Method and system for detecting defects of crankset

Abstract

The invention relates to the technical field of casting image processing, and discloses a crankset defect detection method and system, and the method comprises the steps: obtaining a ray scanning image of a crankset, and marking a semi-macrosegregation characteristic line in the ray scanning image; constructing a microscopic segregation defect image according to the diffusion distribution position of the semi-macroscopic segregation characteristic line; a new ray scanning image is formed on the ray scanning image by the microsegregation defect image, the microsegregation defect image can be quickly recognized in a lossless mode through a common ray scanning method, the complete area of microsegregation can be covered, the image recognition precision is improved, and the recognition efficiency is improved. And the pattern recognition precision of the defect image can be improved through the accurately trained image recognition model.

Description

Technical Field

[0001] The invention relates to the technical field of casting image processing, and in particular to a method and system for detecting defects of a toothed disc. Background Art

[0002] The toothed disc plays a key role in the mechanical transmission system. In the casting process of the toothed disc, the liquid alloy metal melt is injected into the mold for solidification and forming. However, during the solidification and forming process of the melt of the toothed disc, the material flows unevenly due to the differences in various metal components and physical properties in the alloy metal melt. This phenomenon is particularly obvious in the common centrifugal casting, continuous casting, extrusion casting and other processes of the toothed disc. Because during the molding process in the toothed disc mold under the centrifugal force of high-speed rotation of centrifugal casting, the heavy elements in the material will migrate to the outside to form a higher specific gravity area, resulting in uneven distribution of alloy components or specific gravity in different areas of the toothed disc, that is, specific gravity segregation. At the same time, due to the strong directional heat dissipation through the mold wall during casting, a large temperature difference is formed, resulting in the enrichment of high melting point components in the outer layer, and the enrichment of low melting point components and non-metallic impurities and gases in the core. It is also possible that regional segregation (also known as macro segregation) may occur due to the physical movement of the liquid or solid phase during the solidification process. Gravity segregation (i.e. microscopic segregation, also called microscopic segregation) occurs when the density of the precipitated crystals is different from that of the solution, and the crystals sink or float in the solution, resulting in an uneven chemical composition. The slower the cooling, the slower the increase in the number of crystals.

[0003] These two segregation phenomena will lead to uneven mechanical properties of the toothed disc, especially when subjected to alternating loads (loads whose magnitude and direction change periodically over time during operation). Segregation may lead to the formation and expansion of fatigue cracks, reduce the mechanical properties of the casting, easily lead to hot cracking and cold cracking, reduce the corrosion resistance of the casting, and in severe cases, cause the casting to be scrapped or fail due to unqualified performance or fracture. Since macrosegregation is mainly manifested as the uneven chemical composition of various regions inside the toothed disc casting, it can be observed with the naked eye or a low-power microscope, while microsegregation refers to the uneven chemical composition between grains or near grain boundaries inside the toothed disc casting, which usually requires a high-power microscope or electron microscope to observe, see reference: Qu Ying. Principles of Steelmaking [M]. Metallurgical Industry Press, 1994. Therefore, in the existing defect detection technologies (carbon and sulfur detection, chemical analysis, direct reading spectroscopy, metal in-situ analysis methods), many defect images involving micro-segregation on the images of the crankshaft castings cannot be directly detected, and it is even more impossible to non-destructively and quickly identify the defect images of micro-segregation through common macroscopic detection technologies such as DR ray scanning and ultrasonic scanning. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for detecting defects in a crankset, so as to solve one or more technical problems existing in the prior art and at least provide a beneficial choice or create conditions.

[0005] In order to achieve the above object, according to one aspect of the present invention, a method for detecting defects of a toothed disc is provided, the method comprising the following steps: Obtaining a radiographic scanning image of the toothed disc, and marking a semi-macro segregation characteristic line in the radiographic scanning image; The defect image of microsegregation is constructed from the diffuse distribution position of the semi-macro segregation characteristic line; A new radiographic scanning image is formed on the radiographic scanning image from the microscopically segregated defect image.

[0006] Furthermore, the method for obtaining the X-ray scanning image of the toothed disc is: scanning the toothed disc by using the XB-18 real-time digital imaging detection system of Maicixiongye to obtain the X-ray scanning image.

[0007] Furthermore, a method for marking a semi-macro segregation feature line in a ray scanning image is as follows: marking a boundary line of a sub-image obtained by segmenting the ray scanning image by a threshold segmentation method, in which the average grayscale value of all points on the boundary line is less than the average grayscale value of the ray scanning image, as a semi-macro segregation feature line.

[0008] Preferably, the threshold segmentation method is a maximum inter-class variance method or a histogram bimodal method.

[0009] Preferably, the method for marking the semi-macro segregation characteristic line in the ray scanning image is: marking the region of interest of the ray scanning image, and using the boundary line of the region of interest as the semi-macro segregation characteristic line.

