Methods and computer equipment for weld quality inspection of thick-walled welded workpieces

Abstract

This invention relates to a method and equipment for inspecting weld quality in thick-walled welded workpieces. The weld quality inspection method includes the following steps: image processing of a metallographic image of the weld cross-section to obtain the outer contours of the inner and outer welds; drawing inner and outer weld curves based on first and second contour information; obtaining a first center line, a first horizontal line, and a second horizontal line based on the first contour information; obtaining a second center line, a third horizontal line, and a fourth horizontal line based on the second contour information; calculating center deviation, misalignment, the residual height of the inner weld, and the residual height of the outer weld based on the first center line, second center line, first horizontal line, second horizontal line, third horizontal line, and fourth horizontal line; and determining whether the weld quality of the thick-walled welded workpiece is qualified based on the center deviation, misalignment, residual height of the inner weld, and residual height of the outer weld. The above weld quality inspection method can improve the inspection efficiency and accuracy of weld quality inspection.

Description

Technical Field

[0001] This invention relates to the field of welding manufacturing technology, and in particular to a method and computer equipment for inspecting weld quality in thick-walled welded workpieces. Background Technology

[0002] In the field of metal welding, for welding thick-walled workpieces, considering the thickness of the workpiece itself and to ensure the quality of the welded workpiece, two welding bevels are usually machined on the inner and outer sides of the joint, using an inner and outer welding method to improve the weld quality. However, such welding can also lead to problems such as misalignment or displacement of the inner and outer weld seams, which directly affect the quality of the workpiece. Currently, the quality inspection of weld seams after welding generally uses manual observation and judgment methods. The most common weld seam inspection method is to manually obtain the cross-sectional shape of the weld seam and then judge the weld quality by manually drawing lines. However, this manual inspection method has the problems of low inspection accuracy and efficiency, and it also depends heavily on the skill level of the inspector. Summary of the Invention

[0003] Therefore, it is necessary to address the problem of low detection accuracy in traditional weld seam inspection methods for thick-walled workpieces by providing a weld quality inspection method and computer equipment for thick-walled workpieces that can improve weld seam inspection accuracy.

[0004] A method for inspecting weld quality in thick-walled welded workpieces, comprising the following steps:

[0005] Obtain metallographic images of the weld cross-section of thick-walled welded workpieces;

[0006] Image processing is performed on the metallographic images of the weld cross-section to obtain the outer contours of the inner weld and the outer weld.

[0007] The first contour information is obtained based on the outer contour of the inner weld, the second contour information is obtained based on the outer contour of the outer weld, and the inner weld curve and the outer weld curve are drawn based on the first contour information and the second contour information.

[0008] The inner weld curve and the outer weld curve are stored in a first mask and a second mask of the same size, respectively. A logical AND operation is performed on the image pixels in the first mask and the second mask to obtain the coordinates of the first intersection point and the second intersection point between the inner weld curve and the outer weld curve.

[0009] Based on the first contour information, obtain the coordinates of the highest extreme point, the lowest extreme point, the leftmost extreme point, and the rightmost extreme point of the inner weld curve, and draw the first center line, the first horizontal line, and the second horizontal line based on the coordinates of the first intersection point and the coordinates of the leftmost and rightmost extreme points of the inner weld curve.

[0010] Based on the second contour information, obtain the coordinates of the highest extreme point, the lowest extreme point, the rightmost extreme point, and the rightmost extreme point of the outer weld curve. Then, based on the coordinates of the second intersection point and the coordinates of the leftmost and rightmost extreme points of the outer weld curve, draw the second center line, the third horizontal line, and the fourth horizontal line.

[0011] The center deviation value is calculated based on the first center line and the second center line; the misalignment value is calculated based on the first horizontal line and the third horizontal line; the excess height value of the inner weld is calculated based on the inner weld curve and the second horizontal line; and the excess height value of the outer weld is calculated based on the outer weld curve and the fourth horizontal line.

[0012] The quality of the weld in a thick-walled welded workpiece is determined based on the center deviation value, misalignment value, inner weld reinforcement value, and outer weld reinforcement value.

