Welding defect detection method, device and detection system

Abstract

The embodiment of the present invention relates to the technical field of image data processing, and discloses a welding defect detection method, comprising obtaining a three-dimensional welding image of a welded object; extracting a physical welding contour from the three-dimensional welding image; determining a plane to be detected of the welded object, projecting the plane to be detected, and obtaining a two-dimensional detection image; obtaining a preset standard welding image, and extracting a standard welding contour from the preset standard welding image; calculating the absolute value of the height difference between each pixel point of the physical welding contour and the plane to be detected of the standard welding contour; setting the grayscale value of the pixel point whose height difference is greater than a convex threshold and less than a concave threshold to a first value, and setting the grayscale values ​​of the remaining pixel points to a second value; filling the corresponding value of each pixel point into a two-dimensional detection map to obtain a two-dimensional height grayscale map; connecting adjacent pixel points with the first grayscale value in the two-dimensional height grayscale map to obtain a connected area. Through the above method, the embodiment of the present invention can quickly and easily detect welding defects.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of image data processing, and in particular to a method, device, and system for detecting welding defects in lithium batteries. Background Art

[0002] Lithium batteries are now widely used in various parts of automobiles, aerospace, aircraft, and electrical equipment. Welding is a critical step in the lithium battery production process. Due to the complexity of the welding process, defects such as weld holes, weld pits, and incomplete welds are inevitable. These defects not only affect the appearance and performance of the battery, but also pose safety risks such as battery leakage and thermal runaway. Therefore, lithium battery weld quality inspection is particularly important.

[0003] During the implementation of the embodiments of the present invention, the inventors found that the traditional welding defect detection method is relatively cumbersome and inefficient in processing welding images. Summary of the Invention

[0004] The main technical problem solved by the embodiments of the present invention is to provide a lithium battery welding defect detection method. By directly obtaining a two-dimensional detection image from a three-dimensional welding image, and then reconstructing the contour morphology of the weld and comparing it with the contour data of the original weld, welding defects can be detected quickly and easily.

[0005] To solve the above technical problems, a technical solution adopted in an embodiment of the present invention is: providing a welding defect detection method, including obtaining a three-dimensional welding image of a weld, extracting a physical welding contour from the three-dimensional welding image, determining a plane to be detected of the weld, and projecting the plane to be detected to obtain a two-dimensional detection image, obtaining a preset standard welding image, and extracting a standard welding contour from the preset standard welding image, calculating the absolute value of the height difference between each pixel point of the plane to be detected of the physical welding contour and the standard welding contour, setting the grayscale value of the pixel point whose height difference is greater than a convex threshold and the pixel point whose height difference is less than a concave threshold to a first value, and setting the grayscale value of the remaining pixel points to a second value, the first value and the second value are different, filling the value of each pixel point into the two-dimensional detection image accordingly to obtain a two-dimensional height grayscale map, and connecting the adjacent pixel points with the first grayscale value in the two-dimensional height grayscale map to obtain a connected area.

[0006] Optionally, the step of obtaining a preset standard welding image and extracting a standard welding profile from the preset standard welding image includes: obtaining a preset conversion matrix; determining a preset standard welding image based on the preset conversion matrix; obtaining a cross-sectional profile of the weld from the preset standard welding image, wherein the cross-sectional profile of the weld is a cross-sectional profile at different angles; and fitting the cross-sectional profile of the weld to obtain a standard welding profile.

[0007] Optionally, the step of determining the defective area based on the connected area also includes: enclosing a minimum rectangle for each of the connected areas; calculating the area of ​​the minimum rectangle enclosing each of the connected areas; calculating whether the area of ​​the minimum rectangle enclosing each of the connected areas is greater than a threshold; if so, determining that the connected area is a defective area.

[0008] Optionally, the method further comprises marking the area of ​​the minimum circumscribed rectangle of each defect area on each defect area.

[0009] Optionally, the method further includes: acquiring a preset conversion matrix; converting the preset standard welding image according to the preset conversion matrix;

[0010] Optionally, the first value is 255 and the second value is 0.