[0010] Since it is difficult to directly obtain the defect image of microsegregation through macroscopic rapid X-ray scanning detection, there are some small macroscopic V-shaped segregations (semi-macro segregations, V-shaped segregations) that have been considered to be non-problematic and will not affect the quality of the toothed disc. According to relevant research, see reference: Yang Wen, Gan Ping. Semi-macro segregation of continuous casting billets [J]. Iron and Steel Research Information, 1983 (03): 77-78. DOI: CNKI: SUN: GTYJ.0.1983-03-010. Semi-macro segregation is mainly caused by the flow of high-concentration liquid phases formed by solidification shrinkage, and the accumulation and solidification are between macro segregation and micro segregation. The diffusion of semi-macro segregation in a small area will lead to invisible and serious micro segregation. By analyzing the diffusion distribution law of V-shaped segregation (semi-macro segregation), this application constructs the defect image of micro segregation through the following method, specifically: Furthermore, the method of constructing the defect image of micro segregation from the diffusion distribution position of the semi-macro segregation characteristic line is as follows: Mark the V-shaped pointing points on each semi-macro segregation characteristic line; Specifically, the vertex of the acute angle on the semi-macro-segregation characteristic line is recorded as the V-shaped pointing point, or the corner point farthest from the geometric center of gravity of the area formed by the semi-macro-segregation characteristic line among the corner points on the semi-macro-segregation characteristic line is recorded as the V-shaped pointing point; Determine the defect location range corresponding to each V-shaped pointing point; Specifically: the corner point with the smallest gray value among the corner points on the semi-macro segregation characteristic line except the V-shaped pointing point B is A, and the corner point with the largest gray value is C; connect the three points A, B, and C to obtain the flow source area △ABC, rotate △ABC 180° clockwise from the vertex B to obtain the flow direction area △DBF; △DBF is recorded as the defect positioning range.

[0011] Although the above triangular defect location range can roughly estimate the approximate range where microsegregation may diffuse in a small area, and the recognition speed is fast due to the simple algorithm, solidification shrinkage, gravity-induced convection and solid movement (such as bulging) will make the local shrinkage stress generated larger and smoother than the triangular area, which will lead to the above defect location range being insufficient in accuracy and difficult to cover the complete area of ​​microsegregation. In order to improve the location accuracy of the defect range, the present application provides the following preferred methods: Preferably, the corner point with the smallest grayscale value among the corner points on the semi-macro segregation characteristic line except the V-shaped pointing point B is A, and the corner point with the largest grayscale value is C; the three points A, B, and C are connected to obtain the flow source area △ABC, and △ABC is rotated 180° clockwise from the vertex B to obtain the flow direction area △DBF; the sector formed by taking ∠B of △DBF as the central angle and the side BF as the radius is recorded as the extended area, and the extended area is recorded as the defect positioning range.

[0012] Among them, the symbol ‌△ is a triangle, and the symbol ‌‌∠ is the angle symbol used to express the measure of an angle.

[0013] Search for paired points in each defect location range, and construct a micro-segregation defect image from each paired point; Specifically: all V-shaped pointing points within the defect location range are used as pairing points; (Note: each V-shaped pointing point corresponds to a defect location range); The range with the smallest average grayscale value in the defect location range corresponding to each pairing point is LRage, and the range with the largest average grayscale value is HRage; (Since the smaller the grayscale value of semi-macro segregation after solidification, the deeper the segregation, and vice versa, the lighter the segregation, the defect location range LRage with the smallest grayscale value (dark color) is the area with the largest diffusion flow strength starting from the pairing point, and the defect location range HRage with the largest grayscale value (light color) is the area with the smallest diffusion flow strength starting from the pairing point. Diffusion flow will cause micro segregation in the defect location range); The intersection area of ​​the defect positioning range corresponding to each paired point is taken as the core image block; the complement of each complement of LRage and the core image block whose average grayscale value is less than the average grayscale value of the core image block is taken as the first stitching image; the complement of each complement of HRage and the core image block whose average grayscale value is greater than the average grayscale value of the core image block is taken as the second stitching image; The first stitched image, the second stitched image and the core image block are stitched together to obtain a micro-segregation defect image.

[0014] The above method identifies each microsegregation area generated on the diffusion path of semi-macro segregation in a small area according to the magnitude of the diffusion flow force starting from the matching point, and according to the area from deep to shallow segregation, and splices the corresponding microsegregation defect image; however, in actual production, sometimes the diffusion path of semi-macro segregation is not linear. Due to the centrifugal force of centrifugal casting or the tension of die casting, the diffusion path of semi-macro segregation is open and diffuses in all directions. Therefore, the present application proposes the following preferred method to identify all images associated with the core image: Preferably, all V-shaped pointing points within the defect location range are used as pairing points; The range with the smallest average grayscale value in the defect location range corresponding to each pairing point is LRage, and the range with the largest average grayscale value is HRage; The pairing point corresponding to LRage is PL, the pairing point corresponding to HRage is PT, the straight line connecting PL and PT is recorded as the diffusion streamline, and the intersection area of ​​the defect location range corresponding to each pairing point is taken as the core image block; the complementary image of the defect location range corresponding to each pairing point and the core image block is taken; the sequence of complementary images is recorded in order from the distance from the set centroid point of each complementary image to the diffusion streamline as the diffusion image sequence; all complementary images that meet the diffusion flow conditions are recorded as spliced ​​images; all spliced ​​images are spliced ​​with the core image block to obtain the defect image of micro segregation.

[0015] Wherein, the diffusion flow conditions are: HG(i-1)>HG(i) and HG(i)<HG(i+1); HG(i) is the average grayscale value of all images from the 1st to the i-th image in the diffusion image sequence, and i is the sequence number.

