Intelligent monitoring method and system for injection molding of automobile parts

Abstract

The invention belongs to the technical field of image processing, and particularly relates to an intelligent monitoring method and system for injection molding of automobile parts, and the method comprises the steps: obtaining an injection molding image of a to-be-detected automobile part, and calculating a gradient field of the injection molding image; performing hierarchical topology analysis on the gradient field to generate topological features representing the structural features of the local region of the image; generating an enhanced feature descriptor based on the topological features; and based on the enhanced feature descriptor, a preset classifier is adopted to classify a region in the injection molding image so as to identify a surface defect of the region. According to the method, the unique visual features of the injection molding defects of the automobile parts can be sensitively captured by deeply analyzing the fine topological structure of the gradient field, so that the recognition accuracy of the surface defects of the automobile parts is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and more particularly to an intelligent monitoring method and system for injection molding of automobile parts. Background Art

[0002] Injection molding is a core process for producing automotive plastic parts. However, due to the complex interplay of mold design, molding parameters, and raw material properties, sink marks, a hidden surface defect, can easily develop in specific locations (such as behind ribs) as the part cools and shrinks. Physically, sink marks appear as smooth, gradually decreasing depressions on the part surface, potentially measuring only micrometers in depth. These defects, visually, do not produce noticeable edges or color differences, posing a significant challenge to traditional machine vision inspection methods.

[0003] Currently, a commonly used technical solution is to use a feature descriptor based on the directional gradient histogram, combined with a classifier such as a support vector machine (SVM) for defect identification. Patent publication number CN106952258A describes a method for detecting bottle finish defects based on the directional gradient histogram. The method involves segmenting a sample image into multiple windows, calculating the directional gradient histogram within each window to obtain a feature vector, and using a support vector machine to form a classifier. The directional gradient histogram then calculates the feature vector for each detection window, and combines this with a pre-formed classifier to determine whether the current bottle finish is defective.

[0004] However, the physical characteristic of a sink mark defect is a smooth depression on the surface, and its visual feature projected in a two-dimensional image is a continuous and gradual change in the gradient direction. For example, within a sink mark area, the gradient direction may smoothly transition from 45 degrees to 55 degrees. However, the coarse-grained angle quantization mechanism used in existing gradient direction histogram technology will classify all these continuously changing tiny angles that should reflect differences into the same statistical interval, completely losing some key information. This may cause the feature vectors generated by the sink mark area to be highly similar to those of normal areas, making it impossible for the classifier to learn to effectively distinguish boundaries. The ultimate manifestation is low detection sensitivity and serious missed detection, which cannot meet the automotive industry's pursuit of high quality. Summary of the Invention

[0005] To address the technical issues of low recognition rate and serious missed detection of surface defects, especially smooth and gradual sink mark defects, in the above-mentioned machine vision inspection algorithm during the injection molding process of automotive parts, the present invention provides solutions in the following aspects.

[0006] In a first aspect, the present invention provides an intelligent monitoring method for injection molding of automobile parts, comprising: obtaining an injection molding image of an automobile part to be tested, and calculating a gradient field of the injection molding image; performing a hierarchical topological analysis on the gradient field to generate topological features that characterize the structural characteristics of a local area of ​​the image; generating an enhanced feature descriptor based on the topological features; and based on the enhanced feature descriptor, using a preset classifier to classify areas in the injection molding image to identify surface defects in the areas, thereby realizing intelligent monitoring of the injection molding quality of the automobile part.

[0007] This paper uses a layered topological analysis of the gradient field to deeply explore and characterize the essential differences between surface defects and normal surfaces, taking into account multiple dimensions, including gradient direction consistency, the curvature of the principal direction field, and topological singularities. This method goes beyond simple gradient statistics and can analyze the structural information of the gradient field, enabling sensitive identification of subtle gradient variations caused by defects such as sink marks.

