Air spring quality detection system and method based on machine vision

Abstract

The invention belongs to the field of quality detection, and provides an air spring quality detection system and method based on machine vision, and the method comprises the steps: obtaining standard three-dimensional models of an air spring under different pressures; applying a first pressure to the to-be-tested air spring; acquiring two-dimensional image data of the air spring to be measured at multiple angles under the first pressure; projecting a light stripe pattern to the surface of the air spring to be detected, and obtaining three-dimensional shape data of the surface of the air spring to be detected under the first pressure according to deformation of light stripes; fusing the two-dimensional image data and the three-dimensional form data to generate a first three-dimensional model of the air spring; a first standard three-dimensional model under the first pressure is obtained from the template module, texture and geometric information of the first three-dimensional model and the first standard three-dimensional model is compared, and if the difference exceeds a preset threshold value, it is determined that the quality of the air spring to be detected is unqualified.

Description

Technical Field

[0001] The present invention belongs to the field of quality inspection, and in particular relates to a system and method for inspecting air spring quality based on machine vision. Background Art

[0002] As a common shock absorbing device, air springs are widely used in many fields such as automobiles, trains, and buildings. Its main principle is to use compressed air as an elastic medium and change the elastic coefficient by adjusting the air pressure, thereby effectively reducing vibration and impact. The performance of air springs directly affects the overall effect of the shock absorbing system. Therefore, during the production and use process, the quality of air springs needs to be strictly tested and evaluated.

[0003] Traditional air spring quality inspection methods usually rely on manual visual inspection and physical measurement, which is not only inefficient but also difficult to ensure accuracy and consistency. With the development of science and technology, machine vision technology has gradually been introduced into the field of industrial inspection. It extracts visual information of objects through cameras and image processing algorithms, and can efficiently and accurately identify defects on the surface and morphology of objects.

[0004] In existing 3D vision solutions, although the technology has made some progress, there are still some inherent limitations, especially in texture detection. 3D vision technology usually focuses on the acquisition of the geometric shape and depth information of objects, but has weaker ability to detect defects that are rich in details and rely on texture information. This is because the fine features of the surface texture are often lost during the 3D reconstruction process, especially when the texture information in the image is complex or uneven. The texture itself may appear aliased, blurred or distorted in the image, resulting in inaccurate texture mapping of the 3D model, which affects the identification and analysis of defects.

[0005] In addition, as a common elastic element, the deformation characteristics of air springs (or gas springs) are directly related to external pressure. When the pressure of the air spring changes, its shape will change accordingly, usually in the form of compression or expansion. Due to the nonlinear relationship between air pressure and deformation, two-dimensional images will be affected by distortion when capturing these changes. Specifically, as deformation occurs, the original geometric structure and texture distribution in the image will be affected, and even severe deformation may occur, which is not conducive to image matching, making effective defect detection in two-dimensional images complicated and challenging. Summary of the invention

[0006] In order to solve the problems in the prior art, the present invention provides an air spring quality detection system based on machine vision, comprising the following modules: A template module, used to store a standard three-dimensional model of the air spring under different pressures, wherein the standard three-dimensional model includes surface texture and geometric information; A boost module, used for applying a first pressure to the air spring to be tested; An image acquisition module, used for acquiring two-dimensional image data of multiple angles of the air spring to be tested under a first pressure; a structured light module, used for projecting a light stripe pattern onto the surface of the air spring to be tested, and acquiring three-dimensional morphological data of the surface of the air spring to be tested under a first pressure according to the deformation of the light stripes; a data fusion processing module, used for fusing the two-dimensional image data with the three-dimensional morphological data to generate a first three-dimensional model of the air spring, wherein the first three-dimensional model includes surface texture and geometric information of the air spring to be tested under the first pressure; A defect detection module is used to obtain the first standard three-dimensional model under the first pressure from the template module, compare the texture and geometric information of the first three-dimensional model with that of the first standard three-dimensional model, and if the difference exceeds a preset threshold, determine that the quality of the air spring to be tested is unqualified.

[0007] Further, the step of projecting a light stripe pattern onto the surface of the air spring to be tested and acquiring three-dimensional morphological data of the surface of the air spring to be tested under the first pressure according to the deformation of the light stripes includes: A standard cylindrical model is pre-constructed, wherein the diameter and height of the standard cylindrical model correspond to the maximum diameter and maximum height of the air spring respectively; a first projected light stripe pattern is obtained through the standard cylindrical model, and the first projected light stripe pattern is deformed adaptively to the geometric shape of the air spring to be tested, and after the first projected light stripe pattern passes through the surface of the air spring to be tested, three-dimensional morphological data of the surface of the air spring is obtained according to the deformation information of the light stripes.