[0016] Furthermore, the method of forming a new X-ray scanning image from a microscopically segregated defect image on a X-ray scanning image includes: Overlaying the micro-segregation defect image on the corresponding position on the X-ray scanning image to obtain an overlay X-ray scanning image; The covered ray scanning image is subjected to image denoising by a median filtering algorithm to obtain a denoised scanning image; The contrast of the scanned image is adjusted by using a histogram equalization algorithm to obtain an adjusted scanned image; Performing color correction processing on the adjusted scanned image by using a white balance algorithm to obtain a corrected scanned image; Input the corrected scanned image into a preset generator of a generative adversarial network to generate an image, thereby obtaining a labeled scanned image; The labeled scanned image is input into the discriminator of the generative adversarial network for image optimization to obtain a new ray scanned image.

[0017] Preferably, the method of forming a new radiographic scanning image from a microscopically segregated defect image on a radiographic scanning image is replaced by: The convolutional neural network is trained through the defect image of micro-segregation to obtain a trained convolutional neural network; The ray scanning image is recognized by the trained convolutional neural network to obtain a new labeled ray scanning image.

[0018] Preferably, the method of forming a new radiographic scanning image from a microscopically segregated defect image on a radiographic scanning image is replaced by: The corresponding position of the defect image of the micro segregation is marked on the X-ray scanning image to obtain a new X-ray scanning image.

[0019] The present invention also provides a defect detection system for a toothed disc, the defect detection system for a toothed disc comprising: a processor, a memory, and a computer script program stored in the memory and executable on the processor, the processor implementing the steps in the defect detection method for a toothed disc when executing the computer script program, the defect detection system for a toothed disc can be run in computing devices such as desktop computers, notebook computers, PDAs, and cloud data centers, the executable system may include, but is not limited to, a processor, a memory, and a server cluster, the processor executing the computer program runs in the following system units: A segregation feature marking unit, used for acquiring a radiographic scanning image of the toothed disc and marking a semi-macroscopic segregation feature line in the radiographic scanning image; A defect image construction unit, used to construct a defect image of micro segregation from the diffuse distribution position of the semi-macro segregation characteristic line; The microscopic image display unit is used to form a new ray scanning image from a microscopically segregated defect image on the ray scanning image.

[0020] The beneficial effects of the present invention are as follows: the present invention provides a defect detection method and system for a toothed disc, which can non-destructively and quickly identify defect images of micro-segregation through common ray scanning methods, and can cover the entire area of ​​micro-segregation, thereby improving image recognition accuracy, and can improve the graphic recognition accuracy of defect images through accurately trained image recognition models. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and other features of the present invention will become more obvious by describing in detail the embodiments shown in the accompanying drawings. The same reference numerals in the accompanying drawings of the present invention represent the same or similar elements. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other accompanying drawings can be obtained based on these accompanying drawings without creative work. In the accompanying drawings: Figure 1 Shown is a flow chart of a method for detecting defects in a toothed disc; Figure 2 The new X-ray scanning image formed by adding a defect image of micro segregation in Example 1 is shown; Figure 3 The new X-ray scanning image formed by adding a defect image of micro segregation in Example 2 is shown; Figure 4 The new X-ray scanning image formed by adding a defect image of micro segregation in Example 3 is shown; Figure 5 Shown is a diagram of a defect detection system based on a toothed disc. DETAILED DESCRIPTION

[0022] The following will be combined with the embodiments and drawings to clearly and completely describe the concept, specific structure and technical effects of the present invention, so as to fully understand the purpose, scheme and effect of the present invention. It should be noted that the embodiments and features in the embodiments of this application can be combined with each other without conflict.

[0023] Example 1 like Figure 1 The flowchart of a method for detecting a defect of a toothed disc according to the present invention is shown below. Figure 1 A method for detecting defects in a toothed disc according to an embodiment of the present invention will be described below.

[0024] A method for detecting defects in a toothed disc comprises the following steps: Obtaining a radiographic scanning image of the toothed disc, and marking a semi-macro segregation characteristic line in the radiographic scanning image; The defect image of microsegregation is constructed from the diffuse distribution position of the semi-macro segregation characteristic line; A new radiographic scanning image is formed on the radiographic scanning image from the microscopically segregated defect image.

[0025] Furthermore, the method for obtaining the X-ray scanning image of the toothed disc is: scanning the toothed disc by using the XB-18 real-time digital imaging detection system of Maicixiongye to obtain the X-ray scanning image.

[0026] Wherein, the ray scanning image is corrected for scattered rays.

[0027] Furthermore, a method for marking a semi-macro segregation feature line in a ray scanning image is as follows: marking a boundary line of a sub-image obtained by segmenting the ray scanning image by a threshold segmentation method, in which the average grayscale value of all points on the boundary line is less than the average grayscale value of the ray scanning image, as a semi-macro segregation feature line.

[0028] Among them, the threshold segmentation method is the maximum inter-class variance method.

