A new energy vehicle damping component detection method and system based on machine vision

Abstract

The present application relates to the technical field of new energy vehicle parts quality detection, and particularly relates to a new energy vehicle shock absorbing component detection method and system based on machine vision. The method comprises: collecting a composite interface original image; performing spatial mapping on the composite interface original image; extracting a rubber contour set and a metal contour set; constructing a radial distance function and an assembly offset index; performing interface anomaly determination; and outputting a qualifiedness determination result of the shock absorbing component. Compared with the detection method in the prior art which mainly relies on manual visual inspection or simple geometric threshold determination, the technical problem that it is difficult to accurately determine the press-fitting quality of the shock absorbing component under the working conditions of reflection on the surface of the rubber material, changes in the assembly posture, local flanging or asymmetric deformation and the like is solved. Due to the introduction of the radial consistency analysis and the multi-condition joint determination mechanism, the quantitative detection of the abnormal states such as the assembly offset, flanging and asymmetric deformation of the rubber-metal composite interface is realized.

Description

Technical Field

[0001] This invention relates to the field of quality inspection technology for new energy vehicle components, and in particular to a method and system for inspecting shock absorber components of new energy vehicles based on machine vision. Background Technology

[0002] New energy sanitation vehicles typically operate with frequent low-speed starts and stops, full-load sweeping and watering, and the combined effects of road impacts and operational vibrations. The vibration damping performance of key chassis components directly impacts the stability of the operating devices, the reliability of the battery pack and controller installation, and the durability of the chassis structure. Therefore, during the research, development, trial production, and mass production verification of vibration damping technology for key chassis components of new energy sanitation vehicles, it is necessary to conduct stability tests on the press-fit interfaces of vibration damping components such as rubber bushings and metal housings to support vibration damping structure optimization, assembly process adjustments, and consistent quality control.

[0003] However, existing machine vision inspection solutions mostly focus on judging single geometric dimensions, local contour features, or grayscale thresholds, which still have significant shortcomings in practical applications. For example, when there is reflection, shadow, or uneven grayscale distribution on the surface of rubber bushing material, detection methods based on fixed thresholds or simple contour extraction are prone to false detections or missed detections. At the same time, when the assembly posture of shock-absorbing components changes or the clamping position deviates in automated production lines, the method of directly judging based on image pixel coordinates is difficult to guarantee the consistency of results at different inspection times.

[0004] Furthermore, for complex assembly defects that may occur during the pressing of rubber bushings, such as overall misalignment, local flanging, and asymmetric deformation caused by uneven pressing force, existing technologies can often only provide a coarse-grained judgment of "whether it is abnormal" and it is difficult to effectively distinguish different types of abnormalities. This results in limited engineering guidance significance of the test results and insufficient testing stability in high-speed automated production line environments.

[0005] Therefore, there is an urgent need for a testing method that can stably and quantitatively determine the assembly state of the composite interface between the rubber bushing and the metal shell, even when the surface characteristics of the rubber material are complex and the assembly posture is fluctuating, so as to improve the accuracy, consistency and reliability of the testing of shock absorber components of new energy vehicles in automated production lines. Summary of the Invention

[0006] To address the aforementioned technical shortcomings, the present invention aims to propose a machine vision-based method for detecting shock absorber components in new energy vehicles. This method addresses the technical problem that existing detection methods, which primarily rely on manual visual inspection or simple geometric threshold judgments, struggle to accurately determine the press-fit quality of shock absorber components under conditions such as surface reflection of rubber materials, changes in assembly posture, and localized flanging or asymmetrical deformation.

[0007] To solve the above-mentioned technical problems, the present invention adopts the following technical solution: The present invention provides a machine vision-based method for detecting shock absorption components of new energy vehicles.