[0008] Preferably, the gradient field is subjected to a hierarchical topological analysis to generate a topological feature characterizing the structural characteristics of a local region of the image, including: calculating a structural tensor based on the gradient field within the local region of the injection molding image, and determining a directional consistency index for characterizing the degree of uniformity of the gradient direction within the local region according to the eigenvalue of the structural tensor; screening a structurally ordered region based on the directional consistency index, and determining a main direction field within the structurally ordered region; calculating the Laplace value of the main direction field to obtain a gradient field curvature index for characterizing the degree of curvature of the main direction field; calculating the divergence of the main direction field to obtain a flow field divergence index for characterizing the degree of convergence or divergence of the main direction field; and using the directional consistency index, the gradient field curvature index, and the flow field divergence index as the topological feature.

[0009] This method uses a four-layer analysis framework, from consistency to principal direction field to curvature to divergence, to gradually filter out irrelevant background and noise interference. It effectively eliminates the interference of random textures, distinguishes straight edges from defects, and accurately separates surface defects from complex backgrounds.

[0010] Preferably, the directional consistency index satisfies the expression: ,in is the gradient direction consistency indicator, and are the maximum eigenvalue and minimum eigenvalue of the structure tensor, respectively. A preset positive number used to prevent the denominator of the relationship from being zero.

[0011] Preferably, the gradient field curvature index satisfies the expression: ,in The coordinates are The gradient field curvature index of the pixel, is the main direction field, is the partial derivative.

[0012] Preferably, the flow field divergence index satisfies the expression: ,in, The coordinates are The flow field divergence index of the pixel.

[0013] Preferably, it also includes: normalizing the gradient field curvature index and the flow field divergence index; performing weighted summation on the normalized gradient field curvature index and the flow field divergence index; calculating the average value of the gradient amplitudes of all pixel points in the local area as the local average gradient amplitude; and multiplying the result of the weighted summation with the directional consistency index and the local average gradient amplitude to generate a topological significance index.

[0014] Preferably, the topological significance index satisfies the expression: ,in, is the topological significance index, and are the absolute values ​​of the normalized gradient field curvature index and flow field divergence index, and is the preset weight, is the local average gradient magnitude.

[0015] Preferably, the generation of an enhanced feature descriptor based on the topological feature includes: calculating a standard gradient direction histogram feature vector in a local area of ​​the injection molding image; and concatenating the topological feature vector composed of the topological feature and the topological significance index with the gradient direction histogram feature vector to form the enhanced feature descriptor.

[0016] This paper fuses topological features with traditional gradient directional histogram features to form an enhanced feature descriptor with richer information dimensions and more comprehensive descriptive capabilities. This descriptor retains the ability of traditional algorithms to describe clear contours while more effectively separating normal surfaces from surface defects in feature space, enabling the classifier to learn more precise decision boundaries.

[0017] Preferably, the preset classifier is a support vector machine classifier.

[0018] In a second aspect, the present invention provides an intelligent monitoring system for injection molding of automobile parts, comprising a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned intelligent monitoring method for injection molding of automobile parts is implemented.

[0019] By adopting the above technical solution, a computer program is generated by the above-mentioned intelligent monitoring method for injection molding of automobile parts and stored in a memory to be loaded and executed by a processor, thereby making a terminal device based on the memory and the processor for easy use.

[0020] The present invention can identify all structurally ordered regions in the image through directional consistency analysis, effectively filtering out unstructured texture noise; then, within these ordered regions, further collaborative analysis of gradient field curvature and flow field divergence can be performed to accurately lock in regions that simultaneously meet the dual characteristics of morphological curvature and topological singularity, thereby separating surface defects such as sink marks from normal surfaces with ordinary design curvature.

