Metal surface defect detection method
By performing rubbing and coating operations on the metal surface, the rubbing images are obtained to identify surface defects, which solves the subjectivity of manual detection and the reflection impact of visual detection, and achieves efficient and accurate detection of metal surface defects and optimizes the production process.
Patent Information
- Application Number
- CN202411409320.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-10
- Publication Date
- 2024-12-10
- Estimated Expiration
- 2044-10-10
AI Technical Summary
The existing metal surface defect detection methods have problems with subjectivity and fatigue susceptibility to manual detection, as well as the problem that automated visual detection is difficult to obtain high-quality images on high-reflectivity metal materials and complex shapes.
Using rubbing technology, by marking specific points on metal surfaces and performing paint operations, rubbing images are obtained for analysis, normal and abnormal areas of the surface are identified, and workpieces are classified to improve detection accuracy and consistency.
Through the printing technology, errors are reduced, the morphological information is accurately obtained, the impact of reflection is eliminated, the reliability and efficiency of detection is improved, different types of surface defects can be accurately identified, the production process is optimized, and costs and resource waste are reduced.
Smart Images

Figure CN119104559A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of metal surface defect detection, and in particular to a metal surface defect detection method. Background Art
[0002] In industrial production, metal materials are widely used, especially in the manufacture of various parts and equipment. The quality of the metal surface determines the performance and service life of metal products to a certain extent. Therefore, defect detection on the metal surface is an extremely important process step, especially in the field of precision manufacturing. The control of surface quality directly affects the overall performance of the product.
[0003] At present, the detection methods for metal surface defects can be roughly divided into two categories: manual detection and automated detection. Manual detection is usually performed by experienced technical workers who judge the quality of the metal surface visually or with the help of simple tools. Although this detection method has certain flexibility, it also has obvious defects. First, manual detection is limited by the personal ability of the inspectors, is highly subjective and unstable, and different inspectors may give different test results. Second, manual detection is easily affected by factors such as fatigue, and is prone to misjudgment or missed detection when working for a long time or at a high detection intensity. In addition, manual detection is inefficient and difficult to adapt to the needs of large-scale production.
[0004] With the advancement of science and technology, automated detection technology has gradually been applied in the field of metal surface detection; a common automated detection method is visual detection, which is based on computer image processing technology. It uses a camera to collect metal surface images, and then uses image processing algorithms to identify defects on the metal surface. Compared with manual detection, this method has higher detection accuracy and efficiency, but there are also some technical difficulties in practical applications; for example, the reflective properties of the metal surface can easily affect the clarity and recognition accuracy of the image, especially on metal materials with high reflectivity, the detection system is difficult to obtain high-quality images; in addition, when facing metal products with complex shapes, visual detection often requires multiple adjustments to the detection equipment, which increases the difficulty and cost of detection.
[0005] In summary, this method proposes a metal surface defect detection method, which detects defects on the metal surface by rubbing the metal surface and collecting the rubbing image of the metal surface for analysis, thereby solving the subjectivity and fatigue of manual detection, and at the same time, solving the influence of the reflective properties of the metal surface in visual inspection. Summary of the invention
[0006] The present invention provides a metal surface defect detection method, which helps solve the problems mentioned in the above background technology.
[0007] The present invention provides the following technical solution: a metal surface defect detection method, comprising:
[0008] Each round metal piece to be inspected is recorded as a test workpiece;
[0009] The circular metal sheet is a thin sheet made of metal;
[0010] The surfaces of two circular faces of the test workpiece are inspected;
[0011] Obtain two surfaces of each test workpiece that need to be inspected, and record them as a first inspection surface and a second inspection surface of the test workpiece respectively;
[0012] Take any test workpiece and record it as the workpiece to be tested;
[0013] Marking points X1 and X2 of the first detection surface and points Y1 and Y2 of the second detection surface on the workpiece to be detected;
[0014] Acquire a first detection surface of the workpiece to be tested, and perform a coating operation on the workpiece to be tested;
[0015] The workpiece to be tested that has completed one coating operation is recorded as workpiece No. 1;
[0016] Perform a rubbing operation on workpiece No. 1, and mark points X3 and X4 to obtain a first rubbing pattern;
[0017] Acquire the second inspection surface of workpiece No. 1 and perform a secondary coating operation on workpiece No. 1;
[0018] The workpiece No. 1 that has completed the secondary coating operation is recorded as the workpiece No. 2, and a rubbing operation is performed on the workpiece No. 2, and points Y3 and Y4 are marked to obtain a second rubbing pattern;
[0019] Collecting images of the first rubbing pattern and the second rubbing pattern respectively, and recording them as the first image and the second image respectively;
[0020] Processing the first image and the second image to form a first image and a second image;
[0021] According to the first image and the second image, respectively obtain the normal area and the abnormal area on the first detection surface and the second detection surface of the workpiece to be detected;
[0022] The normal area and the abnormal area of the first detection surface and the second detection surface are compared to classify the workpiece to be detected.
[0023] Optionally, marking the points X1 and X2 of the first detection surface and the points Y1 and Y2 of the second detection surface on the workpiece to be detected includes:
[0024] Obtaining an edge contour line of a first detection surface or a second detection surface of a workpiece to be detected, recorded as a surface contour line;
[0025] Adjust the workpiece to be measured so that the plane enclosed by the surface contour is parallel to the horizontal plane;
[0026] Draw two vertical lines perpendicular to the horizontal plane, so that the vertical lines intersect with the edge contours of the first detection surface and the second detection surface of the workpiece to be measured, and record the two vertical lines as the first vertical line and the second vertical line respectively;
[0027] The intersection point of the first vertical line with the first detection surface is recorded as point X1, and the intersection point with the second detection surface is recorded as point Y1;
[0028] The intersection point of the second perpendicular line with the first detection surface is recorded as point X2, and the intersection point of the second perpendicular line with the second detection surface is recorded as point Y2.