[0013] In one embodiment, the step of image processing the metallographic image of the weld cross-section to obtain the outer contour of the inner weld and the outer contour of the outer weld includes the following steps:

[0014] Preprocess the metallographic images of the weld section to obtain a smooth image;

[0015] The watershed algorithm is used to segment and color fill the smooth image to obtain a segmented and filled image;

[0016] The target region of the weld fill image is extracted using the HSV color space conversion method to obtain the inner weld region and the outer weld region.

[0017] The contour curves of the inner weld region and the outer weld region are completed and interference is eliminated by morphological opening and closing operations. The outer contours of the inner weld and the outer weld are obtained by Canny edge detection.

[0018] In one embodiment, the step of preprocessing the metallographic image of the weld section to obtain a smooth image is as follows: the metallographic image of the weld section is preprocessed using Gaussian filtering to obtain a filtered smooth image.

[0019] In one embodiment, the step of extracting the target region of the weld fill image using an HSV color space conversion method to obtain the inner weld region and the outer weld region includes:

[0020] The HSV color space conversion algorithm is used to convert the color of the weld fill image;

[0021] The target area is extracted based on the H, S, and V values ​​of the color within the inner weld area after color conversion, to obtain the inner weld area.

[0022] The target area is extracted based on the H, S, and V values ​​of the color within the outer weld seam area after color conversion, thus obtaining the outer weld seam area.

[0023] In one embodiment, the steps of obtaining first contour information based on the outer contour of the inner weld, obtaining second contour information based on the outer contour of the outer weld, and drawing the inner weld curve and the outer weld curve based on the first contour information and the second contour information include:

[0024] The findContours function is used to detect the outer contours of the inner weld and the outer weld respectively to obtain the first contour information and the second contour information.

[0025] The drawContours function is used to draw the inner weld curve and the outer weld curve based on the first contour information and the second contour information, respectively.

[0026] In one embodiment, after the step of using the findContours function to detect the outer contour of the inner weld and the outer contour of the inner weld to obtain first contour information and second contour information, the method further includes:

[0027] The first contour information and the second contour information are stored in a preset first storage unit and a preset second storage unit, respectively.

[0028] In one embodiment, the steps of calculating the reinforcement value of the inner weld based on the inner weld curve and the second horizontal line, and calculating the reinforcement value of the outer weld based on the outer weld curve and the fourth horizontal line, include:

[0029] According to the formula Calculate the height value of the inner weld curve; where, This represents the height value of the inner weld curve. The coordinates of the highest extreme point of the internal weld curve are given. These are the coordinates of the lowest extreme point of the internal weld curve;

[0030] According to the formula Calculate the height value of the external weld curve; where, This represents the height value of the outer weld curve. The coordinates of the highest extreme point of the external weld curve. These are the coordinates of the lowest extreme point of the external weld curve;

[0031] like Greater than Then the coordinates of the highest extreme point of the inner weld curve The inner weld reinforcement value is obtained by subtracting from the second horizontal line, and the coordinates of the lowest extreme point of the outer weld curve are obtained. The excess height of the outer weld is obtained by subtracting from the fourth horizontal line.

[0032] like Less than Then the coordinates of the lowest extreme point of the inner weld curve. The inner weld reinforcement value is obtained by subtracting from the second horizontal line, and the coordinates of the highest extreme point of the outer weld curve are obtained. The excess height of the outer weld is obtained by subtracting from the fourth horizontal line.

[0033] In one embodiment, the weld inspection items for thick-walled welded workpieces include a center deviation value less than or equal to a first preset value, a misalignment value less than or equal to a second preset value, an inner weld reinforcement value within a first preset range, and an outer weld reinforcement value within a second preset range.

[0034] The steps for determining whether the weld quality of a thick-walled welded workpiece is qualified based on the center deviation value, misalignment value, inner weld reinforcement value, and outer weld reinforcement value include: if all of the above welding inspection items are met, the weld of the thick-walled welded workpiece is qualified; if any one of the above welding inspection items is not met, the weld of the thick-walled welded workpiece is unqualified.