[0008] Further, the fusing the two-dimensional image data with the three-dimensional morphological data comprises: The deformation of the first projection light fringe pattern is registered with the two-dimensional image, and the two-dimensional image is mapped to the three-dimensional morphological model according to the registration result.

[0009] Furthermore, the two-dimensional image data at multiple angles completely covers the surface of the air spring to be tested.

[0010] Furthermore, during the defect detection process, the texture differences and geometric differences are compared, and weighted calculation is used to consider the weights of texture differences and geometric differences in quality judgment to obtain a difference value. If the difference exceeds a preset threshold, the quality of the air spring to be tested is judged to be unqualified, otherwise, it is judged to be qualified.

[0011] Another aspect of the present invention further provides an air spring quality detection method based on machine vision, comprising the following steps: Obtaining a standard three-dimensional model of the air spring under different pressures, and saving the standard three-dimensional model of the air spring under different pressures, wherein the standard three-dimensional model includes surface texture and geometric information; Applying a first pressure to the air spring to be tested; Acquire two-dimensional image data of multiple angles of the air spring to be tested under a first pressure; Projecting a light stripe pattern onto the surface of the air spring to be tested, and acquiring three-dimensional morphological data of the surface of the air spring to be tested under a first pressure according to the deformation of the light stripes; fusing the two-dimensional image data with the three-dimensional morphological data to generate a first three-dimensional model of the air spring, wherein the first three-dimensional model includes surface texture and geometric information of the air spring to be tested under the first pressure; A first standard three-dimensional model under the first pressure is obtained from the template module, and texture and geometric information of the first three-dimensional model are compared with those of the first standard three-dimensional model. If the difference exceeds a preset threshold, it is determined that the quality of the air spring to be tested is unqualified.

[0012] Further, the step of projecting a light stripe pattern onto the surface of the air spring to be tested and acquiring three-dimensional morphological data of the surface of the air spring to be tested under the first pressure according to the deformation of the light stripes includes: A standard cylindrical model is pre-constructed, wherein the diameter and height of the standard cylindrical model correspond to the maximum diameter and maximum height of the air spring respectively; a first projected light stripe pattern is obtained through the standard cylindrical model, and the first projected light stripe pattern is deformed adaptively to the geometric shape of the air spring to be tested, and after the first projected light stripe pattern passes through the surface of the air spring to be tested, three-dimensional morphological data of the surface of the air spring is obtained according to the deformation information of the light stripes.

[0013] Further, the fusing the two-dimensional image data with the three-dimensional morphological data comprises: The deformation of the first projection light fringe pattern is registered with the two-dimensional image, and the two-dimensional image is mapped to the three-dimensional morphological model according to the registration result.

[0014] Furthermore, the two-dimensional image data at multiple angles completely covers the surface of the air spring to be tested.

[0015] Furthermore, during the defect detection process, the texture differences and geometric differences are compared, and weighted calculation is used to consider the weights of texture differences and geometric differences in quality judgment to obtain a difference value. If the difference exceeds a preset threshold, the quality of the air spring to be tested is judged to be unqualified, otherwise, it is judged to be qualified.

[0016] The present invention effectively solves the problems existing in the background technology by designing an air spring quality detection system and method based on machine vision. The specific beneficial effects are as follows: Through the fusion of multi-dimensional information, especially the joint processing of 3D images and texture images, the shortcomings of traditional 3D vision solutions in texture recognition can be made up. This solution can more accurately capture the detailed texture of the object surface, thereby improving the accuracy of defect detection, especially in the case of complex texture information.

[0017] Considering the deformation characteristics of air springs when pressure changes, the system can dynamically adjust the image acquisition and analysis methods to deal with image distortion caused by deformation. This adaptability enables the system to process deformation data under different pressure states in real time, ensuring that possible defects can still be accurately detected during the pressure change process.

[0018] By combining the distortion of the 3D surface, the system can match the 2D image under complex deformation and distortion, thus facilitating the accurate identification of surface defects. This ability to improve accuracy is particularly important in automated production and quality inspection, helping to improve the quality control level of the production process and reduce human errors. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 It is a structural diagram of the system of the present invention. DETAILED DESCRIPTION

[0021] Below, the invention is preferably described in conjunction with the accompanying drawings and specific implementation methods.