[0029] Optionally, the obtaining of the first detection surface of the workpiece to be detected and performing a coating operation on the workpiece to be detected is specifically as follows:
[0030] Acquire a first detection surface of the workpiece to be detected;
[0031] Paint is evenly applied on the first detection surface of the workpiece to be tested, and the paint completely covers the first detection surface of the workpiece to be tested, thereby completing a coating operation on the workpiece to be tested.
[0032] Optionally, performing a rubbing operation on workpiece No. 1 and marking points X3 and X4 to obtain a first rubbing pattern includes:
[0033] A rubbing paper for carrying a rubbing pattern is provided;
[0034] Obtain a circular metal sheet with a shape and size that meets production requirements and record it as a standard workpiece;
[0035] Obtain two circular surfaces of a standard workpiece, and arbitrarily select one of the circular surfaces as a reference circular surface;
[0036] Make the reference circular surface parallel to the plane of the rubbing paper, and project it vertically onto the rubbing paper, draw the edge contour line of the projection on the rubbing paper, and record the edge contour line as the reference contour diagram;
[0037] Place workpiece No. 1 on top of the rubbing paper so that the first detection surface of workpiece No. 1 is below the second detection surface;
[0038] Project workpiece No. 1 onto the rubbing paper, and record the projection of workpiece No. 1 on the rubbing paper as projection No. 1;
[0039] Adjust the position of workpiece No. 1 so that the edge contour line of projection No. 1 on the rubbing paper coincides with the reference contour map, and use this position as the No. 1 rubbing preparation position for workpiece No. 1;
[0040] Control workpiece No. 1 to move vertically downward from No. 1 rubbing preparation position. When it touches the rubbing paper, stop moving and keep for six seconds. At the same time, project point X1 and point X2 vertically onto the rubbing paper and mark them, and record them as point X3 and point X4 respectively;
[0041] When the contact time between workpiece No. 1 and the rubbing paper is six seconds, workpiece No. 1 is controlled to move vertically upward and separate from the rubbing paper, thus completing the rubbing operation on workpiece No. 1;
[0042] The figure on the rubbing paper and points X3 and X4 are recorded as the first rubbing figure.
[0043] Optionally, the obtaining of the second inspection surface of the workpiece No. 1 and performing a secondary coating operation on the workpiece No. 1 is specifically as follows:
[0044] Obtaining the second detection surface of workpiece No. 1;
[0045] On the second inspection surface of the No. 1 workpiece, paint is evenly applied, and the paint completely covers the second inspection surface of the No. 1 workpiece, thereby completing the secondary coating operation on the No. 1 workpiece.
[0046] Optionally, the workpiece No. 1 that has completed the secondary coating operation is recorded as the workpiece No. 2, and a rubbing operation is performed on the workpiece No. 2 to mark the points Y3 and Y4 to obtain a second rubbing pattern, including:
[0047] Re-arranging a rubbing paper for carrying the rubbing pattern, which is recorded as the second rubbing paper;
[0048] Obtain a standard workpiece and select a reference circular surface;
[0049] Make the reference circular surface parallel to the plane where the second rubbing paper is located, and project it vertically onto the second rubbing paper, draw the edge contour line of the projection on the second rubbing paper, and record the edge contour line as the second reference contour diagram;
[0050] Place the second workpiece on top of the second rubbing paper so that the second detection surface of the second workpiece is below the first detection surface;
[0051] Projecting the No. 2 workpiece onto the second rubbing paper, and recording the projection of the No. 2 workpiece on the second rubbing paper as the No. 2 projection;
[0052] Adjust the position of the second workpiece so that the edge contour line of the second projection on the second rubbing paper coincides with the second reference contour map, and use this position as the second rubbing preparation position of the second workpiece;
[0053] Control the No. 2 workpiece to move vertically downward from the No. 2 rubbing preparation position. When it touches the second rubbing paper, stop moving and keep for six seconds. At the same time, vertically project the Y1 point and the Y2 point onto the second rubbing paper and mark them, and record them as the Y3 point and the Y4 point respectively.
[0054] When the contact time between the No. 2 workpiece and the second rubbing paper is six seconds, the No. 2 workpiece is controlled to move vertically upward and separate from the second rubbing paper, thereby completing the rubbing operation on the No. 2 workpiece;
[0055] The figure on the second rubbing paper and points Y3 and Y4 are recorded as the second rubbing figure.
[0056] Optionally, the processing the first image and the second image to form a first image and a second image includes:
[0057] For the first image, take point X3 as the pole, draw a ray pointing to the direction of X4 as the polar axis, take the direction from X3 to X4 as the positive direction, and establish the first polar coordinate system on the first image to form image No. 1;
[0058] For the second image, take point Y3 as the pole, draw a ray pointing to Y4 as the polar axis, take the direction from Y3 to Y4 as the positive direction, and establish a second polar coordinate system on the second image to form image No. 2.
[0059] Optionally, the step of respectively acquiring the normal area and the abnormal area on the first detection surface and the second detection surface of the workpiece to be detected according to the first image and the second image includes:
[0060] For image number one:
[0061] If the area within the reference contour map in the first image is completely covered by the paint, and no paint exists in the area outside the reference contour map, then the area covered by the entire first image is recorded as the normal area of the first detection surface;
[0062] If there are both areas covered by paint and areas not covered by paint in the reference contour map in the first image, the area of the area covered by paint is recorded as the first covered area, and the area of the area not covered by paint is recorded as the first blank area;
[0063] Compare the No. 1 covered area with the No. 1 blank area. If the No. 1 covered area is greater than or equal to the No. 1 blank area, then record the area on the first detection surface corresponding to the No. 1 blank area as the abnormal concave area of the first detection surface.