[0035] In one embodiment, the first preset value is 3 mm; the second preset value is 1.6 mm; the first preset range is 0 mm to 3.5 mm; and the second preset range is 0 mm to 3.0 mm.

[0036] A computer device includes a memory and a processor, the memory storing a computer program, characterized in that the computer program, when executed by the processor, implements the steps of the weld quality inspection method as described above.

[0037] The aforementioned method and computer equipment for inspecting weld quality in thick-walled welded workpieces, by executing the steps described above, can extract the outer contours of the inner and outer welds from the metallographic image of the weld cross-section. Data processing is then performed on these outer contours to obtain complete and less-interfered inner and outer weld curves, which improves the accuracy of weld quality inspection results. Furthermore, data calculations are performed on the coordinate pixels of the inner and outer weld curves to identify the intersection coordinates between the two curves and the coordinates of the four extreme points of each curve. Based on these intersection and extreme point coordinates, quality evaluation parameters such as center deviation, misalignment, inner weld reinforcement height, and outer weld reinforcement height are calculated by drawing auxiliary lines, further improving the accuracy of the inspection results. Therefore, the use of the aforementioned method for inspecting weld quality in thick-walled welded workpieces can improve the efficiency and accuracy of weld inspection. Attached Figure Description

[0038] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiments below. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0039] Figure 1 This is an application environment diagram of a weld quality inspection method for thick-walled welded workpieces provided in an embodiment of the present invention.

[0040] Figure 2 This is a schematic flowchart of a weld quality inspection method for thick-walled welded workpieces according to an embodiment of the present invention.

[0041] Figure 3 This is a drawing of the weld feature line in one embodiment of the present invention.

[0042] Figure 4 for Figure 2 The flowchart shown is a schematic diagram of step S200 in the weld quality inspection method for thick-walled welded workpieces.

[0043] Figure 5 for Figure 3 A flowchart of step S230 in step S200 is shown.

[0044] Figure 6 for Figure 2 The flowchart shown is a schematic diagram of step S300 in the weld quality inspection method for thick-walled welded workpieces. Detailed Implementation

[0045] The following are the annotations in the attached figures: 10, inner weld curve; 20, outer weld curve; 30, first center line; 40, second center line; 50, first horizontal line; 60, second horizontal line; 70, third horizontal line; 80, fourth horizontal line; 91, inner weld area; 92, outer weld area; 01, coordinates of the first intersection point; 02, coordinates of the second intersection point. Detailed Implementation

[0047] To facilitate understanding of the present invention, a more complete description will be given below with reference to the accompanying drawings. Preferred embodiments of the invention are shown in the drawings. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a thorough and complete understanding of the disclosure of the invention.

[0048] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0049] When describing positional relationships, unless otherwise specified, when an element is referred to as being "on" another element, it may be directly on the other element or there may be intermediate elements. It is also understood that when an element is referred to as being "between" two elements, it may be the only one between the two elements, or there may be one or more intermediate elements.

[0050] When using the terms “including,” “having,” and “comprising” as described herein, another component may be added unless explicitly qualifying terms such as “only,” “consisting of,” etc. are used. Unless otherwise stated, singular terms may include plural forms and should not be construed as having a quantity of one.

[0051] The weld quality inspection method for thick-walled welded workpieces provided in this application can be applied to, for example... Figure 1 The application environment shown. Figure 1 This diagram illustrates an application environment for a weld quality inspection method for thick-walled welded workpieces, as shown in one embodiment. The environment includes a server 104 and a terminal 102. The server 104 inspects the weld quality and sends the results to the terminal 102. The terminal 102 receives the inspection results from the server 104 and returns feedback information. The server 104 can communicate with the terminal 102 via a network. The server 104 can be a standalone server or a server cluster consisting of multiple servers. The terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, and tablets; this embodiment does not impose such limitations.

[0052] In current technologies, the visual inspection of thick-walled welded workpieces is often performed manually, but this method is both inefficient and inaccurate. Therefore, the current methods still suffer from low efficiency and accuracy in weld inspection.