[0029] Since it is difficult to directly obtain the defect image of microsegregation through macroscopic rapid X-ray scanning detection, there are some small macroscopic V-shaped segregations (semi-macro segregations, V-shaped segregations) that have been considered to be non-problematic and will not affect the quality of the toothed disc. According to relevant research, see reference: Yang Wen, Gan Ping. Semi-macro segregation of continuous casting billets [J]. Iron and Steel Research Information, 1983 (03): 77-78. DOI: CNKI: SUN: GTYJ.0.1983-03-010. Semi-macro segregation is mainly caused by the flow of high-concentration liquid phases formed by solidification shrinkage, and the accumulation and solidification are between macro segregation and micro segregation. The diffusion of semi-macro segregation in a small area will lead to invisible and serious micro segregation. By analyzing the diffusion distribution law of V-shaped segregation (semi-macro segregation), this application constructs the defect image of micro segregation through the following method, specifically: Furthermore, the method of constructing the defect image of micro segregation from the diffusion distribution position of the semi-macro segregation characteristic line is as follows: Mark the V-shaped pointing points on each semi-macro segregation characteristic line; Specifically: the vertex of the acute angle on the semi-macro segregation characteristic line is recorded as the V-shaped pointing point; Determine the defect location range corresponding to each V-shaped pointing point; Specifically: the corner point with the smallest gray value among the corner points on the semi-macro segregation characteristic line except the V-shaped pointing point B is A, and the corner point with the largest gray value is C; connect the three points A, B, and C to obtain the flow source area △ABC, rotate △ABC 180° clockwise from the vertex B to obtain the flow direction area △DBF; △DBF is recorded as the defect positioning range.

[0030] Among them, the key source code of the C# language description of the specific implementation of the method for determining the defect location range corresponding to each V-shaped pointing point is: Class Program { / / The corner point list is pointList, each point contains a grayscale value List <pointwithgrayvalue>pointList = GetCornerPoints(); / / Find the corner point A with the smallest gray value and the corner point C with the largest gray value, excluding the point B pointed by the V shape PointWithGrayValue A = FindMinGrayValuePoint(pointList, outPointWithGrayValue B); PointWithGrayValue C = FindMaxGrayValuePoint(pointList, B); / / Calculate the flow source area △ABC Triangle ABC = new Triangle(A.Point, B.Point, C.Point); / / Rotate △ABC to get the flow direction area △DBF Triangle DBF = RotateTriangle(ABC, B.Point, 180); static List <pointwithgrayvalue>GetCornerPoints() {static PointWithGrayValue FindMinGrayValuePoint(List <pointwithgrayvalue>points, out PointWithGrayValue excludedPoint) {excludedPoint = points.Find(p =>p.Point == new Point(125, 225)); / / Assume this is point B PointWithGrayValue minPoint = null; foreach (var point in points) {if (!point.Equals(excludedPoint)&&(minPoint == null ||point.GrayValue<minPoint.GrayValue)) {minPoint = point;}} return minPoint;} static PointWithGrayValue FindMaxGrayValuePoint(List <pointwithgrayvalue>points, PointWithGrayValue excludedPoint) {PointWithGrayValue maxPoint = null; foreach (var point in points) {if (!point.Equals(excludedPoint)&&(maxPoint == null ||point.GrayValue>maxPoint.GrayValue)) {maxPoint = point;}} return maxPoint;} static Triangle RotateTriangle(Triangle triangle, PointrotationCenter, float angle) {Point vertex1 = RotatePoint(triangle.Vertex1, rotationCenter,angle); Point vertex2 = RotatePoint(triangle.Vertex2, rotationCenter, angle); Point vertex3 = RotatePoint(triangle.Vertex3, rotationCenter, angle); return new Triangle(vertex1, vertex2, vertex3);} static Point RotatePoint(Point point, Point center, float angle) {double radians = angle * Math.PI / 180; int x = (int)(Math.Cos(radians) * (point.X - center.X) - Math.Sin(radians) * (point.Y - center.Y) + center.X); int y = (int)(Math.Sin(radians) * (point.X - center.X) + Math.Cos(radians) * (point.Y - center.Y) + center.Y); return new Point(x, y);}} class PointWithGrayValue {public Point Point { get;} public int GrayValue { get;} public PointWithGrayValue(Point point, int grayValue) {Point = point; GrayValue = grayValue;}}.

[0031] Search for paired points in each defect location range, and construct a micro-segregation defect image from each paired point; Specifically: all V-shaped pointing points within the defect location range are used as pairing points; (Note: each V-shaped pointing point corresponds to a defect location range); The range with the smallest average grayscale value in the defect location range corresponding to each pairing point is LRage, and the range with the largest average grayscale value is HRage; (Since the smaller the grayscale value of semi-macro segregation after solidification, the deeper the segregation, and vice versa, the lighter the segregation, the defect location range LRage with the smallest grayscale value (dark color) is the area with the largest diffusion flow strength starting from the pairing point, and the defect location range HRage with the largest grayscale value (light color) is the area with the smallest diffusion flow strength starting from the pairing point. Diffusion flow will cause micro segregation in the defect location range); The intersection area of ​​the defect positioning range corresponding to each paired point is taken as the core image block; the complement of each complement of LRage and the core image block whose average grayscale value is less than the average grayscale value of the core image block is taken as the first stitching image; the complement of each complement of HRage and the core image block whose average grayscale value is greater than the average grayscale value of the core image block is taken as the second stitching image; The first stitched image, the second stitched image and the core image block are stitched together to obtain a micro-segregation defect image.