[0008] The machine vision-based detection method for shock absorber components in new energy vehicles includes: Step S10: Acquire the original image of the composite interface between the rubber bushing and the metal housing of the vehicle shock absorber component. Based on the original image of the composite interface A pinhole imaging model is used for mapping, and a standardized interface image after distortion correction is output. ; Step S20: Based on the normalized interface image after distortion correction Perform local statistics-driven adaptive grayscale segmentation to extract the rubber contour set. With metal profile set ; Step S30: Based on the rubber profile set With metal profile set A radial distance function construction task is performed using a radial consistency modeling mechanism based on contour polar coordinate reparameterization, and the radial distance function is output. and assembly offset index ;in, Indicates the circumferential direction of the metal casing; Step S40: Based on radial distance function Constructing an index for the asymmetric deformation of rubber during compression fitting Based on the rubber compression deformation asymmetry index and assembly offset index Perform UI error detection and output a set of UI error detection flags. ; Step S50: Based on the set of interface anomaly detection flags Perform a pass / fail assessment and output the pass / fail assessment results for the shock absorber components.

[0009] Preferably, the original image of the composite interface between the rubber bushing and the metal housing of the vehicle shock absorber component is acquired. Based on the original image of the composite interface A pinhole imaging model is used for mapping, and a standardized interface image after distortion correction is output. The steps specifically include: Step S101: On the automated assembly line, for the air suspension shock absorber components that have completed press-fitting, an industrial camera triggered synchronously with the motion rhythm of the automated assembly line is used to capture raw images of the composite interface including the rubber bushing and the metal housing. ; Step S102: Based on the pre-completed camera intrinsic and extrinsic parameter calibration relationship, the original image of the composite interface is... Mapped to a unified workpiece coordinate system, a standardized interface image after distortion correction is obtained. Among them, the original image of the composite interface The step of mapping to a unified workpiece coordinate system is performed using a pinhole imaging model.

[0010] Preferably, in step S102, the mapping step using the pinhole imaging model satisfies the following mapping relationship: ;in, Original image of composite interface The x-coordinate of the pixel of the feature point in the interface; Original image of composite interface The pixel ordinates of the feature points on the interface. This represents the rotational relationship between the image coordinate system and the workpiece coordinate system; This represents the translation relationship between the image coordinate system and the workpiece coordinate system. This represents the spatial coordinate value of the interface feature point in the first radial direction in the workpiece coordinate system established with the axis of the shock-absorbing component as the reference; This represents the spatial coordinate value of the interface feature point in the second radial direction within the workpiece coordinate system established with the axis of the damping component as the reference. This represents the spatial coordinate value of the interface feature point along the axis of the damping component in the workpiece coordinate system established with the axis of the damping component as the reference; The intrinsic parameter matrix of the industrial camera is used to characterize the camera's focal length, principal point position, and pixel scaling relationship; s is the scale factor used to unify the ratio between pixel coordinates and actual spatial dimensions.

[0011] Preferably, in step S20, the standardized interface image after distortion correction is used. Perform local statistics-driven adaptive grayscale segmentation to extract the rubber bushing region. With metal casing area The steps specifically include: Set adaptive segmentation threshold , ,in, Standardized interface image after distortion correction The pixel x-coordinate, Standardized interface image after distortion correction The pixel ordinate, In pixel coordinates The average gray level within a local window centered on the value. In pixel coordinates Standard deviation centered on This is an empirical adjustment coefficient used to suppress reflections and shadow interference on the surface of rubber materials; Based on adaptive segmentation threshold Standardized interface image after distortion correction Perform local statistics-driven adaptive grayscale segmentation processing to output the rubber bushing region. With metal casing area ; For the rubber bushing area With metal casing area Edge detection and contour fitting were performed using Python's cv2 and scikit libraries to obtain a set of rubber contours. With metal profile set .

[0012] Preferably, in step S30, based on the rubber profile set With metal profile set A radial distance function construction task is performed using a radial consistency modeling mechanism based on contour polar coordinate reparameterization, and the radial distance function is output. and assembly offset index ;in, The steps for indicating the circumferential direction of a metal casing specifically include: Step S301: Based on the rubber profile set The profile was geometrically modeled using the least squares circle fitting method to obtain the equivalent center of the rubber bushing. Equivalent radius of rubber bushing ; Step S302: Based on the metal profile set The least squares circle fitting method was used to geometrically model the contour, and the equivalent center of the metal shell was obtained. Equivalent radius of metal shell ; Step S303: Based on the equivalent center of the rubber bushing Equivalent center of the metal shell Assembly offset index for constructing rubber-metal composite interfaces , Meanwhile, with the equivalent center of the metal shell... Let the origin be the polar coordinate system, and let the equivalent radius of the rubber bushing be used as the reference point. Equivalent radius of metal shell Along the circumference of the metal shell Establish radial distance function .