[0053] Based on this, this application provides a method and equipment for inspecting the weld quality of thick-walled workpieces, which can automatically inspect the weld quality of thick-walled welded workpieces, thereby improving the efficiency and accuracy of weld quality inspection. Figure 2 This is a schematic flowchart of a weld quality inspection method for thick-walled welded workpieces provided in an embodiment of this application.

[0054] Please see Figure 2 and Figure 3 The preferred embodiment of the present invention provides a weld quality inspection method for thick-walled welded workpieces, used to inspect the weld appearance quality of thick-walled welded workpieces. The thick-walled welded workpieces are pipe or plate welded parts with high welding requirements and requiring double-sided welding. The weld quality inspection method for thick-walled welded workpieces includes steps S100 to S800.

[0055] Step S100: Obtain metallographic images of the weld cross-section of the thick-walled welded workpiece.

[0056] The metallographic images of the weld cross-section can be existing images or newly acquired images.

[0057] Step S200: Perform image processing on the metallographic image of the weld section to obtain the outer contour of the inner weld and the outer contour of the outer weld.

[0058] Specifically, by inputting the metallographic image of the weld section into the image processing software, the metallographic image of the weld section can be accurately processed to quickly and accurately obtain the outer contour of the inner weld and the outer contour of the outer weld in the metallographic image of the weld section.

[0059] Step S300: Obtain first contour information based on the outer contour of the inner weld, obtain second contour information based on the outer contour of the outer weld, and draw the inner weld curve 10 and the outer weld curve 20 based on the first contour information and the second contour information. Specifically, the first contour information includes the pixel coordinates, contour feature parameters, and contour number of each pixel of the inner weld contour; the second contour information includes the pixel coordinates, contour feature parameters, and contour number of the outer weld contour.

[0060] In step S400, the inner weld curve 10 and the outer weld curve 20 are stored in a first mask and a second mask of the same size, respectively, and a logical AND operation is performed on the image pixels in the first mask and the second mask to obtain the first intersection point coordinates O1 and the second intersection point coordinates O2 between the inner weld curve 10 and the outer weld curve 20.

[0061] Step S500: Obtain the coordinates of the highest extreme point, lowest extreme point, leftmost extreme point, and rightmost extreme point of the inner weld curve 10 based on the first contour information, and draw the first center line 30, the first horizontal line 50, and the second horizontal line 60 based on the first intersection point coordinates 01 and the coordinates of the leftmost and rightmost extreme points of the inner weld curve 10.

[0062] Specifically, the first centerline 30 is a vertical straight line, and the leftmost and rightmost extreme points of the inner weld curve 10 are equidistant from the first centerline 30 or its extension; the first horizontal line 50 is a horizontal line passing through the first intersection point; the second horizontal line 60 is the line connecting the leftmost and rightmost extreme points of the inner weld curve 10. Therefore, the first centerline 30 and the first horizontal line 50 are perpendicular to each other. In the weld of a welded workpiece, the leftmost and rightmost extreme points usually appear on the surface of the welded workpiece, so the second horizontal line 60 is the horizontal line connecting the inner weld at the inner surface of the thick-walled welded workpiece.

[0063] Step S600: Obtain the coordinates of the highest extreme point, lowest extreme point, leftmost extreme point, and rightmost extreme point of the outer weld curve 20 based on the second contour information, and draw the second center line 40, the third horizontal line 70, and the fourth horizontal line 80 based on the coordinates of the second intersection point 02 and the coordinates of the leftmost and rightmost extreme points of the outer weld curve 20.

[0064] The second centerline 40 is a vertical line, and the distances from the leftmost and rightmost extreme points of the outer weld curve 20 to the second centerline 40 or its extension are the same. The third horizontal line 70 is a horizontal line passing through the second intersection point. The fourth horizontal line 80 is a horizontal line connecting the leftmost and rightmost extreme points of the outer weld curve 20. Therefore, the second centerline 40 and the third horizontal line 70 are perpendicular to each other. The fourth horizontal line 80 is a horizontal line connecting the outer weld at the outer surface of the thick-walled welded workpiece.