[0032] The key source code of the C# language description of the specific implementation of the method of searching for paired points in each defect positioning range and constructing a micro-segregation defect image from each paired point is: public class DefectImageMerger {public List <defectregion>DefectRegions { get; set;} / / Defect location range public List <pointf>VPoints { get; set;} / / V-shaped pointing points public DefectImageMerger(List <defectregion>defectRegions, List <pointf>vPoints) {DefectRegions = defectRegions; VPoints = vPoints;} public Image MergeDefectImages() {var pairingPoints = VPoints; var LRange = GetLRage(pairingPoints); var HRange = GetHRage(pairingPoints); var coreImageBlock = CalculateCoreImageBlock(pairingPoints); var firstStitchImage = GetFirstStitchImage(LRange, coreImageBlock); var secondStitchImage = GetSecondStitchImage(HRange, coreImageBlock); return StitchImages(firstStitchImage, secondStitchImage,coreImageBlock); } private DefectRegion GetLRage(IEnumerable <pointf>pairingPoints) { / / Get the area with the smallest average gray value in the defect positioning range corresponding to each paired point return pairingPoints.Select(p =>GetDefectRegionAtPoint(p)) OrderBy(region =>region.AverageGrayValue) FirstOrDefault();} private DefectRegion GetHRage(IEnumerable <pointf>pairingPoints) { / / Get the area with the largest average gray value in the defect location range corresponding to each paired point return pairingPoints.Select(p =>GetDefectRegionAtPoint(p)) OrderByDescending(region =>region.AverageGrayValue) FirstOrDefault();} private DefectRegion CalculateCoreImageBlock(IEnumerable <pointf>pairingPoints) { / / Calculate the intersection of all paired points corresponding to the defect area return new DefectRegion(); / / Returns the core image block} private Image GetFirstStitchImage(DefectRegion LRange, DefectRegioncoreImageBlock) {var complementImages = GetComplementImages(LRange); var validComplements = complementImages.Where(img =>img.AverageGrayValue <coreImageBlock.AverageGrayValue).ToList(); / / Stitch the valid complement images return CombineImages(validComplements);} private Image GetSecondStitchImage(DefectRegion HRange, DefectRegioncoreImageBlock) {var complementImages = GetComplementImages(HRange); var validComplements = complementImages.Where(img =>img.AverageGrayValue>coreImageBlock.AverageGrayValue).ToList(); / / Stitch the valid complement images return CombineImages(validComplements);} private List GetComplementImages(DefectRegion region) { / / Get the complement image based on the defect area return new List (); / / Returns a list of complement images} private Image StitchImages(Image firstStitch, Image secondStitch,DefectRegion coreImageBlock) { return new Bitmap(1, 1); / / Return the final stitched image} private Image CombineImages(List images) {return new Bitmap(1, 1); / / Return the merged image} private DefectRegion GetDefectRegionAtPoint(PointF point) { / / Get the defect location range (DefectRegion) based on the point / / Get the area data corresponding to this point here return new DefectRegion(); / / Returns the defect region}}.

[0033] Among them, according to the formation mechanism of the V-shaped pointing point of macro-segregation, it can be known that the diffusion within a small area formed by the flow channel formed by the sliding of the two-phase region in the equiaxed crystal at the position corresponding to the V-shaped pointing point will form a defect image of micro-segregation nearby; each pairing point can accurately locate the position of the defect image of micro-segregation in the X-ray scanning image.

[0034] Among them, the formation mechanism of the V-shaped pointing point of semi-macro segregation is as follows: in the early stage of solidification, columnar crystals grow, and as the temperature decreases, equiaxed crystals begin to grow and replace columnar crystals; when the center of the ingot is still liquid, there is still a small amount of solid phase in the liquid phase, forming a two-phase region with flowing properties; due to the effects of gravity and solidification shrinkage, equiaxed crystals slide in the two-phase region to form flow channels; these flow channels are located in the V-shaped cone area along the pouring direction, and finally form V-shaped segregation during solidification, and its V-shaped apex is the V-shaped pointing point. See reference: Zhang Weiping, Shen Houfa. Several factors affecting A, V-shaped segregation in steel ingots [J]. Anshan Iron and Steel Technology, 1995(6):6.

[0035] Furthermore, the method of forming a new X-ray scanning image from a microscopically segregated defect image on a X-ray scanning image includes: Overlaying the micro-segregation defect image on the corresponding position on the X-ray scanning image to obtain an overlay X-ray scanning image; The covered ray scanning image is subjected to image denoising by a median filtering algorithm to obtain a denoised scanning image; The contrast of the scanned image is adjusted by using a histogram equalization algorithm to obtain an adjusted scanned image; Performing color correction processing on the adjusted scanned image by using a white balance algorithm to obtain a corrected scanned image; Input the corrected scanned image into a preset generator of a generative adversarial network to generate an image, thereby obtaining a labeled scanned image; The labeled scanned image is input into the discriminator of the generative adversarial network for image optimization, and the following is obtained: Figure 2 New ray scan image shown.

[0036] Example 2 This embodiment 2 replaces the method of marking all the same boundary points corresponding to the current crack boundary point on the basis of embodiment 1, specifically: On the basis of Example 1, the method of marking the semi-macro segregation characteristic line in the ray scanning image is replaced by: marking the region of interest of the ray scanning image, and taking the boundary line of the region of interest as the semi-macro segregation characteristic line.

[0037] On the basis of Example 1, the method of marking the V-shaped pointing points on each semi-macro segregation characteristic line is replaced by: the corner point farthest from the geometric center of gravity of the area formed by the semi-macro segregation characteristic line among each corner point on the semi-macro segregation characteristic line is recorded as the V-shaped pointing point.