[0022] This embodiment solves the above problem through the following steps: In one embodiment, reference Figure 1 The present invention provides an air spring quality inspection system based on machine vision, which aims to realize quality assessment and defect detection of air springs under different working conditions through efficient and accurate visual analysis means.

[0023] In the present invention, the air spring is a shock absorbing device that uses compressed air as an elastic medium and is widely used in shock absorbing systems in industries such as automobiles, trains, and construction. The characteristics of the air spring are its flexibility and adjustability, and its elastic coefficient can be adjusted according to changes in load or compressed air pressure to meet the needs of different working conditions.

[0024] Specifically, the system of the present invention includes the following modules: The template module is used to store a standard three-dimensional model of an air spring under different pressures, wherein the standard three-dimensional model includes surface texture and geometric information.

[0025] The template module described in the present invention refers to a module specifically used to store and manage the standard three-dimensional models corresponding to air springs under different inflation pressures or working conditions. The template module can provide a standard reference model for comparison and detection during the quality inspection of air springs. The standard three-dimensional model consists of two parts, namely surface texture information and geometric information, which together constitute the ideal state or reference form of the air spring under specific pressure conditions.

[0026] The main function of the template module is to store and provide standard three-dimensional models, which represent the standard shapes of air springs under various working pressures.

[0027] The template module saves a set of standard 3D models obtained through experiments and measurements, which can accurately reflect the ideal shape of air springs under different working pressures. The standard model is designed and measured according to the working conditions of air springs in actual use (such as different loads, air pressures, etc.).

[0028] During the quality inspection process of air springs, the standard 3D model provided by the template module is used as a comparison benchmark for comparative analysis with the actual detected 3D data of the air spring, so as to identify parts that do not meet the standards, such as morphological changes, defects, deformations, etc.

[0029] The template module not only saves the standard model in a single state, but also includes the standard three-dimensional model of the air spring under different inflation pressures, loads or working environment conditions, so that the system can automatically select the corresponding reference model for comparison according to the actual working conditions during detection.

[0030] The standard 3D model includes surface texture and geometric information. Surface texture information refers to the two-dimensional image data of the surface details of the air spring, including visual features such as color, surface texture, scratches, and wear. In the model, these surface information are attached to the three-dimensional surface through texture mapping technology, so that during the inspection process, not only the geometric shape of the spring can be obtained, but also the subtle changes on its surface can be identified. Geometric information refers to the three-dimensional data that describes the shape of the air spring, including key structural features such as surface curvature, edge profile, size, and shape. Geometric information is generally obtained through three-dimensional scanning technology (such as laser scanning, structured light scanning, etc.) and expressed through point cloud data, three-dimensional mesh, etc. Geometric information provides key morphological data for quality inspection, ensuring that the inspection system can identify whether the size and shape of the air spring meet the standards.

[0031] The standard three-dimensional model can be stored in the template module using different technologies according to actual needs, such as STL, OBJ, etc. The specific storage method and form do not affect the main scheme of the present invention and are not specifically limited in this embodiment.

[0032] The boost module is used to apply a first pressure to the air spring to be tested.

[0033] The boost module in the present invention refers to a device module specifically used to apply a certain pressure to the air spring to be tested during the air spring quality test. The main function of the boost module is to simulate the load or working condition of the air spring under a specific working state by applying a first pressure during the test process, so as to ensure that the performance and quality of the air spring to be tested under the simulated state can be accurately evaluated.

[0034] The booster module can apply a first pressure to the air spring to be tested, and the first pressure is set according to the working requirements, test standards or detection tasks of the air spring. The first pressure is usually the typical working pressure of the air spring under normal use, or simulates the load pressure under certain specific conditions.

[0035] By applying the first pressure, the booster module simulates the working conditions that the air spring may experience during actual use, ensuring that key parameters such as the shape change and size change of the air spring under different pressures can be accurately detected. The application of the first pressure helps trigger the deformation or surface defects of the air spring, thus providing a basis for subsequent quality inspections.

[0036] The booster module can not only apply a fixed first pressure, but also realize adjustable pressure control, so that the system can adjust the applied pressure value according to the detection requirements. By applying different pressures multiple times, the performance data of the air spring under different working conditions can be obtained, providing a more comprehensive quality evaluation for the detection system.