[0064] If the No. 1 covered area is smaller than the No. 1 blank area, the area on the first detection surface corresponding to the No. 1 covered area is recorded as the abnormal raised area on the first detection surface;
[0065] For image number 2:
[0066] If the area within the second reference contour map in the second image is completely covered by the paint, and no paint exists in the area outside the second reference contour map, then the area covered by the entire second image is recorded as the normal area of the second detection surface;
[0067] If there are both areas covered by paint and areas not covered by paint in the second reference contour map in the second image, the area of the area covered by paint is recorded as the second covered area, and the area of the area not covered by paint is recorded as the second blank area;
[0068] Compare the No. 2 covered area with the No. 2 blank area. If the No. 2 covered area is greater than or equal to the No. 2 blank area, then record the area on the second detection surface corresponding to the No. 2 blank area as the abnormal concave area of the second detection surface.
[0069] If the No. 2 covered area is smaller than the No. 2 blank area, the area on the second detection surface corresponding to the No. 2 covered area is recorded as the abnormal raised area of the second detection surface.
[0070] Optionally, comparing the normal area and the abnormal area of the first detection surface and the second detection surface to classify the workpiece to be detected includes:
[0071] If the first detection surface is a normal area and the second detection surface is a normal area, the workpiece to be detected is marked as a type of workpiece;
[0072] If there are abnormal concave areas or abnormal convex areas on both the first detection surface and the second detection surface, the polar coordinates of the center point of the abnormal concave area and the center point of the abnormal convex area on the first detection surface in the first polar coordinate system are obtained respectively, and are recorded as the concave position of the first detection surface and the convex position of the first detection surface respectively, and the polar coordinates of the center point of the abnormal convex area and the center point of the abnormal concave area on the second detection surface in the second polar coordinate system are obtained respectively, and are recorded as the convex position of the second detection surface and the concave position of the second detection surface respectively;
[0073] If the number of the recessed positions on the first detection surface is the same as the number of the raised positions on the second detection surface, the number of the raised positions on the first detection surface is the same as the number of the recessed positions on the second detection surface, and the recessed positions on the first detection surface correspond to and are the same as the raised positions on the second detection surface, and the raised positions on the first detection surface correspond to and are the same as the recessed positions on the second detection surface, then the workpiece to be tested is marked as a second-class workpiece;
[0074] If the workpiece to be tested is not marked as a Class I workpiece and is not marked as a Class II workpiece, the workpiece to be tested will be rejected;
[0075] The workpieces to be tested marked as Class I workpieces are retained, and the workpieces to be tested marked as Class II workpieces are repaired.
[0076] The present invention has the following beneficial effects:
[0077] 1. By marking four points, X1, X2, Y1, and Y2, on the first and second test surfaces of the workpiece to be tested, subsequent operations can have clear reference points, which plays an important role in the subsequent rubbing and testing process. By marking these points, the error caused by the deviation of the workpiece placement can be effectively reduced, ensuring that the morphological information of the area to be tested can be accurately obtained during the rubbing process, reducing manual alignment errors, and thus ensuring the reliability and accuracy of the test results.
[0078] 2. During the rubbing operation, by obtaining the reference contour of the standard workpiece and adjusting the rubbing projection of workpiece No. 1 or workpiece No. 2 to coincide with the reference contour, the accuracy of the rubbing position can be guaranteed. At the same time, each workpiece has a unified standard during inspection, ensuring consistency and repeatability in the defect detection process.
[0079] 3. By applying uniform coating to the first and second test surfaces of the workpiece to be tested, it can be ensured that the complete information of the test surface is captured. This uniform coating operation can ensure that no matter how complex the surface morphology of the workpiece is, all recessed and raised areas can be completely covered, and accurately reflected in the subsequent rubbing process, so that the surface state of the entire workpiece can be completely captured, improving the effectiveness and accuracy of defect detection, and helping to fully identify defects on the metal surface; at the same time, this detection method of applying paint on the workpiece to be tested and performing rubbing can eliminate the impact of reflection on the surface of the workpiece to be tested in visual inspection.
[0080] 4. When processing the first image and the second image, by establishing a polar coordinate system with a specific point as the pole, the processing of the entire image and the marking of the defect area can be made more convenient. The polar coordinate system is convenient for describing and comparing the defect characteristics at different positions, making the analysis more concise and intuitive. At the same time, the polar coordinate system can better describe the relative position relationship and determine whether the positions are the same, which helps to quickly locate and compare the concave and convex defects on the test surface, thereby improving the analysis efficiency and accuracy.
[0081] 5. By comparing the areas on image No. 1 and image No. 2, judging whether the area in the reference contour map is completely covered, and comparing the covered area with the blank area, the abnormal area on the test surface can be accurately determined, and the normal area and the abnormal area can be distinguished. If the reference contour map is completely covered with paint, it means that the test surface is a normal area. If there are parts covered and uncovered by paint in the reference contour map, it means that there is an abnormal area on the test surface; if the covered area on the test surface is greater than or equal to the blank area, it means that there is an abnormal concave area on the test surface; if the covered area on the test surface is less than the blank area, it means that there is an abnormal convex area on the test surface; this distinction between normal areas and abnormal areas, and further subdividing them into abnormal concave and abnormal convex, helps to accurately identify different types of surface defects, can make the classification of workpieces clearer, and helps to adopt different treatment methods for different defects.