[0065] During the execution of steps S500 and S600, the inner and outer directions of the weld are defined as the height direction, and the width direction of the weld is defined as the left and right direction. In the height direction, the height of the highest extreme point of the inner weld curve is higher than the height of the lowest extreme point of the inner weld curve, and the height of the highest extreme point of the outer weld curve is higher than the height of the lowest extreme point of the outer weld curve. In the left and right direction, the distance between the leftmost and rightmost extreme points of the inner weld curve is the maximum width of the inner weld curve, and the distance between the leftmost and rightmost extreme points of the outer weld curve is the maximum width of the outer weld curve.

[0066] The first center line 30, the second center line 40, the first horizontal line 50, the second horizontal line 60, the third horizontal line 70, and the fourth horizontal line 80 are auxiliary lines drawn in the image after data processing to help obtain subsequent quality evaluation parameters.

[0067] Step S700, calculate the center deviation value according to the first center line 30 and the second center line 40, calculate the offset value according to the first horizontal line 50 and the third horizontal line 70, calculate the reinforcement value of the internal weld according to the internal weld curve 10 and the second horizontal line 60, and calculate the reinforcement value of the external weld according to the external weld curve 20 and the fourth horizontal line 80. Among them, the center deviation value, the offset value, the reinforcement value of the internal weld, and the reinforcement value of the external weld are weld quality evaluation parameters.

[0068] Step S800, determine whether the weld quality of the thick-walled welded workpiece is qualified according to the center deviation value, the offset value, the reinforcement value of the internal weld, and the reinforcement value of the external weld.

[0069] Specifically, the weld quality inspection items of the thick-walled welded workpiece include that the center deviation value is less than or equal to the first preset value, the offset value is less than or equal to the second preset value, the reinforcement value of the internal weld is within the first preset range, and the reinforcement value of the external weld is within the second preset range. The steps of Step S800 include: if the center deviation value is less than or equal to the first preset value, and the offset value is less than or equal to the second preset value, and at the same time the reinforcement value of the internal weld is within the first preset range, and at the same time the reinforcement value of the external weld is within the second preset range, it means that the weld quality is qualified; if the center deviation value is greater than the first preset value, and / or the offset value is greater than the second preset value, and / or the reinforcement value of the internal weld exceeds the first preset range, and / or the reinforcement value of the external weld exceeds the second preset range, it means that the weld quality is unqualified.

[0070] More specifically, the first preset value is 3 mm; the second preset value is 1.6 mm; the first preset range is from 0 mm to 3.5 mm; the second preset range is from 0 mm to 3.0 mm. Among them, if the center deviation value is greater than 3 mm, it means that the misalignment of the internal and external welds is large, which can reduce the welding firmness; if the offset value is greater than 1.6 mm, the distance between the internal and external welds in the wall thickness direction of the thick-walled workpiece is large, and there is a high probability that incomplete penetration will occur; if the reinforcement values of the internal weld and the external weld are less than 0, there is a high probability that full welding cannot be achieved. If the reinforcement value of the internal weld is greater than 3.5 mm and the reinforcement value of the external weld is greater than 3.0 mm, it means that the reinforcement of the internal weld and the internal weld is too high, which may cause stress concentration in the weld bead, and excessive stress may cause phenomena such as weld bead tearing and easy corrosion. Therefore, only when all the above inspection items are qualified can the weld quality of the thick-walled welded workpiece be qualified.

[0071] By executing steps S100 to S800, the weld seams of thick-walled welded workpieces can be automatically inspected. Compared to the traditional manual line drawing inspection method, the above-mentioned weld seam inspection method for thick-walled welded workpieces has higher inspection efficiency. Furthermore, by executing steps S200 and S300, complete and less-interfered inner weld seam curves 10 and 20 can be obtained, contributing to improved accuracy of weld quality inspection results. Further, by executing steps S400 to S600, accurate first center line 30, second center line 40, first horizontal line 50, second horizontal line 60, third horizontal line 70, and fourth horizontal line 80 can be automatically drawn as auxiliary lines for obtaining weld quality evaluation parameters. Then, by executing steps S700 and S800, accurate weld quality inspection results for thick-walled welded workpieces can be obtained. Therefore, the use of the above-mentioned weld quality inspection method for thick-walled welded workpieces can improve the inspection efficiency and accuracy of weld seam inspection results for thick-walled welded workpieces.