[0013] Preferably, in step S40, based on the radial distance function Constructing an index for the asymmetric deformation of rubber during compression fitting Based on the rubber compression deformation asymmetry index and assembly offset index Perform UI error detection and output a set of UI error detection flags. The steps specifically include: Step S401: Based on radial distance function Constructing an index for the asymmetric deformation of rubber during compression fitting , ;in, Indicates the direction along the circumference of the metal shell The maximum radial outward extension of the rubber bushing relative to the metal shell in each angular direction; Indicates the direction along the circumference of the metal shell The minimum radial outward extension of the rubber bushing relative to the metal housing in each angular direction; Step S402: Preset assembly offset threshold Flanging abnormal threshold and deformation asymmetry threshold Perform a multi-condition joint judgment: when At that time, it was determined that there was an abnormality in the overall pressing and offset of the rubber bushing; when At that time, it was determined that there was an abnormality in the rubber edge or local outward turning; when At that time, it was determined that the rubber compression deformation showed a significant asymmetry, which was abnormal. Step S403: Output the set of anomaly detection flags for the result of multi-condition joint judgment. .

[0014] Preferably, in step S50, the set of interface anomaly determination flags is used. The steps for performing a conformity assessment and outputting the conformity assessment results for the vibration damping components specifically include: when the interface abnormality assessment flag set... If at least one anomaly detection flag exists, the air suspension shock absorber component is deemed unqualified; if the set of interface anomaly detection flags is... If no abnormality indicator is found, the air suspension damping component is deemed qualified.

[0015] This invention also provides a machine vision-based detection system for shock absorber components of new energy vehicles, comprising: Step S10: Acquire the original image of the composite interface between the rubber bushing and the metal housing of the vehicle shock absorber component. Based on the original image of the composite interface A pinhole imaging model is used for mapping, and a standardized interface image after distortion correction is output. ; Step S20: Based on the normalized interface image after distortion correction Perform local statistics-driven adaptive grayscale segmentation to extract the rubber contour set. With metal profile set ; Step S30: Based on the rubber profile set With metal profile set A radial distance function construction task is performed using a radial consistency modeling mechanism based on contour polar coordinate reparameterization, and the radial distance function is output. and assembly offset index ;in, Indicates the circumferential direction of the metal casing; Step S40: Based on radial distance function Constructing an index for the asymmetric deformation of rubber during compression fitting Based on the rubber compression deformation asymmetry index and assembly offset index Perform UI error detection and output a set of UI error detection flags. ; Step S50: Based on the set of interface anomaly detection flags Perform a pass / fail assessment and output the pass / fail assessment results for the shock absorber components.

[0016] The present invention also provides a machine vision-based detection device for shock absorber components of new energy vehicles, comprising: a memory, a processor, and a machine vision-based detection program for shock absorber components of new energy vehicles stored in the memory and executable on the processor. When the machine vision-based detection program for shock absorber components of new energy vehicles is executed by the processor, a machine vision-based detection method for shock absorber components of new energy vehicles is implemented.

[0017] The present invention also provides a computer program product, including a machine vision-based detection program for shock absorber components of new energy vehicles, wherein the machine vision-based detection program for shock absorber components of new energy vehicles implements the machine vision-based detection method for shock absorber components of new energy vehicles when executed by a processor.

[0018] The beneficial effects of the present invention are as follows: The present invention maps the composite interface between the rubber bushing and the metal shell to the workpiece coordinate system with the axis of the shock-absorbing component as the reference, and on this basis, constructs a radial consistency modeling mechanism based on contour polar coordinate reparameterization, thereby realizing the quantitative characterization of the assembly state of the rubber-metal composite interface.