[0021] Furthermore, these novel topological features are fused with traditional gradient directional histogram features to construct an enhanced feature descriptor with high sensitivity and discrimination for surface defects. This significantly improves recognition sensitivity and greatly enhances feature discrimination and recognition accuracy, significantly reducing the missed detection rate while effectively suppressing false positives caused by normal highlights, curvature, and other factors. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the following detailed description with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an illustrative and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1 is a flow chart schematically illustrating an intelligent monitoring method for injection molding of automobile parts in the present invention; Figure 2 is a diagram schematically showing the actual injection molding of the automobile part to be tested; Figure 3 is a schematic diagram of an original grayscale image schematically illustrating a sink mark defect; Figure 4 is a schematic diagram schematically illustrating the calculated gradient amplitude; Figure 5 is a visualization image schematically showing the calculated directional consistency index; Figure 6 is a visualization image schematically showing the calculated gradient field curvature index; Figure 7is a visualization image schematically showing the calculated flow field divergence index; Figure 8 Schematically shows a topological feature image after the gradient field curvature and flow field divergence indicators are fused; Figure 9 is a schematic visualization image of the topological saliency index. DETAILED DESCRIPTION

[0023] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work shall fall within the scope of protection of the present invention.

[0024] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0025] The embodiment of the present invention discloses an intelligent monitoring method for injection molding of automobile parts, referring to Figure 1 , including steps S1 to S4: S1. Acquire an injection molding image of the automobile part to be tested, and calculate the gradient field of the injection molding image.

[0026] Specifically, a high-resolution industrial camera is deployed on the automotive part injection molding production line, with its position and angle fixed relative to the workstation of the part to be tested. Simultaneously, a single, fixed, indirect light source is used to capture images of the injection-molded automotive part. This creates a clear, stable, and informative reflection on the part surface, ensuring that sink mark defects are presented in a consistent optical form.

[0027] In an optional embodiment, if Figure 2 The figure below is a schematic diagram showing the actual injection molding of the automobile parts to be tested. To further improve the reliability of the collected images, the collected color images can be converted into grayscale images, and then the grayscale images can be gamma corrected to linearize the image brightness, thereby ensuring that the grayscale value of the pixel is linearly related to the light intensity of the scene. Figure 3 , which is a schematic diagram of an original grayscale image schematically illustrating a sink mark defect.

[0028] In this optional embodiment, a Gaussian filter is applied to the linearized grayscale image for smoothing to suppress the interference of sensor noise on gradient calculation. For example, the size of the Gaussian kernel can be .

[0029] In this optional embodiment, a 3×3 Sobel operator can be used to calculate the first-order partial derivatives of the image in the horizontal (x) and vertical (y) directions, respectively, to obtain the coordinates The gradient component of the pixel and From this, the gradient amplitude of each pixel can be calculated and gradient direction In this application, the obtained gradient amplitudes and gradient directions are taken together as the gradient field of the injection molding image. Figure 4 FIG. 1 is a schematic diagram schematically illustrating the calculated gradient amplitude.

[0030] In this way, through standardized image acquisition and preprocessing methods, high-quality gradient field data can be provided for subsequent topological analysis, ensuring the accuracy and reliability of the final recognition results.

[0031] S2. Performing hierarchical topological analysis on the gradient field to generate topological features that characterize the structural characteristics of the local region of the image.

[0032] In an optional embodiment, in order to extract topological features with strong directivity to surface defects from the fine structure of the gradient field, the basic unit of analysis can be set to a local block of 16×16 pixels.

[0033] Specifically, first, in each 16×16 local block, a structure tensor is constructed :

[0034] Where W represents the local block currently being analyzed, and then the two eigenvalues ​​of the 2×2 matrix are calculated and ( ), and from this we can calculate the directional consistency index of the gradient :

[0035] in, It is a directional consistency index that characterizes the degree of uniformity of the gradient direction within the local block area, and its value range is [0, 1]; , is the structure tensor the maximum and minimum eigenvalues ​​of ; Is a very small positive number used to prevent the denominator from being 0, such as .

[0036] Specifically, when the gradient direction in the region is highly consistent (such as a straight line), ,at this time When the gradient direction in the region is completely random and isotropic (such as ideal noise), ,at this time For a shrinkage area, the reflection distortion caused by it is orderly. Typically high values, similar to a normal smooth surface.

[0037] Furthermore, the maximum eigenvalue can be calculated The corresponding eigenvector, whose direction is the main gradient direction of the block , all local blocks Together they form the main direction field. If the index is higher than a specific threshold, for example, the specific threshold is 0.6, then the corresponding local block can be considered as a structured area and is the key area for subsequent analysis; while the local block below the specific threshold can be considered as unstructured and can be directly excluded, thereby improving the processing efficiency of the subsequent process.