[0037] The boost module can implement the function of applying pressure in a variety of ways, such as an air pump, a hydraulic device, etc. As long as the set pressure can be applied, this embodiment does not specifically limit the implementation method.

[0038] The image acquisition module is used to obtain two-dimensional image data of multiple angles of the air spring to be tested under a first pressure.

[0039] The image acquisition module in the present invention refers to a device module specifically used to collect image data of the air spring to be tested under specific pressure conditions. The module captures two-dimensional images of the air spring under the first pressure from different angles by installing multiple camera devices to provide the required image data for subsequent quality inspection, three-dimensional modeling and defect analysis.

[0040] The main function of the image acquisition module is to capture the morphological changes and surface information of the air spring to be tested after the first pressure is applied through a camera device. The image acquisition module is used to obtain two-dimensional image data from multiple different angles when the air spring is under the first pressure. These image data include the surface texture, geometric shape and possible defect characteristics of the air spring. In order to obtain the morphological information of the air spring more comprehensively, the image acquisition module uses multiple cameras to collect images from different angles. By obtaining image data from multiple perspectives, a more accurate quality analysis of the air spring can be performed, especially in terms of the complex shape and texture of the spring surface.

[0041] The image acquisition module includes an image sensor and a camera. The image sensor is the core component of the image acquisition module, which is responsible for converting the shape of the air spring to be tested under a specific pressure into processable digital image data. The image sensor can be a CMOS sensor or a CCD sensor, which can provide high-resolution image quality to clearly record the surface information and possible defects of the air spring. The image acquisition module contains multiple cameras, which are arranged in the form of multiple camera arrays to capture image data of the air spring from different angles. Each camera can adjust the shooting angle and distance according to the position and shape of the air spring to be tested to ensure the integrity and accuracy of the image data.

[0042] In order to ensure that all texture data are obtained, the two-dimensional image data at multiple angles completely covers the surface of the air spring to be tested.

[0043] The structured light module is used to project a light stripe pattern onto the surface of the air spring to be tested, and acquire three-dimensional morphological data of the surface of the air spring to be tested under a first pressure according to the deformation of the light stripes.

[0044] The structured light module in the present invention is a device module that uses structured light technology to collect three-dimensional morphology. Structured light technology projects a light stripe pattern of a known pattern onto the surface of an object, and then captures the deformation of the light stripes on the surface to infer the three-dimensional morphological information of the object. In the application of the present invention, the structured light module is used to obtain the surface three-dimensional morphological data of the air spring to be tested under the first pressure, so as to evaluate and detect its quality.

[0045] The main function of the structured light module is to obtain the three-dimensional morphological data of the surface of the air spring to be tested through the projection of light stripe patterns and deformation detection. Specific functions include: The structured light module uses a projection device to project a specific light stripe pattern onto the surface of the air spring to be tested. The shape, density and direction of these stripe patterns are known and are used for subsequent 3D reconstruction.

[0046] The geometry and texture of the surface of the air spring to be tested will cause deformation of the projected light stripes. By capturing these deformed light stripe patterns with a camera, the structured light module can calculate the three-dimensional surface morphology of the air spring to be tested based on the deformation.

[0047] By analyzing the deformed light stripe pattern and combining known optical principles and geometric algorithms, the structured light module can calculate and output the three-dimensional morphological data of the air spring surface to be tested. This data not only contains the geometric outline of the object, but also the surface detail information.

[0048] The processing module is responsible for analyzing and calculating the captured light streak deformation data. Through the image processing algorithm, the light streak deformation is first identified, and then the three-dimensional surface morphology of the air spring to be tested is calculated using the known geometric model and optical transformation relationship. The processing module can also output the results in the form of three-dimensional coordinate points, surface grids or depth maps as needed.

[0049] Furthermore, a standard cylindrical model is pre-constructed, and the diameter and height of the standard cylindrical model correspond to the maximum diameter and maximum height of the air spring respectively; a first projected light stripe pattern is obtained through the standard cylindrical model, and the first projected light stripe pattern is deformed adaptively to the geometric shape of the air spring to be tested. After the first projected light stripe pattern passes through the surface of the air spring to be tested, three-dimensional morphological data of the air spring surface is obtained based on the deformation information of the light stripes.