[0019] This invention further constructs a rubber pressing deformation asymmetry index based on the radial distance function, and adopts a multi-condition joint judgment mechanism in combination with the assembly offset index to identify abnormal interface states, which can effectively distinguish different types of assembly defects such as overall pressing offset, local flanging and pressing deformation asymmetry. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart illustrating the first embodiment of a machine vision-based method for detecting shock absorber components in new energy vehicles according to the present invention. Detailed Implementation

[0022] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. 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.

[0023] Example 1: As Figure 1 The diagram shown is a flowchart of the first embodiment of the machine vision-based detection method for shock absorber components of new energy vehicles according to the present invention. The first embodiment of the machine vision-based detection method for shock absorber components of new energy vehicles according to the present invention is presented.

[0024] In the first embodiment, the machine vision-based method for detecting shock absorber components in new energy vehicles includes: Step S10: Acquire the original image of the composite interface between the rubber bushing and the metal housing of the vehicle shock absorber component. Based on the original image of the composite interface A pinhole imaging model is used for mapping, and a standardized interface image after distortion correction is output. ; It should be noted that the original image of the composite interface refers to the original image data of the assembly interface between the rubber bushing and the metal shell in the air suspension shock absorber component. This image may be affected by factors such as changes in assembly posture, workpiece transport deviation, and differences in camera installation position during acquisition, and its pixel coordinates do not directly have physical meaning that can be used for geometric consistency analysis.

[0025] It is understandable that by introducing a pinhole imaging model to map the original image of the composite interface, the pixel coordinates in the image are essentially converted into spatial coordinates in a unified workpiece coordinate system with the axis of the shock-absorbing component as the reference. This allows image data acquired at different shooting times and under different assembly postures to be compared in the same physical scale and reference system, thus providing a reliable data foundation for subsequent assembly offset calculation and radial consistency analysis.

[0026] It should be understood that if contour extraction and geometric calculation are performed directly based on the original pixel coordinates without going through the mapping and distortion correction process of the pinhole imaging model, when the position or posture of the workpiece changes in the detection station, it is easy to cause inconsistency in the center position, radius parameters and radial distance function obtained in subsequent calculations, which in turn affects the accuracy of the judgment of the pressing state of the rubber bushing.

[0027] Step S20: Based on the normalized interface image after distortion correction Perform local statistics-driven adaptive grayscale segmentation to extract the rubber contour set. With metal profile set ; It should be noted that the rubber profile set and the metal profile set in this step refer to the continuous boundary point sets corresponding to the outer edge of the rubber bushing and the inner edge of the metal shell, respectively, in the standardized interface image after distortion correction. This profile set will serve as the direct input for subsequent geometric modeling and assembly offset calculation, and its completeness and accuracy directly affect the reliability of the subsequent analysis results.

[0028] Understandably, by introducing an adaptive grayscale segmentation method based on local statistical characteristics, the segmentation threshold can be dynamically adjusted according to the local grayscale distribution of different regions in the image, thereby effectively distinguishing the rubber bushing region from the metal shell region. Compared with fixed global threshold segmentation, this method is more suitable for interface region extraction under complex imaging conditions such as surface reflection, local shadows, and uneven grayscale distribution of rubber materials, and is beneficial for obtaining continuous and stable interface contours.

[0029] It should be understood that if only a segmentation method based on a fixed threshold or a single grayscale feature is used, it is easy to cause contour breakage, false edges or missegmentation when there are high reflective areas on the surface of the rubber bushing or local dark areas on the edge of the metal shell. This will cause deviations in the center position and radius parameters obtained subsequently based on contour fitting, and thus affect the calculation accuracy of the assembly offset index and radial distance function.