[0072] Please refer to the following: Figure 4 In some implementations, step S200 includes steps S210 to S240.

[0073] Step S210: Perform preprocessing on the metallographic image of the weld section to obtain a smooth image.

[0074] Specifically, step S210 involves performing Gaussian filtering on the metallographic image of the weld cross-section to preprocess the image and obtain a smoothed image. Thus, by performing Gaussian filtering on the metallographic image of the weld cross-section, a smooth image with higher image quality is obtained.

[0075] Step S220: Use the watershed algorithm to segment and color fill the smooth image to obtain a segmented and filled image.

[0076] Specifically, the target area is selected using the mouse, and the watershed algorithm is used to fill and segment the feature region and background. A smoothed image is used as the input image, and gradient calculation is performed on the input image to obtain a segmented and filled image, which is beneficial for the subsequent extraction of the outer contours of the inner and outer welds. Different feature regions in the segmented and filled image are filled with different colors.

[0077] Step S230: The target region of the weld fill image is extracted using the HSV color space conversion method to obtain the inner weld region 91 and the outer weld region 92. Please refer to [link / reference needed]. Figure 5 Specifically, step S230 includes steps S231 to S233:

[0078] Step S231: Use the HSV color space conversion algorithm to perform color conversion on the weld fill image.

[0079] Step S232: Extract the target area based on the H, S, and V values ​​of the color in the inner weld area 91 after color conversion to obtain the inner weld area 91.

[0080] Step S233: Extract the target area based on the H, S, and V values ​​of the color in the outer weld area 92 after color conversion, so as to obtain the outer weld area 92.

[0081] Therefore, by executing steps S231 to S233, the inner weld area 91 and the outer weld area 92 can be automatically extracted with high accuracy.

[0082] Step S240: The contour curves of the inner weld region 91 and the outer weld region 92 are completed and interference is eliminated by morphological opening and closing operations, and the outer contours of the inner weld and the outer weld are obtained by Canny edge detection.

[0083] Therefore, in step S240, the contour curves of the inner weld region 91 and the outer weld region 92 are completed by morphological opening and closing operations, respectively, and the interference of smaller objects is eliminated. Then, Canny edge detection is used to obtain a more complete inner weld outer contour and an outer weld outer contour with less interference.

[0084] Therefore, by performing steps S210 to S240 to calculate and process the metallographic image of the weld section, a clearer, more complete, and less interfered inner weld outer contour can be automatically obtained, which helps to further improve the accuracy of weld quality inspection results for thick-walled welded workpieces.

[0085] Please refer to the following: Figure 6 In some embodiments, step S300 includes steps S310 and S320.

[0086] Step S310: Use the findContours function to detect the outer contour of the inner weld and the outer contour of the inner weld respectively, so as to obtain the first contour information and the second contour information.

[0087] In step S320, the drawContours function is used to draw the inner weld curve 10 and the outer weld curve 20 based on the first contour information and the second contour information, respectively. Specifically, during the execution of step S320, the drawing of non-contour curves is reduced by using contour length conditions to further improve the accuracy of the inner weld curve 10 and the outer weld curve 20.

[0088] The drawContours function can automatically draw the inner weld curve 10 and the outer weld curve 20, which is beneficial to further improve the detection efficiency and accuracy of weld quality inspection.

[0089] Specifically, between steps S310 and S320, the method further includes storing the first contour information and the second contour information in preset first storage units and preset second storage units, respectively.

[0090] In some embodiments, step S700 includes the following steps:

[0091] According to the formula Calculate the height value of the inner weld curve 10; where, This represents the height value of the inner weld curve 10. The coordinates of the highest extreme point of the inner weld curve 10 are given. The coordinates of the lowest extreme point of the inner weld curve 10 are given.

[0092] According to the formula Calculate the height value of curve 20 of the outer weld; where, This refers to the height value of the outer weld curve 20. The coordinates of the highest extreme point of the external weld curve 20 are given. The coordinates of the lowest extreme point of the external weld curve 20 are given.