[0050] The construction of the standard cylinder model is based on the maximum diameter and maximum height of the air spring. This model is used as a reference standard for projecting light fringe patterns. By generating the standard light fringe pattern under ideal conditions and deforming it, the deformation of the surface of the air spring to be tested under different pressures can be simulated.

[0051] The structured light method is to project a known light stripe pattern onto the surface of an object and calculate the three-dimensional shape of the object based on the deformation of the light stripes caused by the geometric shape of the object surface. In this scheme, a light stripe pattern is first generated based on the geometric features of the standard cylindrical model, and then the pattern is projected onto the surface of the air spring to be tested. Since the surface features of the air spring will cause the deformation of the light stripes, after the camera equipment captures these deformed images, the three-dimensional shape data of the object to be tested is calculated through the algorithm.

[0052] By analyzing the deformed light stripe pattern, the computer vision algorithm can accurately invert the surface 3D data of the air spring to be tested. These 3D data contain the surface geometry information and texture features of the air spring, making it possible to accurately detect whether its shape meets the standard requirements.

[0053] This method can accurately capture the three-dimensional geometric shape of the surface of the air spring to be tested, with high measurement accuracy. The three-dimensional information is obtained by the deformation of the light stripes, which can accurately reflect the deformation characteristics of the air spring under different pressures. By pre-building a standard cylindrical model and adapting the projection of the light stripes, the distortion caused by the change of the surface morphology can be effectively reduced, ensuring the accuracy of the three-dimensional data, thereby improving the reliability of quality inspection.

[0054] The data fusion processing module is used to fuse the two-dimensional image data with the three-dimensional morphological data to generate a first three-dimensional model of the air spring, wherein the first three-dimensional model includes surface texture and geometric information of the air spring to be tested under the first pressure.

[0055] The data fusion processing module in the present invention is a module for fusing various types of measurement data. It generates a first three-dimensional model of the air spring to be tested by combining two-dimensional image data with three-dimensional morphological data. The three-dimensional model contains not only geometric shape information of the air spring, but also surface texture information, thereby achieving comprehensive and accurate modeling of the air spring under the first pressure. This process provides accurate data support for subsequent quality evaluation and performance analysis.

[0056] The main function of the data fusion processing module is to establish a connection between the two-dimensional image data and the three-dimensional morphological data, effectively fuse these two different types of data, and generate a unified three-dimensional model. Through this model, the surface morphology, texture characteristics and geometric structure of the air spring to be tested under the first pressure can be fully described. The specific functions are as follows: The 2D image data provides high-resolution information about the surface details of the air spring to be tested, including color, texture and other surface features, while the 3D morphology data provides geometric structure information of the object surface, such as depth, contour and shape. Through the data fusion processing module, the 2D image and 3D morphology data can be combined in the same coordinate system to form a complete 3D model.

[0057] During the fusion process, the data fusion processing module uses image processing algorithms and three-dimensional reconstruction algorithms to match the texture information of the two-dimensional image with the geometric structure of the three-dimensional form. The generated three-dimensional model can simultaneously include the geometric shape and surface texture of the air spring, reflecting its true state under the first pressure.

[0058] Through fusion, the texture information in the two-dimensional image is mapped onto the surface of the three-dimensional geometric model, thereby enhancing the detail performance of the model. The geometric information in the model is obtained through three-dimensional morphological data, ensuring that the geometric features such as surface curvature, boundaries and volume are accurately represented.

[0059] The data fusion processing module can improve the accuracy and detail display of the final 3D model by effectively combining data from different sources, especially in the combination of surface texture and geometric structure, greatly enhancing the realism and usability of the model.

[0060] The data fusion processing module mainly consists of a data receiving and preprocessing unit, a data alignment and fusion unit, and a 3D modeling unit. Each unit works together to complete the entire process from data receiving, preprocessing to the final 3D model generation.

[0061] The data receiving and preprocessing unit obtains two-dimensional image data through the camera device, including surface images of the air spring to be tested at different angles. These images contain information such as surface color, texture, light reflection, etc., which are used for subsequent texture mapping. The three-dimensional morphological data obtained by devices such as structured light modules provide geometric information of the air spring to be tested, including surface contour, curvature, depth and other data. Three-dimensional morphological data is generally represented in the form of point cloud or grid. After receiving these data, the preprocessing unit performs preliminary processing on them, including denoising, data completion, image enhancement and other operations to improve the quality and availability of the data.