[0082] 6. By comparing the normal area and the abnormal area of the first test surface and the second test surface, if the first test surface is a normal area and the second test surface is a normal area, it means that there are no defects on both surfaces of the workpiece to be tested, and the workpiece to be tested is marked as a type of workpiece; on the basis of comparing the normal area and the abnormal area of the first test surface and the second test surface, the workpiece is classified according to the number and corresponding relationship of the sunken positions and convex positions of the test surface, if the number of sunken positions on the first test surface is the same as the number of convex positions on the second test surface, and the number of convex positions on the first test surface is the same as the number of sunken positions on the second test surface, and the sunken positions on the first test surface correspond to the convex positions on the second test surface one by one and are the same, the convex positions on the first test surface and the concave positions on the second test surface correspond to each other one by one and are the same. The concave positions on the surfaces correspond one to one and are the same, which means that corresponding concave positions and convex positions with the same position appear on the two surfaces of the workpiece to be tested, which means that during the production process of the workpiece to be tested, the workpiece to be tested is affected by external factors, resulting in a concave on one of the two surfaces of the workpiece to be tested, and a convexity appears on the same position on the other surface. By pressing down the convexity, the workpiece to be tested may be repaired, and the workpiece to be tested that may be repaired is divided into two categories of workpieces. This classification method can effectively distinguish different defect types of workpieces; it can not only determine the qualification of the workpiece, but also provide a clear basis for subsequent repair and processing; by distinguishing different defect types, it can help the production process better select the corresponding treatment plan, reduce production costs, and improve the utilization rate of workpieces.
[0083] 7. After classifying the workpieces, different treatment methods such as retention, repair or elimination can be adopted to improve the efficiency of the entire production process; retaining Class I workpieces can save unnecessary processing time; repairing Class II workpieces can reduce waste while ensuring workpiece quality; eliminating workpieces to be tested that do not belong to Class I and Class II workpieces can ensure product quality; this classification process helps to optimize the production process, reduce resource waste, and improve the product qualification rate, thereby improving the efficiency and economic benefits of the entire production line. BRIEF DESCRIPTION OF THE DRAWINGS
[0084] Figure 1 It is a schematic diagram of the basic steps of the present invention. DETAILED DESCRIPTION
[0085] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0086] Embodiment 1, refer to Figure 1 , a metal surface defect detection method, comprising:
[0087] Each round metal piece to be inspected is recorded as a test workpiece;
[0088] The circular metal sheet is a thin sheet of metal material; the thin sheet of metal material comprises two circular surfaces which are opposite and parallel to each other, and the two circular surfaces are of the same size;
[0089] The surfaces of two circular faces of the test workpiece are inspected;
[0090] Obtain two surfaces of each test workpiece that need to be inspected, and record them as a first inspection surface and a second inspection surface of the test workpiece respectively;
[0091] Take any test workpiece and record it as the workpiece to be tested;
[0092] Mark the X1 and X2 points of the first detection surface and the Y1 and Y2 points of the second detection surface on the workpiece to be measured; by marking the four points X1, X2, Y1, and Y2 on the first detection surface and the second detection surface of the workpiece to be measured, subsequent operations can have clear reference points, which plays an important role in the subsequent rubbing and testing process. By marking these points, the error caused by the deviation of the workpiece placement can be effectively reduced, ensuring that the morphological information of the area to be measured can be accurately obtained during the rubbing process, reducing manual alignment errors, and thus ensuring the reliability and accuracy of the test results.
[0093] Acquire a first detection surface of the workpiece to be tested, and perform a coating operation on the workpiece to be tested;
[0094] The workpiece to be tested that has completed one coating operation is recorded as workpiece No. 1;
[0095] Perform a rubbing operation on workpiece No. 1, and mark points X3 and X4 to obtain a first rubbing pattern;
[0096] Acquire the second inspection surface of workpiece No. 1 and perform a secondary coating operation on workpiece No. 1;
[0097] The workpiece No. 1 that has completed the secondary coating operation is recorded as the workpiece No. 2, and a rubbing operation is performed on the workpiece No. 2, and points Y3 and Y4 are marked to obtain a second rubbing pattern;
[0098] Collecting images of the first rubbing pattern and the second rubbing pattern respectively, and recording them as the first image and the second image respectively;
[0099] Processing the first image and the second image to form a first image and a second image;
[0100] According to the first image and the second image, respectively obtain the normal area and the abnormal area on the first detection surface and the second detection surface of the workpiece to be detected;
[0101] The normal area and the abnormal area of the first detection surface and the second detection surface are compared to classify the workpiece to be detected.
[0102] The step of marking the X1 point and the X2 point of the first detection surface and the Y1 point and the Y2 point of the second detection surface on the workpiece to be detected comprises:
[0103] Obtaining an edge contour line of a first detection surface or a second detection surface of a workpiece to be detected, recorded as a surface contour line;
[0104] Adjust the workpiece to be measured so that the plane enclosed by the surface contour is parallel to the horizontal plane;
[0105] Draw two vertical lines perpendicular to the horizontal plane, so that the vertical lines intersect with the edge contours of the first detection surface and the second detection surface of the workpiece to be measured, and record the two vertical lines as the first vertical line and the second vertical line respectively;
[0106] The intersection point of the first vertical line with the first detection surface is recorded as point X1, and the intersection point with the second detection surface is recorded as point Y1;
[0107] The intersection point of the second perpendicular line with the first detection surface is recorded as point X2, and the intersection point of the second perpendicular line with the second detection surface is recorded as point Y2.
[0108] The first detection surface of the workpiece to be tested is obtained, and a coating operation is performed on the workpiece to be tested, specifically:
[0109] Acquire a first detection surface of the workpiece to be detected;
[0110] Paint is evenly applied on the first detection surface of the workpiece to be tested, and the paint completely covers the first detection surface of the workpiece to be tested, thereby completing a coating operation on the workpiece to be tested.