[0038] Although the above triangular defect location range can roughly estimate the approximate range where microsegregation may diffuse in a small area, and the recognition speed is fast due to the simple algorithm, solidification shrinkage, gravity-induced convection and solid movement (such as bulging) will make the local shrinkage stress generated larger and smoother than the triangular area, which will lead to the above defect location range being insufficient in accuracy and difficult to cover the complete area of ​​microsegregation. In order to improve the location accuracy of the defect range, the present application provides the following preferred methods: On the basis of Example 1, the method for determining the defect location range corresponding to each V-shaped pointing point is replaced as follows: the corner point with the smallest grayscale value among the corner points on the semi-macro segregation characteristic line except the V-shaped pointing point B is taken as A, and the corner point with the largest grayscale value is taken as C; the three points A, B, and C are connected to obtain the flow source area △ABC, and △ABC is rotated 180° clockwise from the vertex B to obtain the flow direction area △DBF; the sector formed by taking ∠B of △DBF as the central angle and the side BF as the radius is recorded as the extended area, and the extended area is recorded as the defect location range.

[0039] Among them, the symbol ‌△ is a triangle, and the symbol ‌‌∠ is the angle symbol used to express the measure of an angle.

[0040] Among them, the key source code of the C# language description of the specific implementation of the method for determining the defect location range corresponding to each V-shaped pointing point of this embodiment 2 is: using System.Drawing; / / Use the System.Drawing.Common NuGet package public class DefectLocationProcessor {public List <pointgray>CornerPoints { get; set;} / / Corner point set, including points and corresponding grayscale values public DefectLocationProcessor(List <pointgray>cornerPoints) {CornerPoints = cornerPoints;} public (PointF A, PointF B, PointF C, PointF D, PointF F)CalculateRegions() {if (CornerPoints == null || CornerPoints.Count<3) throw new InvalidOperationException("At least three corner points are required"); / / Determine points A, B, and C var pointB = GetPointB(); / / Point to point B var pointA = GetPointWithMinGrayValue(pointB); / / The corner point with the minimum grayscale var pointC = GetPointWithMaxGrayValue(); / / Corner point with maximum grayscale / / Calculate points D and F to form an expansion area var pointD = RotatePoint(pointB, pointA, 180); var pointF = RotatePoint(pointB, pointC, 180); return (pointA, pointB, pointC, pointD, pointF);} private PointF GetPointB() { / / V-shaped pointing point return new PointF(CornerPoints[0].X, CornerPoints[0].Y);} private PointF GetPointWithMinGrayValue(PointF excludePoint) {float minGray = float.MaxValue; PointF minPoint = PointF.Empty; foreach (var point in CornerPoints) {if (point.ToPointF() != excludePoint&&point.GrayValue<minGray){ minGray = point.GrayValue; minPoint = point.ToPointF();}} return minPoint;} private PointF GetPointWithMaxGrayValue() {float maxGray = float.MinValue; PointF maxPoint = PointF.Empty; foreach (var point in CornerPoints) {if (point.GrayValue>maxGray){ maxGray = point.GrayValue;maxPoint = point.ToPointF(); }} return maxPoint;} / / Rotate △ABC 180° clockwise around vertex B to obtain the flow direction region △DBF private PointF RotatePoint(PointF center, PointF point, float angle) {double radians = angle * Math.PI / 180.0; float cosTheta = (float)Math.Cos(radians); float sinTheta = (float)Math.Sin(radians); float rotatedX = center.X + (point.X - center.X) * cosTheta -(point.Y - center.Y) * sinTheta; float rotatedY = center.Y + (point.X - center.X) * sinTheta +(point.Y - center.Y) * cosTheta; return new PointF(rotatedX, rotatedY);}} public class PointGray {public int X { get; set;} public int Y { get; set;} public float GrayValue { get; set;} public PointF ToPointF() =>new PointF(X, Y);}.

[0041] The method of forming a new ray scanning image from a microscopically segregated defect image on a ray scanning image is replaced by: marking the corresponding position of the microscopically segregated defect image on the ray scanning image, and obtaining the following Figure 3 New ray scan image shown.

[0042] Example 3 The above method identifies each microsegregation area generated on the diffusion path of semi-macro segregation in a small area according to the magnitude of the diffusion flow force starting from the matching point, and according to the area from deep to shallow segregation, and splices the corresponding microsegregation defect image; however, in actual production, sometimes the diffusion path of semi-macro segregation is not linear. Due to the centrifugal force of centrifugal casting or the tension of die casting, the diffusion path of semi-macro segregation is open and diffuses in all directions. Therefore, the present application proposes the following preferred method to identify all images associated with the core image: In this embodiment 3, based on the embodiment 1, the method of searching for paired points in each defect positioning range and constructing a defect image of micro segregation from each paired point is replaced by: Preferably, all V-shaped pointing points within the defect location range are used as pairing points; The range with the smallest average grayscale value in the defect location range corresponding to each pairing point is LRage, and the range with the largest average grayscale value is HRage; The pairing point corresponding to LRage is PL, the pairing point corresponding to HRage is PT, the straight line connecting PL and PT is recorded as the diffusion streamline, and the intersection area of ​​the defect location range corresponding to each pairing point is taken as the core image block; the complementary image of the defect location range corresponding to each pairing point and the core image block is taken; the sequence of complementary images is recorded in order from the distance from the set centroid point of each complementary image to the diffusion streamline as the diffusion image sequence; all complementary images that meet the diffusion flow conditions are recorded as spliced ​​images; all spliced ​​images are spliced ​​with the core image block to obtain the defect image of micro segregation.