[0038] like Figure 5 As shown, it is a visualization image schematically showing the calculated directional consistency index. It can be seen that most areas including the background and defects are highlighted, indicating that they are all structurally ordered.

[0039] In an optional embodiment, after identifying the structurally ordered region, it is necessary to further distinguish between straight structures and curved structures, because a normal cylindrical part surface will also form ordered, straight reflective stripes, while sink marks will cause it to bend.

[0040] Specifically, whether a pixel belongs to a smooth defect area depends not only on the gradient of the point, but also on the overall shape of the gradient direction field in its neighborhood. For a flat or regularly curved surface, its gradient direction field is smooth and linear, and its second-order derivative approaches zero. However, in a shrinkage area, its gradient direction field will show a concave or convex shape, resulting in a significantly non-zero second-order derivative value. Therefore, the gradient of the main direction can be calculated. The Laplace value of is used to obtain the gradient field curvature index used to characterize the degree of curvature of the main direction field:

[0041] in, The gradient field curvature characterizes the degree of curvature of the main direction field; is the main gradient direction obtained through structural tensor analysis.

[0042] It is worth noting that the second-order partial derivative in the discrete image can be approximated by further differentiating the first-order difference image. Figure 6 As shown, it is a schematic visualization image showing the calculated gradient field curvature index. It can be seen that Figure 6A ring-shaped highlighted area corresponding to the defect edge is shown, proving that the gradient field curvature metric successfully identified the curved feature.

[0043] Furthermore, on a flat or regular cylindrical surface, the main gradient direction is constant or changes linearly, and its second-order derivative is zero, so is 0; however, in a shrinkage area, its concave shape will inevitably lead to nonlinear bending of the main direction field, resulting in a significant non-zero value.

[0044] In this way, by calculating the gradient field curvature index, it is possible to further screen out regions with curved morphology from all structurally ordered regions.

[0045] In an optional embodiment, after further screening out curved regions from the structurally ordered regions, since the part's inherent rounded corners can also produce curvature, sink marks can cause the gradient flow field to converge or diverge. Therefore, further analysis can be performed using Divergence, a specialized tool that describes this phenomenon.

[0046] Specifically, the main direction field Considered as a two-dimensional vector field , and calculate the divergence of its gradient flow field as the flow field divergence index characterizing the degree of convergence or divergence of the main direction field :

[0047] Specifically, for a designed fillet, although its main direction field is curved ( non-zero), but usually nearly parallel streamlines with divergence For a sink mark with a concave center, the gradient streamlines converge toward the center, resulting in a significant negative divergence ( ), and vice versa, its absolute value | ∣ will be significantly non-zero. Figure 7 , which schematically illustrates a visualization image of the calculated flow field divergence index.

[0048] In this way, by calculating the flow field divergence index, the structural center with converging or diverging topological characteristics can be accurately identified, which is the main feature that distinguishes sink marks from other curved structures.

[0049] In this optional embodiment, the directional consistency index, the gradient field curvature index and the flow field divergence index are used as topological features. Specifically, for an area to be highly suspected of being a surface defect, it must simultaneously meet the following conditions: High), structural bending ( High), and the curvature presents a converging or diverging shape ( |High). Therefore, in this application, these conditions are combined to construct a topological significance index .

[0050] Specifically, an area only needs or If a key topological dimension shows a strong enough response, it should be considered as a potential defect. Through linear weighted summation, the contributions of the two can be comprehensively considered. Even if one feature is slightly weak, the other strong feature can still ensure that the defect is effectively detected. At the same time, in order to eliminate and To avoid the influence of different numerical ranges of two indicators, they are linearly normalized to the interval [0,1] independently before fusion. Figure 8 As shown in FIG, this application schematically illustrates a topological feature image after the gradient field curvature and flow field divergence index are fused. In this application, the normalized index is n( )and , then the topological significance index for:

[0051] in, is the topological significance index, and are the absolute values ​​of the normalized gradient field curvature index and flow field divergence index, and is the preset weight, is the non-negative local average gradient magnitude.