[0011] To solve the above technical problems, another technical solution adopted in an embodiment of the present invention is to provide a welding defect detection device, comprising: a first acquisition module for acquiring a three-dimensional welding image of a weld; an extraction module for extracting a physical weld contour from the three-dimensional welding image; a first determination module for determining a plane to be detected of the weld and projecting the plane to be detected to obtain a two-dimensional detection image; a second acquisition module for acquiring a preset standard welding image and extracting a standard welding contour from the preset standard welding image; a calculation module for calculating the absolute value of the height difference between each pixel point on the plane to be detected of the physical weld contour and the standard weld contour; a setting module for setting the grayscale value of the pixel point whose height difference is greater than a convex threshold and less than a concave threshold to a first value, and setting the grayscale value of the remaining pixel points to a second value, wherein the first value and the second value are different; a filling module for filling the two-dimensional detection image with the corresponding value of each pixel point to obtain a two-dimensional height grayscale image; a connecting module for connecting adjacent pixel points with the first grayscale value in the two-dimensional height grayscale image to obtain a connected area; and a second determination module for determining a defect area based on the connected area.

[0012] Optionally, the device further includes: a marking module; the marking module is used to mark the area of ​​the minimum circumscribed rectangle of each defect area on each defect area.

[0013] Optionally, the device also includes a third acquisition module, a third determination module, a fourth acquisition module and a fitting module; the third acquisition module is used to acquire a preset conversion matrix; the second determination module is used to determine a preset standard welding image based on the preset conversion matrix; the fourth acquisition module is used to acquire the cross-sectional profile of the weld from the preset standard welding image, wherein the cross-sectional profile of the weld is a cross-sectional profile at different angles; the fitting module is used to fit the cross-sectional profile of the weld to obtain a standard welding profile.

[0014] Optionally, a welding defect detection system includes: a 3D profiler; a memory; and a controller, connected to the 3D profiler and the memory, respectively, the controller including at least one processor, the memory storing instructions executable by the at least one processor, and the instructions being executed by the at least one processor so that the at least one processor can execute any of the methods described above.

[0015] Optionally, a computer-readable storage medium stores computer-executable instructions, wherein the computer-executable instructions are used to enable a computer to execute any of the methods described above.

[0016] The beneficial effects of the embodiments of the present invention are as follows: different from the prior art, the embodiments of the present invention provide a welding defect detection method including obtaining a three-dimensional welding image of a weld, extracting a physical welding contour from the three-dimensional welding image; then determining a plane to be detected of the weld, and projecting the plane to be detected to obtain a two-dimensional detection image; obtaining a preset standard welding image, and extracting a standard welding contour from the preset standard welding image; calculating the absolute value of the height difference between each pixel point of the plane to be detected of the physical welding contour and the standard welding contour; setting the grayscale value of the pixel point whose height difference is greater than a convex threshold and the pixel point whose height difference is less than a concave threshold to a first value, and setting the grayscale value of the remaining pixel points to a second value, the first value and the second value being different; filling the value of each pixel point into the two-dimensional detection image to obtain a two-dimensional height grayscale image; connecting the adjacent pixel points with the first value in the two-dimensional height grayscale image to obtain a connected area. By the above method, a two-dimensional detection image of the plane to be detected can be obtained on the three-dimensional welding image and defect detection can be performed, so that defects in welding can be efficiently detected. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly describes the drawings required for describing the specific embodiments or the prior art. Similar elements or parts are generally identified by similar reference numerals throughout the drawings. Elements or parts in the drawings are not necessarily drawn to scale.

[0018] Figure 1 is a schematic diagram of a welding defect detection system according to an embodiment of the present invention;

[0019] Figure 2 This is a process of a welding defect detection method according to an embodiment of the present invention;

[0020] Figure 3 is another flow chart of step S104 of a welding defect detection method according to an embodiment of the present invention;

[0021] Figure 4 is another flow chart of step S108 of a welding defect detection method according to an embodiment of the present invention;

[0022] Figure 5 is a flow chart of another embodiment of a welding defect detection method according to an embodiment of the present invention;

[0023] Figure 6 This is a module block diagram of a welding defect detection device according to an embodiment of the present invention;

[0024] Figure 7 The figure is a hardware structure diagram of a welding defect detection system controller according to an embodiment of the present invention. Specific embodiments

[0025] For ease of understanding of the present invention, the present invention will be described in more detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that when an element is described as being "fixed on" another element, it can be directly on the other element or there can be one or more centered elements therebetween. When an element is described as being "connected" to another element, it can be directly connected to the other element or there can be one or more centered elements therebetween. The orientation or positional relationship indicated by the terms "upper", "lower", "inside", "outside", "vertical", "horizontal", etc. used in this specification is based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0026] Unless otherwise defined, all technical and scientific terms used in this specification have the same meanings as those commonly understood by those skilled in the art to which this invention pertains. The terms used in this specification are intended only to describe specific embodiments and are not intended to limit the invention. The term "and / or" as used in this specification includes any and all combinations of one or more of the associated listed items.