[0030] Step S30: Based on the rubber profile set With metal profile set A radial distance function construction task is performed using a radial consistency modeling mechanism based on contour polar coordinate reparameterization, and the radial distance function is output. and assembly offset index ;in, Indicates the circumferential direction of the metal casing; It should be noted that the radial distance function and assembly offset index in this step are quantitative characterization parameters constructed based on the geometric relationship between the rubber profile set and the metal profile set. The assembly offset index is used to reflect the assembly offset between the rubber bushing and the metal shell in the overall coaxial direction, while the radial distance function is used to characterize the local outward or inward state of the rubber bushing in various angular directions around the circumference of the metal shell.

[0031] Understandably, by transforming the rubber profile set and the metal profile set from the Cartesian coordinate system to the polar coordinate system with the equivalent center of the metal shell as the pole, and by reparameterizing the circumferential direction of the metal shell as the angle parameter, the relationship of the profile points that were originally scattered in the two-dimensional plane can be uniformly transformed into a one-dimensional radial function that varies with the angle. This allows the radial consistency or inconsistency of the rubber bushing relative to the metal shell to be expressed intuitively and continuously.

[0032] It should be understood that if the analysis is based solely on the local distance or overall size difference between the rubber profile and the metal profile in the planar coordinate system, it is difficult to effectively distinguish between different types of assembly anomalies such as overall assembly offset and local flanges or collapses. However, the polar coordinate reparameterized radial modeling method in this step can eliminate the influence of overall position offset while retaining the relative radial variation characteristics of the rubber bushing in different circumferential directions, providing a reliable basis for subsequent analysis of rubber press-fit deformation asymmetry.

[0033] For example, in actual assembly, when the rubber bushing undergoes slight eccentric pressing, the radial distance of the bushing changes in each angular direction around the circumference of the metal shell in a generally consistent manner. However, when the rubber bushing experiences localized deformation due to flange formation or uneven pressing force in certain areas, the radial distance function will exhibit a significant abrupt increase or decrease within the corresponding angular range. The radial distance function constructed in this step can differentiate these different assembly states in terms of function shape, providing a quantitative basis for subsequent interface anomaly detection.

[0034] Step S40: Based on radial distance function Constructing an index for the asymmetric deformation of rubber during compression fitting Based on the rubber compression deformation asymmetry index and assembly offset index Perform UI error detection and output a set of UI error detection flags. ; It should be noted that the rubber press-fit deformation asymmetry index constructed in this step is obtained by statistical analysis based on the radial distance function obtained in step S30. It is used to quantitatively characterize whether there is an obvious unevenness in the radial distribution of the rubber bushing in the circumferential direction of the metal shell. The interface anomaly judgment mark set is used to structurally express the assembly state of the rubber-metal composite interface of the shock absorption component in order to distinguish different types of assembly anomalies.

[0035] Understandably, by comparing the maximum and minimum values ​​of the radial distance function in the circumferential direction of the metal shell, it is possible to reflect whether there are local uneven forces, local outward turning, or local collapse during the press-fitting process of the rubber bushing. At the same time, by combining the assembly offset index for joint judgment, it is possible to further distinguish between overall misalignment and local deformation anomalies on the basis of identifying overall coaxial misalignment anomalies, thereby avoiding the risk of misjudgment caused by relying on a single index.

[0036] It should be understood that if the assembly status of the rubber bushing and the metal housing is judged solely based on the assembly offset index, it is easy to be misjudged as qualified when the overall position of the rubber bushing is basically correct but there is flange or asymmetric pressing deformation in local areas. On the other hand, if the judgment is based solely on the local changes in the radial distance function, the coaxiality problem may be ignored when there is overall misalignment. By introducing both the rubber pressing deformation asymmetry index and the assembly offset index in this step, and constructing a multi-condition joint interface anomaly judgment mechanism, the true assembly status of the rubber and metal composite interface can be reflected more comprehensively and accurately.

[0037] Step S50: Based on the set of interface anomaly detection flags Perform a pass / fail assessment and output the pass / fail assessment results for the shock absorber components.

[0038] It should be noted that the set of interface anomaly judgment indicators in this step is a structured summary of the aforementioned assembly anomaly judgment results. It includes at least judgment indicators that reflect the overall assembly offset anomaly of the rubber bushing, local flange anomaly, and press-fit deformation asymmetry anomaly, and is used to uniformly characterize the assembly state of the rubber-metal composite interface of the shock-absorbing component.