[0111] The step of performing a rubbing operation on workpiece No. 1 and marking points X3 and X4 to obtain a first rubbing pattern includes:
[0112] A rubbing paper for carrying a rubbing pattern is provided;
[0113] Obtain a circular metal sheet with a shape and size that meets production requirements and record it as a standard workpiece;
[0114] Obtain two circular surfaces of a standard workpiece, and arbitrarily select one of the circular surfaces as a reference circular surface;
[0115] Make the reference circular surface parallel to the plane of the rubbing paper and project it vertically onto the rubbing paper, draw the edge contour line of the projection on the rubbing paper, and record the edge contour line as the reference contour map; in the rubbing operation, by obtaining the reference contour map of the standard workpiece and adjusting the rubbing projection of workpiece No. 1 or workpiece No. 2 to coincide with the reference contour, the accuracy of the rubbing position can be guaranteed. At the same time, each workpiece has a unified standard during inspection, ensuring consistency and repeatability in the defect detection process.
[0116] Place workpiece No. 1 on top of the rubbing paper so that the first detection surface of workpiece No. 1 is below the second detection surface;
[0117] Project workpiece No. 1 onto the rubbing paper, and record the projection of workpiece No. 1 on the rubbing paper as projection No. 1;
[0118] Adjust the position of workpiece No. 1 so that the edge contour line of projection No. 1 on the rubbing paper coincides with the reference contour map, and use this position as the No. 1 rubbing preparation position for workpiece No. 1;
[0119] Control workpiece No. 1 to move vertically downward from No. 1 rubbing preparation position. When it touches the rubbing paper, stop moving and keep for six seconds. At the same time, project point X1 and point X2 vertically onto the rubbing paper and mark them, and record them as point X3 and point X4 respectively;
[0120] When the contact time between workpiece No. 1 and the rubbing paper is six seconds, workpiece No. 1 is controlled to move vertically upward and separate from the rubbing paper, thereby completing the rubbing operation on workpiece No. 1; the six seconds can be adjusted accordingly, so that workpiece No. 1 keeps in contact with the rubbing paper for a period of time, so that the pigment on workpiece No. 1 can be rubbed onto the rubbing paper;
[0121] The figure on the rubbing paper and points X3 and X4 are recorded as the first rubbing figure.
[0122] The second inspection surface of the first workpiece is obtained, and a secondary coating operation is performed on the first workpiece, specifically:
[0123] Obtaining the second detection surface of workpiece No. 1;
[0124] Paint is evenly applied to the second inspection surface of workpiece No. 1, and the paint completely covers the second inspection surface of workpiece No. 1, thereby completing the secondary coating operation on workpiece No. 1; by performing a uniform coating operation on the first inspection surface and the second inspection surface of the workpiece to be tested, it can be ensured that the complete information of the surface to be tested is captured, and this uniform coating operation can ensure that no matter how complex the morphology of the workpiece surface is, all recessed and raised areas can be completely covered, and accurately reflected in the subsequent rubbing process, so that the surface state of the entire workpiece can be completely captured, thereby improving the effectiveness and accuracy of defect detection, and facilitating the comprehensive identification of defects on the metal surface; at the same time, this detection method of applying paint on the workpiece to be tested and performing rubbing can eliminate the influence of reflection on the surface of the workpiece to be tested in visual inspection.
[0125] The workpiece No. 1 that has completed the secondary coating operation is recorded as the workpiece No. 2, and a rubbing operation is performed on the workpiece No. 2 to mark the points Y3 and Y4 to obtain a second rubbing pattern, including:
[0126] Re-arranging a rubbing paper for carrying the rubbing pattern, which is recorded as the second rubbing paper;
[0127] Obtain a standard workpiece and select a reference circular surface;
[0128] Make the reference circular surface parallel to the plane where the second rubbing paper is located, and project it vertically onto the second rubbing paper, draw the edge contour line of the projection on the second rubbing paper, and record the edge contour line as the second reference contour diagram;
[0129] Place the second workpiece on top of the second rubbing paper so that the second detection surface of the second workpiece is below the first detection surface;
[0130] Projecting the No. 2 workpiece onto the second rubbing paper, and recording the projection of the No. 2 workpiece on the second rubbing paper as the No. 2 projection;
[0131] Adjust the position of the second workpiece so that the edge contour line of the second projection on the second rubbing paper coincides with the second reference contour map, and use this position as the second rubbing preparation position of the second workpiece;
[0132] Control the No. 2 workpiece to move vertically downward from the No. 2 rubbing preparation position. When it touches the second rubbing paper, stop moving and keep for six seconds. At the same time, vertically project the Y1 point and the Y2 point onto the second rubbing paper and mark them, and record them as the Y3 point and the Y4 point respectively.
[0133] When the contact time between the No. 2 workpiece and the second rubbing paper is six seconds, the No. 2 workpiece is controlled to move vertically upward and separate from the second rubbing paper, thereby completing the rubbing operation on the No. 2 workpiece; the six seconds can be adjusted accordingly, so that the No. 2 workpiece and the second rubbing paper remain in contact for a period of time, so that the pigment on the No. 2 workpiece can be rubbed onto the second rubbing paper;
[0134] The figure on the second rubbing paper and points Y3 and Y4 are recorded as the second rubbing figure.
[0135] The processing of the first image and the second image to form a first image and a second image includes:
[0136] For the first image, take point X3 as the pole, draw a ray pointing to the direction of X4 as the polar axis, take the direction from X3 to X4 as the positive direction, and establish the first polar coordinate system on the first image to form image No. 1;
[0137] For the second image, with point Y3 as the pole, a ray pointing to the direction of Y4 is made as the polar axis, and the direction from Y3 to Y4 is made as the positive direction, a second polar coordinate system is established on the second image to form image No. 2; when processing the first image and the second image, by establishing a polar coordinate system with a specific point as the pole, the processing of the entire image and the marking of the defect area can be made more convenient. The polar coordinate system is convenient for describing and comparing the defect characteristics of different positions, making the analysis more concise and intuitive. At the same time, the polar coordinate system can better describe the relative position relationship and judge whether the positions are the same, which is helpful to quickly locate and compare the concave and convex defects on the inspection surface, thereby improving the analysis efficiency and accuracy.