[0027] In addition, the technical features involved in different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0028] See Figure 1 , Figure 1 1 is a schematic diagram of a welding defect detection system according to an embodiment of the present invention, comprising a 3D profiler 10, a slide 20, a carrying platform 30, a controller 40, and a weld 50. The 3D profiler is mounted on the slide, the carrying platform 30 is used to carry the weld 50, and the controller 40 is used to control the 3D profiler 10 to scan the weld 50. The controller 40 is also used to process the acquired image.

[0029] See also Figure 2 , an embodiment of the present invention provides a method for detecting welding defects, comprising:

[0030] Step S101: Acquire a three-dimensional welding image of the welding object;

[0031] The 3D profilometer is controlled to collect a three-dimensional welding image of the welded object according to a preset running trajectory.

[0032] Step S102: extracting a physical welding contour from the three-dimensional welding image;

[0033] Step S103: determining a plane to be inspected of the weld, and projecting the plane to be inspected to obtain a two-dimensional inspection image;

[0034] A plane is calibrated for the physical welding contour, and a two-dimensional projection mapping is performed on the plane to generate a two-dimensional detection image (32 bits or 16 bits) in which a pair of xy coordinates corresponds to a physical height value, and then it is converted into 8-bit grayscale to make the two-dimensional detection image clearer.

[0035] Step S104: obtaining a preset standard welding image, and extracting a standard welding contour from the preset standard welding image;

[0036] See also Figure 3 , step S104 further includes:

[0037] Step S1041: Obtain a preset conversion matrix;

[0038] Step S1042: determining a preset standard welding image according to the preset conversion matrix;

[0039] Step S1043: acquiring a cross-sectional profile of the weld from the preset standard welding image, wherein the cross-sectional profile of the weld is a cross-sectional profile at different angles;

[0040] A welding area conversion matrix template is preset for the welding object, and a two-dimensional rotation and translation matrix is ​​obtained according to the matching calculation of the two-dimensional detection image. The welding area of ​​the preset standard welding image is calculated according to the welding area conversion matrix template and the two-dimensional rotation and translation matrix. The height information under the welding area is resampled along the radial contour of the welding path direction to obtain several cross-sections of the welding object contour at different angles. The cross-section contours at different angles can obtain the welding object contour at any angle and position. It can be arbitrarily sampled in the three-dimensional welding image, and the detection task can be completed in any position and direction. The contour spacing of the cross-section contours at different angles is controlled, and it supports reasonably reducing the accuracy reduction algorithm running time in the case of image accuracy overflow, thereby improving the detection efficiency.

[0041] Step S1044: fitting the cross-sectional profile of the weld to obtain a standard welding profile;

[0042] Traverse all contours, perform least squares quadratic curve fitting on each contour and perform a certain number of iterations, use the fitted curve as the standard welding contour and obtain the standard welding contour data.

[0043] Step S105: calculating the absolute value of the height difference between each pixel point of the plane to be detected of the actual welding profile and the standard welding profile;

[0044] Combining the original position height information of the three-dimensional welding image and the actual welding contour, the standard welding contour is subtracted to obtain the absolute value of all pixel points of all contours in the welding area relative to the standard data. If the height difference exceeds the absolute value, it is determined as a gap or a cold weld; if the height difference is lower than the absolute value, it is determined as a weld pit.