[0052] It is worth noting that it is possible to give more specificity to the center point positioning Slightly higher weight, exemplary, , to highlight the defect center. The term is used as an energy weight to effectively suppress the pseudo features of low-gradient noise areas, while suppressing the weights of high-gradient strong edges to prevent their excessive influence, allowing the algorithm to focus more on the topological structure itself.

[0053] Specifically, when an area is a flat dark area, If the zero weight is zero, the zero weight will be multiplied by the topological features of the region, so that its final topological significance index also becomes zero, thereby effectively suppressing the noise pseudo features from the information-free region.

[0054] Only when there is a valid gradient change in a region, It will be a positive number, allowing its topological characteristics to contribute to the final result. The larger the value, the more energy information the region has, the higher the credibility of the topological analysis result, and the greater the weight obtained. It grows approximately linearly for very large values. growth has become very slow.

[0055] For example, within a certain analysis block, after calculation and normalization, we get (structured and orderly), (significantly curved), (strong convergence), local average gradient amplitude , ,but ; ,but This is a very high significance score, indicating that this area is very likely to be a surface defect. Figure 9 As shown, this is a schematic visualization image of the topological significance index. It can be seen that the defect area appears as a very concentrated, bright highlight patch, while other areas are effectively suppressed.

[0056] In this way, by constructing and calculating the topological significance index, the topological information of multiple dimensions and the energy information can be effectively integrated to generate a characterization index with high signal-to-noise ratio and discrimination for surface defects, providing a solid foundation for the final classification and judgment.

[0057] S3. Generate enhanced feature descriptors based on topological features.

[0058] In an optional embodiment, a standard gradient direction histogram feature vector is calculated in a local area of ​​the injection molding image; the topological feature vector composed of the topological feature and the topological significance index is concatenated with the gradient direction histogram feature vector to form an enhanced feature descriptor.

[0059] Specifically, the standard Histogram of Oriented Gradients (HOG) feature vector is calculated : According to the traditional method, each 16×16 block is divided into 4 8×8 units, and each unit calculates the gradient direction histogram of 9 bins (when constructing the gradient direction histogram, the angle range of 0 degrees to 180 degrees is divided into 9 intervals of 20 degrees), and finally concatenates them to form a 36-dimensional HOG feature vector.

[0060] Then construct the topological feature vector : In each 16×16 block, the four calculated indices are combined to form a 4-dimensional topological feature vector: .

[0061] Finally, the topological feature vector is concatenated with the gradient direction histogram feature vector to form a 40-dimensional enhanced feature descriptor .

[0062] In this way, by fusing topological features with HOG features, a new enhanced feature descriptor was created, which can not only describe the macroscopic shape contours, but also characterize the microscopic surface curvature changes, greatly improving the ability to describe surface defects of automotive parts.

[0063] S4. Based on the enhanced feature descriptor, a preset classifier is used to classify the regions in the injection molding image to identify the surface defects of the regions, thereby realizing intelligent monitoring of the injection molding quality of automotive parts.

[0064] In an alternative embodiment, a large number of injection molding image samples of automotive parts are prepared. Professional quality inspectors accurately label surface defect areas (positive samples) and various typical non-defective areas (negative samples). A 40-dimensional enhanced feature descriptor is extracted for each labeled region. These labeled feature vectors are used to train a binary support vector machine (SVM) classifier to learn the decision boundary that distinguishes defective from non-defective areas.

[0065] Furthermore, for new images of injection-molded automotive parts to be tested, a sliding window method was used to move a 16x16 window across the image, block by block. At each window position, the enhanced feature descriptor was extracted and fed into a trained SVM for discrimination, resulting in a defect probability value and, consequently, a defect saliency map. By applying thresholding and non-maximum suppression to this saliency map, all surface defects could be accurately located and segmented.

[0066] In this way, by using enhanced feature descriptors to train classifiers, it is possible to achieve automated, high-precision online identification and positioning of surface defects in automotive parts on the production line, effectively solving the problem of missed detection in traditional methods.