[0093] like Greater than Then the coordinates of the highest extreme point of the inner weld curve 10 are... The inner weld reinforcement value is obtained by subtracting from the second horizontal line 60, and the coordinates of the lowest extreme point of the outer weld curve 20 are obtained. The excess height of the outer weld is obtained by subtracting from the fourth horizontal line 80.

[0094] like Less than Then the coordinates of the lowest extreme point of the inner weld curve 10 are... The inner weld reinforcement value is obtained by subtracting from the second horizontal line 60, and the coordinates of the highest extreme point of the outer weld curve 20 are obtained. The excess height of the outer weld is obtained by subtracting from the fourth horizontal line 80.

[0095] Therefore, through comparison and The size of the inner weld curve 10 and the outer weld curve 20 is used to determine their relative heights. Based on the different positional relationships between the inner weld curve 10 and the outer weld curve 20, different methods for calculating the residual height value are selected to obtain accurate residual height values ​​for the inner and outer welds.

[0096] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0097] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this invention patent should be determined by the appended claims.

Claims

1. A method for inspecting weld quality in thick-walled welded workpieces, characterized in that, Including the following steps: Obtain metallographic images of the weld cross-section of thick-walled welded workpieces; Image processing is performed on the metallographic images of the weld cross-section to obtain the outer contours of the inner weld and the outer weld. The first contour information is obtained based on the outer contour of the inner weld, the second contour information is obtained based on the outer contour of the outer weld, and the inner weld curve and the outer weld curve are drawn based on the first contour information and the second contour information. The inner weld curve and the outer weld curve are stored in a first mask and a second mask of the same size, respectively. A logical AND operation is performed on the image pixels in the first mask and the second mask to obtain the coordinates of the first intersection point and the second intersection point between the inner weld curve and the outer weld curve. Based on the first contour information, obtain the coordinates of the highest, lowest, leftmost, and rightmost extreme points of the inner weld curve. Then, based on the coordinates of the first intersection point and the leftmost and rightmost extreme points of the inner weld curve, draw a first center line, a first horizontal line, and a second horizontal line. The first center line is a vertical line, and the distances from the leftmost and rightmost extreme points of the inner weld curve to the first center line or its extension are the same. The first horizontal line is a horizontal line passing through the first intersection point. The second horizontal line is the line connecting the leftmost and rightmost extreme points of the inner weld curve. The first center line and the first horizontal line are perpendicular to each other. The second horizontal line is the horizontal line connecting the inner weld at the inner surface of the thick-walled welded workpiece. Based on the second contour information, obtain the coordinates of the highest, lowest, leftmost, and rightmost extreme points of the outer weld curve. Then, based on the coordinates of the second intersection point and the leftmost and rightmost extreme points of the outer weld curve, draw a second center line, a third horizontal line, and a fourth horizontal line. The second center line is a vertical line, and the distances from the leftmost and rightmost extreme points of the outer weld curve to the second center line or its extension are the same. The third horizontal line is a horizontal line passing through the second intersection point. The fourth horizontal line is a horizontal line connecting the leftmost and rightmost extreme points of the outer weld curve. The second center line and the third horizontal line are perpendicular to each other. The fourth horizontal line is a horizontal line representing the outer weld at the outer surface of the thick-walled welded workpiece. The center deviation value is calculated based on the first center line and the second center line; the misalignment value is calculated based on the first horizontal line and the third horizontal line; the excess height value of the inner weld is calculated based on the inner weld curve and the second horizontal line; and the excess height value of the outer weld is calculated based on the outer weld curve and the fourth horizontal line. The quality of the weld in a thick-walled welded workpiece is determined based on the center deviation value, misalignment value, inner weld reinforcement value, and outer weld reinforcement value.