[0045] Step S106: setting the grayscale values ​​of the pixels whose height difference is greater than the convex threshold and the pixel whose height difference is less than the concave threshold as a first value, and setting the grayscale values ​​of the remaining pixels as a second value, wherein the first value and the second value are different;

[0046] The difference between all pixel points of all contours of the welding area and the standard data is backfilled into the original image to obtain a difference map (each value is the height difference of the position). For the set height thresholds of convex height and concave depth, two threshold segmentations are performed respectively. One is the corresponding convex threshold segmentation map (8-bit 2 grayscale map) when the value in the difference map is greater than the convex height, and the other is the corresponding concave threshold segmentation map when the value in the difference map is less than the concave depth. The height difference value corresponding to the convex and concave positions in the segmentation map is the first value, which is 255, and the remaining positions are the second value, which is 0.

[0047] Step S107: Fill the corresponding values ​​of the pixel points into the two-dimensional detection map to obtain a two-dimensional height grayscale map;

[0048] Step S108: Connecting adjacent pixel points in the two-dimensional height grayscale image whose grayscale values ​​are the first value to obtain a connected area.

[0049] See also Figure 4 , based on the connected area, the step of determining the defect area further includes:

[0050] Step S1081: circumscribing the minimum rectangle of each connected area;

[0051] Step S1082: Calculate the area of ​​the minimum circumscribed rectangle of each connected region;

[0052] Step S1083: Calculate whether the area of ​​the minimum circumscribed rectangle of the connected region is greater than a threshold;

[0053] Step S1084: If yes, determine that the connected area is a defective area.

[0054] Compare with the convex area and concave area thresholds, and the area greater than the threshold is the defect area.

[0055] An embodiment of the present invention provides a welding defect detection method, comprising: obtaining a three-dimensional welding image of a weld, extracting a physical welding contour from the three-dimensional welding image; then determining a plane to be detected of the weld, and projecting the plane to be detected to obtain a two-dimensional detection image; obtaining a preset standard welding image, and extracting a standard welding contour from the preset standard welding image; calculating the absolute value of the height difference between each pixel point of the plane to be detected of the physical welding contour and the standard welding contour; setting the grayscale value of the pixel point whose height difference is greater than a convex threshold and the pixel point whose height difference is less than a concave threshold to a first value, and setting the grayscale value of the remaining pixel points to a second value, wherein the first value and the second value are different; filling the value of each pixel point into the two-dimensional detection image to obtain a two-dimensional height grayscale image; connecting the adjacent pixel points with the first value in the two-dimensional height grayscale image to obtain a connected area. By the above method, a two-dimensional detection image of the plane to be detected can be obtained on the three-dimensional welding image and defect detection can be performed, so that defects in welding can be efficiently detected.

[0056] See also Figure 5 , a flow chart of a second embodiment of a welding defect detection method according to an embodiment of the present invention, the difference between this method and the above embodiment is that the method further includes:

[0057] Step S109: Mark the area of ​​the minimum circumscribed rectangle of each defect area on each defect area.

[0058] An embodiment of the present invention provides a welding defect detection method comprising: identifying the area of ​​a minimum rectangle circumscribing each defect region. This method enables obtaining a two-dimensional inspection image of the plane to be inspected on a three-dimensional welding image and performing defect detection, effectively detecting weld defects.

[0059] See also Figure 6, an embodiment of the present invention further provides a welding defect detection device 2, comprising a first acquisition module 21 for acquiring a three-dimensional welding image of a weld; an extraction module 22 for extracting a physical welding contour from the three-dimensional welding image; a first determination module 23 for determining a plane to be detected of the weld and projecting the plane to be detected to obtain a two-dimensional detection image; a second acquisition module 24 for acquiring a preset standard welding image and extracting a standard welding contour from the preset standard welding image; a calculation module 24 for calculating the absolute value of the height difference between each pixel point of the physical welding contour and the standard welding contour on the plane to be detected; a setting module 25 for setting the grayscale value of the pixel point whose height difference is greater than a convex threshold and the pixel point whose height difference is less than a concave threshold to a first value, and setting the grayscale value of the remaining pixel points to a second value, wherein the first value and the second value are different; a connection module 27 for connecting adjacent pixel points whose grayscale values ​​are the first value in the two-dimensional height grayscale image to obtain a connected area; and a second determination module 28 for determining a defect area based on the connected area.

[0060] In some embodiments, the welding defect detection device 2 further includes: a marking module 29; the marking module 29 is used to mark the area of ​​the minimum circumscribed rectangle of each defect area on each defect area.