[0138] The step of respectively acquiring the normal area and the abnormal area on the first detection surface and the second detection surface of the workpiece to be detected according to the first image and the second image comprises:
[0139] For image number one:
[0140] If the area within the reference contour map in the first image is completely covered by the paint, and no paint exists in the area outside the reference contour map, then the area covered by the entire first image is recorded as the normal area of the first detection surface;
[0141] If there are both areas covered by paint and areas not covered by paint in the reference contour map in the first image, the area of the area covered by paint is recorded as the first covered area, and the area of the area not covered by paint is recorded as the first blank area;
[0142] Compare the No. 1 covered area with the No. 1 blank area. If the No. 1 covered area is greater than or equal to the No. 1 blank area, then record the area on the first detection surface corresponding to the No. 1 blank area as the abnormal concave area of the first detection surface.
[0143] If the No. 1 covered area is smaller than the No. 1 blank area, the area on the first detection surface corresponding to the No. 1 covered area is recorded as the abnormal raised area on the first detection surface;
[0144] For image number 2:
[0145] If the area within the second reference contour map in the second image is completely covered by the paint, and no paint exists in the area outside the second reference contour map, then the area covered by the entire second image is recorded as the normal area of the second detection surface;
[0146] If there are both areas covered by paint and areas not covered by paint in the second reference contour map in the second image, the area of the area covered by paint is recorded as the second covered area, and the area of the area not covered by paint is recorded as the second blank area;
[0147] Compare the No. 2 covered area with the No. 2 blank area. If the No. 2 covered area is greater than or equal to the No. 2 blank area, then record the area on the second detection surface corresponding to the No. 2 blank area as the abnormal concave area of the second detection surface.
[0148] If the No. 2 covered area is smaller than the No. 2 blank area, the area on the second test surface corresponding to the No. 2 covered area is recorded as the abnormal raised area of the second test surface; by comparing the areas on the No. 1 image and the No. 2 image, judging whether the area in the reference contour map is completely covered, and comparing the covered area with the blank area, the abnormal area on the test surface can be accurately determined, and the normal area and the abnormal area can be distinguished. If the reference contour map is completely covered with paint, it means that the test surface is a normal area. If there are both parts covered with paint and parts not covered with paint in the reference contour map, it means that there is an abnormal area on the test surface; if the covered area on the test surface is greater than or equal to the blank area, it means that there is an abnormal concave area on the test surface; if the covered area on the test surface is smaller than the blank area, it means that there is an abnormal raised area on the test surface; this distinction between normal areas and abnormal areas, and further subdividing them into abnormal concave and abnormal convex, helps to accurately identify different types of surface defects, can make the classification of workpieces clearer, and helps to adopt different treatment methods for different defects.
[0149] The comparing the normal area and the abnormal area of the first detection surface and the second detection surface to classify the workpiece to be detected includes:
[0150] If the first detection surface is a normal area, and the second detection surface is a normal area, it means that there are no defects on both surfaces of the workpiece to be tested, and the workpiece to be tested is marked as a type of workpiece;
[0151] If there are abnormal concave areas or abnormal convex areas on both the first detection surface and the second detection surface, the polar coordinates of the center point of the abnormal concave area and the center point of the abnormal convex area on the first detection surface in the first polar coordinate system are obtained respectively, and are recorded as the concave position of the first detection surface and the convex position of the first detection surface respectively, and the polar coordinates of the center point of the abnormal convex area and the center point of the abnormal concave area on the second detection surface in the second polar coordinate system are obtained respectively, and are recorded as the convex position of the second detection surface and the concave position of the second detection surface respectively;
[0152] If the number of recessed positions on the first inspection surface is the same as the number of raised positions on the second inspection surface, the number of raised positions on the first inspection surface is the same as the number of recessed positions on the second inspection surface, and the recessed positions on the first inspection surface correspond to and are the same as the raised positions on the second inspection surface, and the raised positions on the first inspection surface correspond to and are the same as the recessed positions on the second inspection surface, then the workpiece to be tested is marked as a second type of workpiece; by comparing the normal area and the abnormal area of the first inspection surface and the second inspection surface, if the first inspection surface is a normal area and the second inspection surface is a normal area, it means that there are no defects on both surfaces of the workpiece to be tested, and the workpiece to be tested is marked as a first type of workpiece; on the basis of comparing the normal area and the abnormal area of the first inspection surface and the second inspection surface, the workpiece is classified according to the number and corresponding relationship of the recessed positions and raised positions of the inspection surfaces; if the number of recessed positions on the first inspection surface is the same as the number of raised positions on the second inspection surface, and the raised positions on the first inspection surface are the same as the recessed positions on the second inspection surface, then the workpiece to be tested is marked as a second type of workpiece; The number of recessed positions on the first and second detection surfaces is the same, and the recessed positions on the first detection surface correspond to and are the same as the raised positions on the second detection surface, and the raised positions on the first detection surface correspond to and are the same as the recessed positions on the second detection surface, indicating that corresponding recessed positions and raised positions with the same position appear on the two surfaces of the workpiece to be tested, indicating that during the production process of the workpiece to be tested, the workpiece to be tested is affected by external factors, resulting in a recess on one surface and a raised position on the other surface at the same position on the two surfaces of the workpiece to be tested. By pressing down the raised position, the workpiece to be tested may be repaired, and the workpiece to be tested that may be repaired is divided into two categories of workpieces. This classification method can effectively distinguish different defect types of workpieces; it can not only determine the qualification of the workpiece, but also provide a clear basis for subsequent repair and processing; by distinguishing different defect types, it can help the production process better select the corresponding treatment plan, reduce production costs, and improve the utilization rate of workpieces.