2. The weld quality inspection method according to claim 1, characterized in that, The steps for image processing of metallographic images of weld sections to obtain the outer contours of the inner and outer welds include: Preprocess the metallographic images of the weld section to obtain a smooth image; The watershed algorithm is used to segment and color fill the smooth image to obtain a segmented and filled image; The target region of the weld fill image is extracted using the HSV color space conversion method to obtain the inner weld region and the outer weld region. The contour curves of the inner weld region and the outer weld region are completed and interference is eliminated by morphological opening and closing operations. The outer contours of the inner weld and the outer weld are obtained by Canny edge detection.

3. The weld quality inspection method according to claim 2, characterized in that, The steps for preprocessing the metallographic image of the weld section to obtain a smooth image are as follows: Gaussian filtering is used to preprocess the metallographic image of the weld section to obtain a filtered smooth image.

4. The weld quality inspection method according to claim 2, characterized in that, The steps for extracting the target region from the weld fill image using HSV color space conversion to obtain the inner and outer weld regions include: The HSV color space conversion algorithm is used to convert the color of the weld fill image; The target area is extracted based on the H, S, and V values ​​of the color within the inner weld area after color conversion, to obtain the inner weld area. The target area is extracted based on the H, S, and V values ​​of the color within the outer weld seam area after color conversion, thus obtaining the outer weld seam area.

5. The weld quality inspection method according to claim 1, characterized in that, The steps include obtaining first contour information based on the outer contour of the inner weld, obtaining second contour information based on the outer contour of the outer weld, and drawing the inner weld curve and the outer weld curve based on the first contour information and the second contour information, including: The findContours function is used to detect the outer contours of the inner weld and the outer weld respectively to obtain the first contour information and the second contour information. The drawContours function is used to draw the inner weld curve and the outer weld curve based on the first contour information and the second contour information, respectively.

6. The weld quality inspection method according to claim 5, characterized in that, After the step of using the findContours function to detect the outer contour of the inner weld and the outer contour of the inner weld to obtain the first contour information and the second contour information, the method further includes: The first contour information and the second contour information are stored in a preset first storage unit and a preset second storage unit, respectively.

7. The weld quality inspection method according to claim 1, characterized in that, The steps for calculating the reinforcement height of the inner weld based on the inner weld curve and the second horizontal line, and for calculating the reinforcement height of the outer weld based on the outer weld curve and the fourth horizontal line, include: According to the formula Calculate the height value of the inner weld curve; where, This represents the height value of the inner weld curve. The coordinates of the highest extreme point of the internal weld curve are given. These are the coordinates of the lowest extreme point of the internal weld curve; According to the formula Calculate the height value of the external weld curve; where, This represents the height value of the outer weld curve. The coordinates of the highest extreme point of the external weld curve. These are the coordinates of the lowest extreme point of the external weld curve; like Greater than Then the coordinates of the highest extreme point of the inner weld curve The inner weld reinforcement value is obtained by subtracting from the second horizontal line, and the coordinates of the lowest extreme point of the outer weld curve are obtained. The excess height of the outer weld is obtained by subtracting from the fourth horizontal line. like Less than Then the coordinates of the lowest extreme point of the inner weld curve. The inner weld reinforcement value is obtained by subtracting from the second horizontal line, and the coordinates of the highest extreme point of the outer weld curve are obtained. The excess height of the outer weld is obtained by subtracting from the fourth horizontal line.

8. The weld quality inspection method according to claim 1, characterized in that, The weld inspection items for thick-walled welded workpieces include center deviation value less than or equal to the first preset value, misalignment value less than or equal to the second preset value, inner weld reinforcement value within the first preset range, and outer weld reinforcement value within the second preset range. The steps for determining whether the weld quality of a thick-walled welded workpiece is qualified based on the center deviation value, misalignment value, inner weld reinforcement value, and outer weld reinforcement value include: if all of the above welding inspection items are met, the weld of the thick-walled welded workpiece is qualified; if any one of the above welding inspection items is not met, the weld of the thick-walled welded workpiece is unqualified.

9. The weld quality inspection method according to claim 8, characterized in that, The first preset value is 3 mm; the second preset value is 1.6 mm; the first preset range is 0 mm to 3.5 mm; the second preset range is 0 mm to 3.0 mm.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the weld quality inspection method according to any one of claims 1 to 9.

Images