[0062] Data alignment and fusion unit, 2D image data and 3D morphological data come from different sensors and have different coordinate systems, so they need to be spatially aligned. The alignment algorithm matches the feature points (such as edges, corners, etc.) in the image and 3D data, thereby aligning the 2D image and 3D morphological data in the same coordinate system. The aligned 2D image data and 3D morphological data are synthesized through a fusion algorithm. This process usually uses texture mapping technology to map the texture information of the 2D image to the surface of the 3D model. In addition, the geometric reconstruction algorithm ensures that the geometric features of the 3D morphological data are correctly presented. Finally, the fusion result generates a complete 3D model containing surface texture and geometric information.

[0063] The 3D modeling unit is responsible for reconstructing the model based on the fused data. The 3D geometry of the air spring is generated by fusing the point cloud data and the texture image. This process usually uses a 3D reconstruction algorithm (such as the voxel method, the surface reconstruction method, etc.) to accurately construct the geometry of the object surface. The texture information in the 2D image data is mapped to the surface of the 3D model. This process calculates the coordinate relationship between the image and the 3D data, and corresponds each pixel in the image to the corresponding point on the surface of the 3D model, thereby achieving accurate texture mapping.

[0064] Furthermore, the deformation of the first projection light stripe pattern is registered with the two-dimensional image, and the two-dimensional image is mapped to the three-dimensional morphological model according to the registration result.

[0065] In the above steps, the structured light module projects the first projected light stripe pattern onto the surface of the air spring to be tested, and obtains the deformation data of the light stripes after reflection. In order to accurately combine the surface texture with the three-dimensional geometric morphology data, the system uses image registration technology to register the deformation of the first projected light stripe pattern with the two-dimensional image data. The registration process includes aligning the two-dimensional images from different perspectives with the three-dimensional model obtained by the deformation of the light stripes through algorithms such as feature extraction, matching and geometric transformation. Specifically, the registration method may include technologies based on feature point matching, edge detection or full-image registration, and through optimization algorithms, reduce the errors caused by different perspectives or different shooting angles, thereby achieving high-precision alignment of the two-dimensional image with the three-dimensional morphology data. Finally, the registered two-dimensional image will be mapped to the surface of the three-dimensional morphology model to form a complete three-dimensional model containing surface texture and geometric information, providing intuitive and accurate data support for subsequent quality inspections.

[0066] Through precise registration technology, the texture data of the two-dimensional image can be efficiently combined with the three-dimensional morphological data, effectively solving the errors caused by the shooting angle and object deformation, ensuring the accurate mapping of the texture and the true reflection of the geometric form. By registering the light streak deformation with the two-dimensional image, the texture distortion phenomenon can be avoided, especially in the case of complex air spring surface deformation, the texture data can be accurately fitted to the three-dimensional model to enhance the expression effect of the texture.

[0067] By fusing two-dimensional image data with three-dimensional morphological data, the generated three-dimensional model not only has the geometric structural characteristics of the air spring, but also can accurately present its surface texture, with high detail expression. The data fusion processing module can effectively reconstruct the surface texture and geometric features to ensure the accuracy and authenticity of the model, especially in the detection of surface defects and small deformations. The fused three-dimensional model has a high degree of visualization and can accurately present the morphological changes of the air spring to be tested under the first pressure, which is convenient for subsequent analysis, evaluation and display.

[0068] A defect detection module is used to obtain the first standard three-dimensional model under the first pressure from the template module, compare the texture and geometric information of the first three-dimensional model with that of the first standard three-dimensional model, and if the difference exceeds a preset threshold, determine that the quality of the air spring to be tested is unqualified.

[0069] The defect detection module in the present invention is an important component of the air spring quality detection system. Its main function is to compare the difference between the three-dimensional model of the air spring to be tested and the standard three-dimensional model, so as to determine whether the air spring to be tested meets the predetermined quality standards. The module analyzes the texture and geometric information, and based on the setting of the difference threshold, accurately identifies possible surface defects or geometric errors, and then evaluates whether the quality of the air spring is qualified. Specifically, the defect detection module ensures that the various performance indicators of the air spring to be tested meet the quality standards and meet the product requirements by comparing with the first standard three-dimensional model provided by the template module.

[0070] The defect detection module mainly consists of a standard 3D model acquisition unit, a texture comparison unit, a geometry comparison unit, a difference calculation and determination unit, and a result output unit. Each unit works together to achieve the entire process from comparative analysis of the standard model and the model to be tested to final quality determination through a series of data processing steps.