[0153] If the workpiece to be tested is not marked as a Class I workpiece and is not marked as a Class II workpiece, it means that the workpiece to be tested is neither a qualified workpiece without surface defects nor a workpiece that can be repaired, but a workpiece with surface defects, and the workpiece to be tested will be rejected;
[0154] The workpieces marked as Class I are retained, and the workpieces marked as Class II are repaired. After the workpieces are classified, different treatment methods of retention, repair or elimination are adopted to improve the efficiency of the entire production process. Retaining Class I workpieces saves unnecessary processing time. Repairing Class II workpieces can reduce waste while ensuring workpiece quality. Eliminating workpieces that do not belong to Class I or Class II ensures product quality. This classification process helps optimize the production process, reduce resource waste, and improve the product qualification rate, thereby improving the efficiency and economic benefits of the entire production line.
[0155] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.
[0156] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.
Claims
1. A method for detecting metal surface defects, characterized in that: include: Each round metal piece to be inspected is recorded as a test workpiece; The circular metal sheet is a thin sheet made of metal; The surfaces of two circular faces of the test workpiece are inspected; Obtain two surfaces of each test workpiece that need to be inspected, and record them as a first inspection surface and a second inspection surface of the test workpiece respectively; Take any test workpiece and record it as the workpiece to be tested; Marking points X1 and X2 of the first detection surface and points Y1 and Y2 of the second detection surface on the workpiece to be detected; Acquire a first detection surface of the workpiece to be tested, and perform a coating operation on the workpiece to be tested; The workpiece to be tested that has completed one coating operation is recorded as workpiece No. 1; Perform a rubbing operation on workpiece No. 1, and mark points X3 and X4 to obtain a first rubbing pattern; Acquire the second inspection surface of workpiece No. 1 and perform a secondary coating operation on workpiece No. 1; The workpiece No. 1 that has completed the secondary coating operation is recorded as the workpiece No. 2, and a rubbing operation is performed on the workpiece No. 2, and points Y3 and Y4 are marked to obtain a second rubbing pattern; Collecting images of the first rubbing pattern and the second rubbing pattern respectively, and recording them as the first image and the second image respectively; Processing the first image and the second image to form a first image and a second image; According to the first image and the second image, respectively obtain the normal area and the abnormal area on the first detection surface and the second detection surface of the workpiece to be detected; The normal area and the abnormal area of the first detection surface and the second detection surface are compared to classify the workpiece to be detected.
2. A metal surface defect detection method according to claim 1, characterized in that: The step of marking the X1 point and the X2 point of the first detection surface and the Y1 point and the Y2 point of the second detection surface on the workpiece to be detected comprises: Obtaining an edge contour line of a first detection surface or a second detection surface of a workpiece to be detected, recorded as a surface contour line; Adjust the workpiece to be measured so that the plane enclosed by the surface contour is parallel to the horizontal plane; Draw two vertical lines perpendicular to the horizontal plane, so that the vertical lines intersect with the edge contours of the first detection surface and the second detection surface of the workpiece to be measured, and record the two vertical lines as the first vertical line and the second vertical line respectively; The intersection point of the first vertical line with the first detection surface is recorded as point X1, and the intersection point with the second detection surface is recorded as point Y1; The intersection point of the second perpendicular line with the first detection surface is recorded as point X2, and the intersection point of the second perpendicular line with the second detection surface is recorded as point Y2.
3. A metal surface defect detection method according to claim 1, characterized in that: The first detection surface of the workpiece to be tested is obtained, and a coating operation is performed on the workpiece to be tested, specifically: Acquire a first detection surface of the workpiece to be detected; Paint is evenly applied on the first detection surface of the workpiece to be tested, and the paint completely covers the first detection surface of the workpiece to be tested, thereby completing a coating operation on the workpiece to be tested.
4. A metal surface defect detection method according to claim 1, characterized in that: The step of performing a rubbing operation on workpiece No. 1 and marking points X3 and X4 to obtain a first rubbing pattern includes: A rubbing paper for carrying a rubbing pattern is provided; Obtain a circular metal sheet with a shape and size that meets production requirements and record it as a standard workpiece; Obtain two circular surfaces of a standard workpiece, and arbitrarily select one of the circular surfaces as a reference circular surface; Make the reference circular surface parallel to the plane of the rubbing paper, and project it vertically onto the rubbing paper, draw the edge contour line of the projection on the rubbing paper, and record the edge contour line as the reference contour diagram; Place workpiece No. 1 on top of the rubbing paper so that the first detection surface of workpiece No. 1 is below the second detection surface; Project workpiece No. 1 onto the rubbing paper, and record the projection of workpiece No. 1 on the rubbing paper as projection No. 1; Adjust the position of workpiece No. 1 so that the edge contour line of projection No. 1 on the rubbing paper coincides with the reference contour map, and use this position as the No. 1 rubbing preparation position for workpiece No. 1; Control workpiece No. 1 to move vertically downward from No. 1 rubbing preparation position. When it touches the rubbing paper, stop moving and keep for six seconds. At the same time, project point X1 and point X2 vertically onto the rubbing paper and mark them, and record them as point X3 and point X4 respectively; When the contact time between workpiece No. 1 and the rubbing paper is six seconds, workpiece No. 1 is controlled to move vertically upward and separate from the rubbing paper, thus completing the rubbing operation on workpiece No. 1; The figure on the rubbing paper and points X3 and X4 are recorded as the first rubbing figure.
5. A metal surface defect detection method according to claim 1, characterized in that: The second inspection surface of the first workpiece is obtained, and a secondary coating operation is performed on the first workpiece, specifically: Obtaining the second detection surface of workpiece No. 1; On the second inspection surface of the No. 1 workpiece, paint is evenly applied, and the paint completely covers the second inspection surface of the No. 1 workpiece, thereby completing the secondary coating operation on the No. 1 workpiece.