[0039] Understandably, by performing conformity assessment based on the set of interface anomaly assessment flags, the multiple geometric and deformation assessment results obtained in the preceding steps are essentially transformed into a single assembly quality conclusion. This allows the test results to be directly used for quality control and process decision-making in automated production lines, thereby avoiding the need for manual interpretation or repeated assessment of multiple intermediate assessment indicators.

[0040] Example 2: Furthermore, the present invention provides a machine vision-based detection system for shock absorber components of new energy vehicles, employing a machine vision-based detection method for shock absorber components of new energy vehicles as described in the above embodiments, which can solve the technical problem of detecting shock absorber components of new energy vehicles based on machine vision. Compared with the prior art, the beneficial effects of the machine vision-based detection system for shock absorber components of new energy vehicles provided by the present invention are the same as those of the machine vision-based detection method for shock absorber components of new energy vehicles provided in the above embodiments, and other technical features of the machine vision-based detection system for shock absorber components of new energy vehicles are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0041] Example 3: This invention provides a machine vision-based detection device for shock absorber components of new energy vehicles, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform a machine vision-based detection method for shock absorber components of new energy vehicles as described in Example 1 above. The machine vision-based detection device for shock absorber components of new energy vehicles in this embodiment of the invention may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. This machine vision-based detection device for shock absorber components of new energy vehicles is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the invention. The machine vision-based detection device for shock absorber components of new energy vehicles may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory or a program loaded from a storage device into a random access memory. The random access memory also stores various programs and data required for the operation of a machine vision-based new energy vehicle shock absorber component inspection device. The processing unit, read-only memory, and random access memory are interconnected via a bus. The I / O interface is also connected to the bus. Typically, the following systems can be connected to the I / O interface: input devices including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices including, for example, magnetic tapes, hard disks, etc.; and communication devices. The communication device allows the machine vision-based new energy vehicle shock absorber component inspection device to communicate wirelessly or wiredly with other devices to exchange data. While a machine vision-based new energy vehicle shock absorber component inspection device with various systems has been described, it should be understood that it is not required to implement or possess all the systems described. More or fewer systems can be implemented alternatively.

[0042] Example 4: This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the machine vision-based method for detecting shock absorber components in new energy vehicles as described above. The computer program product provided by this invention can solve the technical problem of detecting shock absorber components in new energy vehicles based on machine vision. Compared with the prior art, the beneficial effects of the computer program product provided by this invention are the same as those of the machine vision-based method for detecting shock absorber components in new energy vehicles provided in the above embodiments, and will not be repeated here.

[0043] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device, or installed from a read-only memory. When the computer program is executed by a processing device, it performs the functions defined in the methods of the embodiments disclosed in this invention.

[0044] It should be understood that the various parts disclosed in this invention can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics may be combined in any suitable manner in one or more embodiments or examples.

[0045] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A machine vision-based method for detecting shock absorber components in new energy vehicles, characterized in that, The methods include: Step S10: Acquire the original image of the composite interface between the rubber bushing and the metal housing of the vehicle shock absorber component. Based on the original image of the composite interface A pinhole imaging model is used for mapping, and a standardized interface image after distortion correction is output. ; Step S20: Based on the normalized interface image after distortion correction Perform local statistics-driven adaptive grayscale segmentation to extract the rubber contour set. With metal profile set ; Step S30: Based on the rubber profile set With metal profile set A radial distance function construction task is performed using a radial consistency modeling mechanism based on contour polar coordinate reparameterization, and the radial distance function is output. and assembly offset index ;in, Indicates the circumferential direction of the metal casing; Step S40: Based on radial distance function Constructing an index for the asymmetric deformation of rubber during compression fitting Based on the rubber compression deformation asymmetry index and assembly offset index Perform UI error detection and output a set of UI error detection flags. ; Step S50: Based on the set of interface anomaly detection flags Perform a pass / fail assessment and output the pass / fail assessment results for the shock absorber components.