[0067] An embodiment of the present invention further discloses an intelligent monitoring system for injection molding of automobile parts, comprising a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, an intelligent monitoring method for injection molding of automobile parts according to the present invention is implemented.

[0068] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface. The configuration and functions of these components are known in the art and will not be described in detail here.

[0069] In the description of this specification, “multiple” or “several” means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0070] While this specification has shown and described several embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Numerous modifications, variations, and alternatives will occur to those skilled in the art without departing from the concept and spirit of the present invention. It should be understood that in practicing the present invention, alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. An intelligent monitoring method for injection molding of automobile parts, characterized in that: include: Acquire an injection molding image of the automobile part to be tested, and calculate the gradient field of the injection molding image; Performing a hierarchical topological analysis on the gradient field to generate topological features that characterize structural characteristics of a local region of the image; generating an enhanced feature descriptor based on the topological features; Based on the enhanced feature descriptor, a preset classifier is used to classify the regions in the injection molding image to identify surface defects in the regions, thereby realizing intelligent monitoring of the injection molding quality of the automobile parts.

2. The intelligent monitoring method for automobile parts injection molding according to claim 1, characterized in that: The performing of a hierarchical topological analysis on the gradient field to generate a topological feature representing the structural characteristics of a local region of the image includes: In a local area of ​​the injection molding image, a structure tensor is calculated based on the gradient field, and a direction consistency index for characterizing the degree of uniformity of the gradient direction in the local area is determined according to an eigenvalue of the structure tensor; screening a structurally ordered region based on the directional consistency index, and determining a main direction field within the structurally ordered region; Calculating the Laplace value of the main direction field to obtain a gradient field curvature index for characterizing the curvature degree of the main direction field; Calculating the divergence of the main direction field to obtain a flow field divergence index for characterizing the degree of convergence or divergence of the main direction field; The direction consistency index, the gradient field curvature index and the flow field divergence index are used as the topological features.

3. The intelligent monitoring method for automobile parts injection molding according to claim 2, characterized in that: The directional consistency index satisfies the expression: in is the gradient direction consistency indicator, and are the maximum and minimum eigenvalues ​​of the structure tensor, respectively. A preset positive number used to prevent the denominator of the relationship from being zero.

4. The intelligent monitoring method for automobile parts injection molding according to claim 2, characterized in that: The gradient field curvature index satisfies the expression: in The coordinates are The gradient field curvature index of the pixel, is the main direction field, is the partial derivative.

5. The intelligent monitoring method for automobile parts injection molding according to claim 2, characterized in that: The flow field divergence index satisfies the expression: in, The coordinates are The flow field divergence index of the pixel.

6. The intelligent monitoring method for automobile parts injection molding according to claim 2, characterized in that: Also includes: Normalizing the gradient field curvature index and the flow field divergence index; Perform weighted summation on the normalized gradient field curvature index and flow field divergence index; Calculating the average value of the gradient amplitudes of all pixels in the local area as the local average gradient amplitude; The weighted summation result is multiplied by the directional consistency index and the local average gradient magnitude to generate a topological significance index.

7. The intelligent monitoring method for automobile parts injection molding according to claim 6, characterized in that: The topological significance index satisfies the expression: in, is the topological significance index, and are the absolute values ​​of the normalized gradient field curvature index and flow field divergence index, and is the preset weight, is the non-negative local average gradient magnitude.

8. The intelligent monitoring method for automobile parts injection molding according to claim 6, characterized in that: The generating of an enhanced feature descriptor based on the topological feature comprises: Calculating a standard gradient direction histogram feature vector in a local area of ​​the injection molding image; A topological feature vector composed of the topological feature and the topological significance index is connected in series with the gradient direction histogram feature vector to form the enhanced feature descriptor.

9. The intelligent monitoring method for automobile parts injection molding according to claim 8, characterized in that: The preset classifier is a support vector machine classifier.

10. An intelligent monitoring system for injection molding of automobile parts, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, an intelligent monitoring method for injection molding of automobile parts according to any one of claims 1 to 9 is implemented.

Images