6. A metal surface defect detection method according to claim 4, characterized in that: The workpiece No. 1 that has completed the secondary coating operation is recorded as the workpiece No. 2, and a rubbing operation is performed on the workpiece No. 2 to mark the points Y3 and Y4 to obtain a second rubbing pattern, including: Re-arranging a rubbing paper for carrying the rubbing pattern, which is recorded as the second rubbing paper; Obtain a standard workpiece and select a reference circular surface; Make the reference circular surface parallel to the plane where the second rubbing paper is located, and project it vertically onto the second rubbing paper, draw the edge contour line of the projection on the second rubbing paper, and record the edge contour line as the second reference contour diagram; Place the second workpiece on top of the second rubbing paper so that the second detection surface of the second workpiece is below the first detection surface; Projecting the No. 2 workpiece onto the second rubbing paper, and recording the projection of the No. 2 workpiece on the second rubbing paper as the No. 2 projection; Adjust the position of the second workpiece so that the edge contour line of the second projection on the second rubbing paper coincides with the second reference contour map, and use this position as the second rubbing preparation position of the second workpiece; Control the No. 2 workpiece to move vertically downward from the No. 2 rubbing preparation position. When it touches the second rubbing paper, stop moving and keep for six seconds. At the same time, vertically project the Y1 point and the Y2 point onto the second rubbing paper and mark them, and record them as the Y3 point and the Y4 point respectively. When the contact time between the No. 2 workpiece and the second rubbing paper is six seconds, the No. 2 workpiece is controlled to move vertically upward and separate from the second rubbing paper, thereby completing the rubbing operation on the No. 2 workpiece; The figure on the second rubbing paper and points Y3 and Y4 are recorded as the second rubbing figure.
7. A metal surface defect detection method according to claim 1, characterized in that: The processing of the first image and the second image to form a first image and a second image includes: For the first image, take point X3 as the pole, draw a ray pointing to the direction of X4 as the polar axis, take the direction from X3 to X4 as the positive direction, and establish the first polar coordinate system on the first image to form image No. 1; For the second image, take point Y3 as the pole, draw a ray pointing to Y4 as the polar axis, take the direction from Y3 to Y4 as the positive direction, and establish a second polar coordinate system on the second image to form image No.
2.
8. A metal surface defect detection method according to claim 1, characterized in that: The step of respectively acquiring the normal area and the abnormal area on the first detection surface and the second detection surface of the workpiece to be detected according to the first image and the second image comprises: For image number one: If the area within the reference contour map in the first image is completely covered by the paint, and no paint exists in the area outside the reference contour map, then the area covered by the entire first image is recorded as the normal area of the first detection surface; If there are both areas covered by paint and areas not covered by paint in the reference contour map in the first image, the area of the area covered by paint is recorded as the first covered area, and the area of the area not covered by paint is recorded as the first blank area; Compare the No. 1 covered area with the No. 1 blank area. If the No. 1 covered area is greater than or equal to the No. 1 blank area, then record the area on the first detection surface corresponding to the No. 1 blank area as the abnormal concave area of the first detection surface. If the No. 1 covered area is smaller than the No. 1 blank area, the area on the first detection surface corresponding to the No. 1 covered area is recorded as the abnormal raised area on the first detection surface; For image number 2: If the area within the second reference contour map in the second image is completely covered by the paint, and no paint exists in the area outside the second reference contour map, then the area covered by the entire second image is recorded as the normal area of the second detection surface; If there are both areas covered by paint and areas not covered by paint in the second reference contour map in the second image, the area of the area covered by paint is recorded as the second covered area, and the area of the area not covered by paint is recorded as the second blank area; Compare the No. 2 covered area with the No. 2 blank area. If the No. 2 covered area is greater than or equal to the No. 2 blank area, then record the area on the second detection surface corresponding to the No. 2 blank area as the abnormal concave area of the second detection surface. If the No. 2 covered area is smaller than the No. 2 blank area, the area on the second detection surface corresponding to the No. 2 covered area is recorded as the abnormal raised area of the second detection surface.
9. A metal surface defect detection method according to claim 8, characterized in that: The comparing the normal area and the abnormal area of the first detection surface and the second detection surface to classify the workpiece to be detected includes: If the first detection surface is a normal area and the second detection surface is a normal area, the workpiece to be detected is marked as a type of workpiece; If there are abnormal concave areas or abnormal convex areas on both the first detection surface and the second detection surface, the polar coordinates of the center point of the abnormal concave area and the center point of the abnormal convex area on the first detection surface in the first polar coordinate system are obtained respectively, and are recorded as the concave position of the first detection surface and the convex position of the first detection surface respectively, and the polar coordinates of the center point of the abnormal convex area and the center point of the abnormal concave area on the second detection surface in the second polar coordinate system are obtained respectively, and are recorded as the convex position of the second detection surface and the concave position of the second detection surface respectively; If the number of the recessed positions on the first detection surface is the same as the number of the raised positions on the second detection surface, the number of the raised positions on the first detection surface is the same as the number of the recessed positions on the second detection surface, and the recessed positions on the first detection surface correspond to and are the same as the raised positions on the second detection surface, and the raised positions on the first detection surface correspond to and are the same as the recessed positions on the second detection surface, then the workpiece to be tested is marked as a second-class workpiece; If the workpiece to be tested is not marked as a Class I workpiece and is not marked as a Class II workpiece, the workpiece to be tested will be rejected; The workpieces to be tested marked as Class I workpieces are retained, and the workpieces to be tested marked as Class II workpieces are repaired.
Citation Information
Patent Citations
Non-destructive metal surface defect microscopic detection method
CN106248687A
Defect type identification method, identification device, control equipment and storage medium
CN117475205A
Process for detecting area rate of pre-cast bulge on outer circle of cylinder sleeve
CN117928435A
Surface defect detection device for double-layer composite quartz crucible
CN118688118A
Precision casting part surface defect automatic detection system
CN118914211A
Cited By
Method for detecting metal hardness
CN119666627A
Bearing surface defect detection method, system and related device
CN121577637A