[0043] Wherein, the diffusion flow conditions are: HG(i-1)>HG(i) and HG(i)<HG(i+1); HG(i) is the average grayscale value of all images from the 1st to the i-th image in the diffusion image sequence, and i is the sequence number.

[0044] The key source code of the C# language description of the specific implementation of the method of searching for paired points in each defect positioning range and constructing a micro-segregation defect image from each paired point in this embodiment 3 is: using System.Drawing; / / To use the System.Drawing.Common NuGet package class DefectImageProcessor {public DefectImageProcessor(List coreImageBlock, List <point>pl, List <point>pt) {CoreImageBlock = coreImageBlock; LRage PL = pl; HRage PT = pt;} public List ProcessImages() {var diffuseImages = new List (); / / Calculate the complement image of the core image block foreach (var image in CoreImageBlock) {var complementImage = CalculateComplement(image); diffuseImages.Add(complementImage);} / / Calculate the distance from the center of gravity to the diffusion streamline PL to PT var sortedDiffuseImages = diffuseImages.OrderBy(img =>CalculateDistanceToLine(PL, PT, img)).ToList(); / / Calculate HG(i) var hgValues ​​= new List <double>(); for (int i = 0; i <sortedDiffuseImages.Count; i++) {hgValues.Add(CalculateAverageGrayValue(sortedDiffuseImages.Take(i +1)));} / / Determine the stitched image var stitchedImages = new List (); for (int i = 1; i <hgValues.Count - 1; i++) {if (hgValues[i - 1]>hgValues[i]&&hgValues[i] <hgValues[i + 1]) {stitchedImages.Add(sortedDiffuseImages[i]); }} / / Stitch all stitched images and core image blocks return StitchImages(stitchedImages, CoreImageBlock);} private double CalculateAverageGrayValue(IEnumerable images) { / / Calculate the average gray value double totalGrayValue = 0; int count = 0; foreach (var img in images) {totalGrayValue += GetImageGrayValue(img); / / The function returns the average gray value of a single image count++;} return count == 0 ? 0 : totalGrayValue / count; }private double GetImageGrayValue(Image img) { / / Get the average gray value of the image Bitmap bitmap = new Bitmap(img); double totalBrightness = 0; for (int y = 0; y <bitmap.Height; y++) {for (int x = 0; x <bitmap.Width; x++) {totalBrightness += bitmap.GetPixel(x, y).GetBrightness();}} return totalBrightness / (bitmap.Width * bitmap.Height);}}.

[0045] In this embodiment 3, based on the embodiment 1, the method of forming a new ray scanning image from a microscopic segregation defect image on a ray scanning image is replaced by: training a convolutional neural network through a microscopic segregation defect image to obtain a trained convolutional neural network; recognizing the ray scanning image through the trained convolutional neural network to obtain Figure 4 The new annotated ray scan image is shown.

[0046] The diffusion flow condition is to determine all the areas affected by the tension or centrifugal force of the semi-macro segregation in turn according to the color depth changes of all the micro segregations radiated by the core image block, so as to accurately identify the defect image of the micro segregation.

[0047] Preferably, whether the toothed disc has a micro-segregation defect is determined according to the image position of the micro-segregation defect marked on the new X-ray scanning image.

[0048] The embodiment of the present invention provides a defect detection system based on a toothed disc, such as Figure 5 Shown is a diagram of a defect detection system based on a crankset of the present invention. The defect detection system based on a crankset of this embodiment includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above-mentioned embodiment of the defect detection system based on a crankset are implemented.

[0049] The system comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to run in the following units of the system: A segregation feature marking unit, used for acquiring a radiographic scanning image of the toothed disc and marking a semi-macroscopic segregation feature line in the radiographic scanning image; A defect image construction unit, used to construct a defect image of micro segregation from the diffuse distribution position of the semi-macro segregation characteristic line; The microscopic image display unit is used to form a new ray scanning image from a microscopically segregated defect image on the ray scanning image.

[0050] The defect detection system based on a crankset can be run on computing devices such as desktop computers, laptop computers, PDAs, and cloud servers. The defect detection system based on a crankset can be operated on systems including, but not limited to, processors and memories. Those skilled in the art will appreciate that the example is merely an example of a defect detection system based on a crankset and does not constitute a limitation on a defect detection system based on a crankset. It can include more or fewer components than the example, or a combination of certain components, or different components. For example, the defect detection system based on a crankset can also include input and output devices, network access devices, buses, etc.

[0051] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the operating system of the defect detection system based on a toothed disk, and uses various interfaces and lines to connect various parts of the entire operating system of the defect detection system based on a toothed disk.