2. The method for detecting shock absorber components of new energy vehicles based on machine vision as described in claim 1, characterized in that, In step S10, the original image of the composite interface between the rubber bushing and the metal housing of the vehicle shock absorber component is acquired. Based on the original image of the composite interface A pinhole imaging model is used for mapping, and a standardized interface image after distortion correction is output. The steps specifically include: Step S101: On the automated assembly line, for the air suspension shock absorber components that have completed press-fitting, an industrial camera triggered synchronously with the motion rhythm of the automated assembly line is used to capture raw images of the composite interface including the rubber bushing and the metal housing. ; Step S102: Based on the pre-completed camera intrinsic and extrinsic parameter calibration relationship, the original image of the composite interface is... Mapped to a unified workpiece coordinate system, a standardized interface image after distortion correction is obtained. Among them, the original image of the composite interface The step of mapping to a unified workpiece coordinate system is performed using a pinhole imaging model.

3. The method for detecting shock absorber components of new energy vehicles based on machine vision as described in claim 2, characterized in that, In step S102, the mapping step using the pinhole imaging model satisfies the following mapping relationship: ;in, Original image of composite interface The x-coordinate of the pixel of the feature point in the interface; Original image of composite interface The pixel ordinates of the feature points on the interface. This represents the rotational relationship between the image coordinate system and the workpiece coordinate system; This represents the translation relationship between the image coordinate system and the workpiece coordinate system. This represents the spatial coordinate value of the interface feature point in the first radial direction in the workpiece coordinate system established with the axis of the shock-absorbing component as the reference; This represents the spatial coordinate value of the interface feature point in the second radial direction within the workpiece coordinate system established with the axis of the damping component as the reference. This represents the spatial coordinate value of the interface feature point along the axis of the damping component in the workpiece coordinate system established with the axis of the damping component as the reference; The intrinsic parameter matrix of the industrial camera is used to characterize the camera's focal length, principal point position, and pixel scaling relationship; s is the scale factor used to unify the ratio between pixel coordinates and actual spatial dimensions.

4. The method for detecting shock absorber components of new energy vehicles based on machine vision as described in claim 1, characterized in that, In step S20, based on the normalized interface image after distortion correction... Perform local statistics-driven adaptive grayscale segmentation to extract the rubber bushing region. With metal casing area The steps specifically include: Set adaptive segmentation threshold , ,in, Standardized interface image after distortion correction The pixel x-coordinate, Standardized interface image after distortion correction The pixel ordinate, In pixel coordinates The average gray level within a local window centered on the value. In pixel coordinates Standard deviation centered on This is an empirical adjustment coefficient used to suppress reflections and shadow interference on the surface of rubber materials; Based on adaptive segmentation threshold Standardized interface image after distortion correction Perform local statistics-driven adaptive grayscale segmentation processing to output the rubber bushing region. With metal casing area ; For the rubber bushing area With metal casing area Edge detection and contour fitting were performed using Python's cv2 and scikit libraries to obtain a set of rubber contours. With metal profile set .

5. The method for detecting shock absorber components of new energy vehicles based on machine vision as described in claim 1, characterized in that, In step S30, based on the rubber profile set With metal profile set A radial distance function construction task is performed using a radial consistency modeling mechanism based on contour polar coordinate reparameterization, and the radial distance function is output. and assembly offset index ;in, The steps for indicating the circumferential direction of a metal casing specifically include: Step S301: Based on the rubber profile set The profile was geometrically modeled using the least squares circle fitting method to obtain the equivalent center of the rubber bushing. Equivalent radius of rubber bushing ; Step S302: Based on the metal profile set The least squares circle fitting method was used to geometrically model the contour, and the equivalent center of the metal shell was obtained. Equivalent radius of metal shell ; Step S303: Based on the equivalent center of the rubber bushing Equivalent center of the metal shell Assembly offset index for constructing rubber-metal composite interfaces , Meanwhile, with the equivalent center of the metal shell... Let the origin be the polar coordinate system, and let the equivalent radius of the rubber bushing be used as the reference point. Equivalent radius of metal shell Along the circumference of the metal shell Establish radial distance function .