[0071] Standard 3D model acquisition unit, the standard 3D model is a 3D model generated by the template module based on the air spring design specifications and process requirements, as a reference for subsequent comparison. The surface texture and geometric information in the standard model are pre-set and have been quality verified. The standard model is generated under a specific ambient pressure (including the first pressure) to ensure that it represents the actual performance of the air spring under working conditions. The template module will provide the 3D model data under this pressure condition.

[0072] Texture comparison unit, the texture comparison unit extracts surface texture information from the three-dimensional model of the air spring to be tested, including surface color, smoothness, defects (such as cracks, bubbles, scratches, etc.) and other surface features. The texture comparison unit compares the texture information of the air spring to be tested with the texture information in the standard three-dimensional model. The difference between the two is calculated through image processing technology (such as grayscale difference, edge detection, texture mapping, etc.). If there is a significant deviation between the texture of the model to be tested and the standard model, it is considered to be defective.

[0073] The geometry comparison unit extracts geometric information from the three-dimensional model of the air spring to be tested, including surface contour, size, curvature, volume, etc. The unit extracts geometric features such as shape and boundary by analyzing the point cloud or mesh model. The geometry comparison unit compares the geometric information of the model to be tested with the geometric information in the standard three-dimensional model. The geometry difference detection algorithm calculates the difference between the two in terms of size, shape and surface curvature. If the difference exceeds the set tolerance range, it is judged as unqualified.

[0074] The difference calculation and judgment unit comprehensively calculates the difference data output by the texture comparison unit and the geometric comparison unit, and judges whether the air spring to be tested meets the quality standards in combination with the preset difference threshold. The difference calculation usually uses a weighted calculation method, considering the weight of texture difference and geometric difference in quality judgment. If the difference exceeds the preset threshold, the quality of the air spring to be tested is judged to be unqualified. Otherwise, it is judged to be qualified. The judgment result will serve as the basis for subsequent processing (such as scrapping, repair, retesting, etc.).

[0075] The defect detection module will feedback the quality judgment results to the user or control system through the result output unit. The output results can be displayed as qualified, unqualified or pending further inspection. The test results can be stored in the database and a test report can be generated, which records in detail the quality status of the air spring to be tested, the differences during the test process and the final quality judgment.

[0076] On the other hand, the present invention also provides an air spring quality detection method based on machine vision, comprising: Obtaining a standard three-dimensional model of the air spring under different pressures, and saving the standard three-dimensional model of the air spring under different pressures, wherein the standard three-dimensional model includes surface texture and geometric information; Applying a first pressure to the air spring to be tested; Acquire two-dimensional image data of multiple angles of the air spring to be tested under a first pressure; Projecting a light stripe pattern onto the surface of the air spring to be tested, and acquiring three-dimensional morphological data of the surface of the air spring to be tested under a first pressure according to the deformation of the light stripes; fusing the two-dimensional image data with the three-dimensional morphological data to generate a first three-dimensional model of the air spring, wherein the first three-dimensional model includes surface texture and geometric information of the air spring to be tested under the first pressure; A first standard three-dimensional model under the first pressure is obtained from the template module, and texture and geometric information of the first three-dimensional model are compared with those of the first standard three-dimensional model. If the difference exceeds a preset threshold, it is determined that the quality of the air spring to be tested is unqualified.

[0077] The prior art mentioned in the above background technology section and specific embodiment section of the present invention can be used as part of the present invention to understand the meaning of some technical features or parameters.

Claims

1. An air spring quality detection system based on machine vision, characterized in that: The detection system includes the following modules: A template module, used to store a standard three-dimensional model of the air spring under different pressures, wherein the standard three-dimensional model includes surface texture and geometric information; A boost module, used for applying a first pressure to the air spring to be tested; An image acquisition module, used for acquiring two-dimensional image data of multiple angles of the air spring to be tested under a first pressure; A structured light module, used for projecting a light stripe pattern onto the surface of the air spring to be tested, and acquiring three-dimensional morphological data of the surface of the air spring to be tested under a first pressure according to the deformation of the light stripes; a data fusion processing module, used for fusing the two-dimensional image data with the three-dimensional morphological data to generate a first three-dimensional model of the air spring, wherein the first three-dimensional model includes surface texture and geometric information of the air spring to be tested under the first pressure; A defect detection module is used to obtain the first standard three-dimensional model under the first pressure from the template module, compare the texture and geometric information of the first three-dimensional model with that of the first standard three-dimensional model, and if the difference exceeds a preset threshold, determine that the quality of the air spring to be tested is unqualified.