[0052] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the defect detection system based on a toothed disk by running or executing the computer program and / or module stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0053] Although the description of the present invention has been quite detailed and has been described in particular with respect to several described embodiments, it is not intended to be limited to any of these details or embodiments or any particular embodiment, so as to effectively cover the intended scope of the present invention. In addition, the present invention is described above with the embodiments foreseeable by the inventors, and its purpose is to provide a useful description, and those non-substantial changes to the present invention that are not currently foreseen may still represent equivalent changes of the present invention.< / double> < / point> < / point> < / pointgray> < / pointgray> < / pointf> < / pointf> < / pointf> < / pointf> < / defectregion> < / pointf> < / defectregion> < / pointwithgrayvalue> < / pointwithgrayvalue> < / pointwithgrayvalue> < / pointwithgrayvalue>

Claims

1. A method for detecting defects in a toothed disc, characterized in that: The method comprises the following steps: Obtaining a radiographic scanning image of the toothed disc, and marking a semi-macro segregation characteristic line in the radiographic scanning image; The defect image of microsegregation is constructed from the diffuse distribution position of the semi-macro segregation characteristic line; A new radiographic scanning image is formed on the radiographic scanning image from the microscopically segregated defect image.

2. A method for detecting defects in a crankset according to claim 1, characterized in that: The method for marking the semi-macro segregation feature line in the ray scanning image is as follows: marking the boundary line of the sub-image obtained by segmenting the ray scanning image by the threshold segmentation method, in which the average gray value of all points on the boundary line is less than the average gray value of the ray scanning image, as the semi-macro segregation feature line.

3. A method for detecting defects in a crankset according to claim 1, characterized in that: The method of constructing the defect image of micro segregation from the diffusion distribution position of the semi-macro segregation characteristic line is: Mark the V-shaped pointing points on each semi-macro segregation characteristic line; Determine the defect location range corresponding to each V-shaped pointing point; Pairing points are searched in each defect location range, and a defect image of microsegregation is constructed from each pairing point.

4. A method for detecting defects in a crankset according to claim 3, characterized in that: The method of marking the V-shaped pointing point on each semi-macro segregation characteristic line is as follows: the vertex of the acute angle on the semi-macro segregation characteristic line is recorded as the V-shaped pointing point, or the corner point farthest from the geometric center of gravity of the area formed by the semi-macro segregation characteristic line among the corner points on the semi-macro segregation characteristic line is recorded as the V-shaped pointing point.

5. A method for detecting defects in a crankset according to claim 3, characterized in that: The method for determining the defect location range corresponding to each V-shaped pointing point is as follows: the corner point with the smallest grayscale value among the corner points on the semi-macro segregation characteristic line except the V-shaped pointing point B is A, and the corner point with the largest grayscale value is C; connect the three points A, B, and C to obtain the flow source area △ABC, rotate △ABC 180° clockwise from the vertex B to obtain the flow direction area △DBF; record △DBF as the defect location range.

6. A method for detecting defects in a crankset according to claim 5, characterized in that: The method for determining the defect location range corresponding to each V-shaped pointing point is replaced by: the corner point with the smallest grayscale value among the corner points on the semi-macro segregation characteristic line except the V-shaped pointing point B is taken as A, and the corner point with the largest grayscale value is taken as C; the flow source area △ABC is obtained by connecting the three points A, B, and C, and the flow direction area △DBF is obtained by rotating △ABC 180° clockwise from the vertex B; the sector formed by taking ∠B of △DBF as the central angle and the side BF as the radius is recorded as the extended area, and the extended area is recorded as the defect location range.

7. A method for detecting defects in a crankset according to claim 3, characterized in that: The method of searching for pairing points in each defect positioning range and constructing a micro-segregation defect image from each pairing point is as follows: all V-shaped pointing points in the defect positioning range are taken as pairing points; the range with the smallest average grayscale value in the defect positioning range corresponding to each pairing point is taken as LRage, and the range with the largest average grayscale value is taken as HRage; the intersection area of ​​the defect positioning range corresponding to each pairing point is taken as the core image block; the complement of each complement of LRage and the core image block whose average grayscale value is less than the average grayscale value of the core image block is taken as the first stitching image; the complement of each complement of HRage and the core image block whose average grayscale value is greater than the average grayscale value of the core image block is taken as the second stitching image; The first stitched image, the second stitched image and the core image block are stitched together to obtain a micro-segregation defect image.

8. A method for detecting defects in a crankset according to claim 7, characterized in that: The method of searching for paired points in each defect location range and constructing a defect image of microsegregation from each paired point is replaced by: Take all V-shaped pointing points within the defect positioning range as pairing points; take the range with the smallest average grayscale value in the defect positioning range corresponding to each pairing point as LRage, and the range with the largest average grayscale value as HRage; let the pairing point corresponding to LRage be PL, and the pairing point corresponding to HRage be PT, and the straight line connecting PL to PT be recorded as the diffusion streamline, and take the intersection area of ​​the defect positioning range corresponding to each pairing point as the core image block; take the complementary image of the defect positioning range corresponding to each pairing point and the core image block; take the distance from the set centroid point of each complementary image to the diffusion streamline from small to large to form a sequence of complementary images as a diffusion image sequence; all complementary images that meet the diffusion flow condition are recorded as stitched images; all stitched images are stitched with the core image block to obtain a defect image of micro segregation.

9. A defect detection system for a toothed disc, characterized in that: The defect detection system for a crankset comprises: a processor, a memory, and a computer script program stored in the memory and running on the processor. When the processor executes the computer script program, the steps in any one of the defect detection methods for a crankset in claims 1-8 are implemented.

Images