6. The method for detecting shock absorber components of new energy vehicles based on machine vision as described in claim 1, characterized in that, In step S40, based on the radial distance function Constructing an index for the asymmetric deformation of rubber during compression fitting Based on the rubber compression deformation asymmetry index and assembly offset index Perform UI error detection and output a set of UI error detection flags. The steps specifically include: Step S401: Based on radial distance function Constructing an index for the asymmetric deformation of rubber during compression fitting , ;in, Indicates the direction along the circumference of the metal shell The maximum radial outward extension of the rubber bushing relative to the metal shell in each angular direction; Indicates the direction along the circumference of the metal shell The minimum radial outward extension of the rubber bushing relative to the metal housing in each angular direction; Step S402: Preset assembly offset threshold Flanging abnormal threshold and deformation asymmetry threshold Perform a multi-condition joint judgment: when At that time, it was determined that there was an abnormality in the overall pressing and offset of the rubber bushing; when At that time, it was determined that there was an abnormality in the rubber edge or local outward turning; when At that time, it was determined that the rubber compression deformation showed a significant asymmetry, which was abnormal. Step S403: Output the set of anomaly detection flags for the result of multi-condition joint judgment. .

7. The method for detecting shock absorber components of new energy vehicles based on machine vision as described in claim 6, characterized in that, In step S50, based on the set of interface anomaly judgment flags... The steps for performing a conformity assessment and outputting the conformity assessment results for the vibration damping components specifically include: when the interface abnormality assessment flag set... If at least one anomaly detection flag exists, the air suspension shock absorber component is deemed unqualified; if the set of interface anomaly detection flags is... If no abnormality indicator is found, the air suspension damping component is deemed qualified.

8. A machine vision-based inspection system for shock absorber components of new energy vehicles, applied to the machine vision-based inspection method for shock absorber components of new energy vehicles as described in any one of claims 1 to 7, characterized in that, The machine vision-based detection system for shock absorber components of new energy vehicles includes: The interface imaging and normalized mapping module is used to acquire raw images of the composite interface between the rubber bushing and the metal housing of vehicle shock absorber components. Based on the original image of the composite interface A pinhole imaging model is used for mapping, and a standardized interface image after distortion correction is output. ; The composite interface contour construction module is used to construct interface contours based on distortion-corrected, standardized interface images. Perform local statistics-driven adaptive grayscale segmentation to extract the rubber contour set. With metal profile set ; Radial consistency modeling module, used for rubber profile sets With metal profile set A radial distance function construction task is performed using a radial consistency modeling mechanism based on contour polar coordinate reparameterization, and the radial distance function is output. and assembly offset index ;in, Indicates the circumferential direction of the metal casing; The interface anomaly detection module is used for determining anomalies based on the radial distance function. Constructing an index for the asymmetric deformation of rubber during compression fitting Based on the rubber compression deformation asymmetry index and assembly offset index Perform UI error detection and output a set of UI error detection flags. ; The pass / fail judgment module is used to determine the pass / fail status based on the set of interface anomaly judgment flags. Perform a pass / fail assessment and output the pass / fail assessment results for the shock absorber components.

9. A machine vision-based testing device for shock absorber components of new energy vehicles, characterized in that, The machine vision-based new energy vehicle shock absorber component detection device includes: a memory, a processor, and a machine vision-based new energy vehicle shock absorber component detection program stored in the memory and executable on the processor. When the machine vision-based new energy vehicle shock absorber component detection program is executed by the processor, it implements a machine vision-based new energy vehicle shock absorber component detection method according to any one of claims 1 to 7.

10. A computer program product, characterized in that, The computer program product includes a machine vision-based detection program for shock absorber components of new energy vehicles. When the machine vision-based detection program for shock absorber components of new energy vehicles is executed by the processor, it implements a machine vision-based detection method for shock absorber components of new energy vehicles according to any one of claims 1 to 7.

Images