithm module collects three core compensation parameters in real time: ambient temperature, gland sealing force, and shell material expansion coefficient. It then establishes a multivariate linear compensation model and adjusts the pressure attenuation threshold based on the model's calculation results. The multivariate linear compensation model formula is P. 阈值 =P 基础 +k1×ΔT+k2×ΔF+k3×ΔE where, P 阈值 P is the dynamically adjusted pressure threshold. 基础 The preset basic threshold is defined as k1, k2, and k3, which are the corresponding compensation coefficients. ΔT, ΔF, and ΔE are the deviation values ​​of temperature, sealing force, and material expansion, respectively. The control execution layer includes a PLC core responsible for receiving HMI commands, processing sensor data, and controlling and executing actions; a sensor data acquisition module for simultaneously collecting detection data from various sensors; and a communication gateway that enables data exchange between different types of settings.

Images