2. The air spring quality detection system based on machine vision according to claim 1 is characterized in that: The step of projecting a light stripe pattern onto the surface of the air spring to be tested and acquiring three-dimensional morphological data of the surface of the air spring to be tested under the first pressure according to the deformation of the light stripes comprises: A standard cylindrical model is pre-constructed, wherein the diameter and height of the standard cylindrical model correspond to the maximum diameter and maximum height of the air spring respectively; a first projected light stripe pattern is obtained through the standard cylindrical model, and the first projected light stripe pattern is deformed adaptively to the geometric shape of the air spring to be tested, and after the first projected light stripe pattern passes through the surface of the air spring to be tested, three-dimensional morphological data of the surface of the air spring is obtained according to the deformation information of the light stripes.

3. The machine vision-based air spring quality detection system according to claim 2 is characterized in that: The fusing of the two-dimensional image data with the three-dimensional morphological data comprises: The deformation of the first projection light fringe pattern is registered with the two-dimensional image, and the two-dimensional image is mapped to the three-dimensional morphological model according to the registration result.

4. The machine vision-based air spring quality detection system according to claim 1 is characterized in that: The two-dimensional image data at multiple angles completely cover the surface of the air spring to be tested.

5. The machine vision-based air spring quality detection system according to claim 1 is characterized in that: During the defect detection process, the texture differences and geometric differences are compared, and weighted calculation is used to consider the weights of texture differences and geometric differences in quality judgment to obtain the difference value. If the difference exceeds the preset threshold, the quality of the air spring to be tested is judged to be unqualified, otherwise, it is judged to be qualified.

6. A method for detecting the quality of an air spring based on machine vision, characterized in that: The method comprises the following steps: Obtaining a standard three-dimensional model of the air spring under different pressures, and saving the standard three-dimensional model of the air spring under different pressures, wherein the standard three-dimensional model includes surface texture and geometric information; Applying a first pressure to the air spring to be tested; Acquire two-dimensional image data of multiple angles of the air spring to be tested under a first pressure; Projecting a light stripe pattern onto the surface of the air spring to be tested, and acquiring three-dimensional morphological data of the surface of the air spring to be tested under a first pressure according to the deformation of the light stripes; fusing the two-dimensional image data with the three-dimensional morphological data to generate a first three-dimensional model of the air spring, wherein the first three-dimensional model includes surface texture and geometric information of the air spring to be tested under the first pressure; A first standard three-dimensional model under the first pressure is obtained from the template module, and texture and geometric information of the first three-dimensional model are compared with those of the first standard three-dimensional model. If the difference exceeds a preset threshold, it is determined that the quality of the air spring to be tested is unqualified.

7. The air spring quality detection method based on machine vision according to claim 6 is characterized in that: The step of projecting a light stripe pattern onto the surface of the air spring to be tested and acquiring three-dimensional morphological data of the surface of the air spring to be tested under the first pressure according to the deformation of the light stripes comprises: A standard cylindrical model is pre-constructed, wherein the diameter and height of the standard cylindrical model correspond to the maximum diameter and maximum height of the air spring respectively; a first projected light stripe pattern is obtained through the standard cylindrical model, and the first projected light stripe pattern is deformed adaptively to the geometric shape of the air spring to be tested, and after the first projected light stripe pattern passes through the surface of the air spring to be tested, three-dimensional morphological data of the surface of the air spring is obtained according to the deformation information of the light stripes.

8. The air spring quality detection method based on machine vision according to claim 7 is characterized in that: The fusing of the two-dimensional image data with the three-dimensional morphological data comprises: The deformation of the first projection light fringe pattern is registered with the two-dimensional image, and the two-dimensional image is mapped to the three-dimensional morphological model according to the registration result.

9. The air spring quality detection method based on machine vision according to claim 6 is characterized in that: The two-dimensional image data at multiple angles completely cover the surface of the air spring to be tested.

10. The air spring quality detection method based on machine vision according to claim 6, characterized in that: During the defect detection process, the texture differences and geometric differences are compared, and weighted calculation is used to consider the weights of texture differences and geometric differences in quality judgment to obtain the difference value. If the difference exceeds the preset threshold, the quality of the air spring to be tested is judged to be unqualified, otherwise, it is judged to be qualified.

Images