[0061] In some embodiments, the welding defect detection device also includes: a third acquisition module 201, a third determination module 202, a fourth acquisition module 203 and a fitting module 204; the third acquisition module 201 is used to obtain a preset conversion matrix; the third determination module 202 is used to determine a preset standard welding image based on the preset conversion matrix; the fourth acquisition module 203 is used to obtain the cross-sectional profile of the weld from the preset standard welding image, wherein the cross-sectional profile of the weld is a cross-sectional profile at different angles; the fitting module 204 is used to fit the cross-sectional profile of the weld to obtain a standard welding profile.

[0062] An embodiment of the present invention provides a welding defect detection device, comprising a first acquisition module for acquiring a three-dimensional welding image of a weld; an extraction module for extracting a physical welding contour from the three-dimensional welding image; a determination module for determining a preset standard welding image according to the preset conversion matrix, and projecting the plane to be detected to obtain a two-dimensional detection image; a second acquisition module for acquiring a preset standard welding image and extracting a standard welding contour from the preset standard welding image; a calculation module for calculating the absolute value of the height difference between each pixel point of the physical welding contour and the standard welding contour on the plane to be detected; a setting module for setting the height difference of the pixel point to be greater than a convex threshold, and the height of the pixel point to be greater than a convex threshold. The grayscale value of the pixel point whose height difference is less than the depression threshold is set to the first value, and the grayscale values ​​of the remaining pixel points are set to the second value, and the first value and the second value are different; a setting module is used to set the grayscale value of the pixel point whose height difference is greater than the protrusion threshold and the grayscale value of the pixel point whose height difference is less than the depression threshold to the first value, and the grayscale values ​​of the remaining pixel points are set to the second value, and the first value and the second value are different; a connection module is used to connect the pixel points whose adjacent grayscale values ​​are the first value in the two-dimensional height grayscale image to obtain a connected area; a determination module is used to determine the defect area according to the connected area, and by obtaining a two-dimensional detection image of the plane to be detected on the three-dimensional welding image and performing defect detection, defects in the welding can be efficiently detected.

[0063] See also Figure 7 , Figure 7 FIG. 1 is a schematic diagram of the hardware structure of a calibration system controller provided by an embodiment of the present invention. Figure 7 As shown, the controller 40 includes: one or more processors 401 and a memory 402. The figure takes one processor 401 as an example. The processor 401 and the memory 402 can be connected via a bus or other means. Figure 7 The bus connection is taken as an example.

[0064] The memory 402 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as the program instructions / modules corresponding to the method for generating expert influence in the embodiment of the present invention (for example, the attached Figure 6 The processor 401 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions, and modules stored in the memory 402, thereby implementing the expert influence generation method and expert recommendation method of the above-mentioned method embodiment.

[0065] The memory 402 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the expert influence generation device and the expert recommendation device. In addition, the memory 402 may include a high-speed random access memory and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory may optionally include a memory remotely located relative to the processor 401, and these remote memories may be connected to the expert influence generation device and the expert recommendation device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0066] The one or more modules are stored in the memory 402, and when executed by the one or more processors 401, perform the method in any of the above method embodiments, for example, perform the above described Figure 2 Steps S101 to S108 of the method, Figure 3 In the method steps S1041-S1044, Figure 4 Steps S1081 to S1084 of the method, Figure 5 Steps S101 to S109 of the method are implemented Figure 6 The functions of modules 21-204 in the above product can execute the method provided by the embodiment of the present invention, and have the corresponding functional modules and beneficial effects of the execution method. For technical details not fully described in this embodiment, please refer to the method provided by the embodiment of the present invention.

[0067] An embodiment of the present invention provides a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used by an electronic device to execute the method in any of the above method embodiments, for example, to execute the method described above. Figure 2 Steps S101 to S108 of the method, Figure 3 In the method steps S1041-S1044, Figure 4 Steps S1081 to S1084 of the method, Figure 5 Steps S101 to S109 of the method are implemented Figure 6 Module 21-204 in.

[0068] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention's description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A welding defect detection method, characterized in that: include: Acquire a three-dimensional welding image of the weld; extracting a physical welding contour from the three-dimensional welding image; Determining a plane to be inspected of the weld, and projecting the plane to be inspected to obtain a two-dimensional inspection image; Obtaining a preset standard welding image and extracting a standard welding profile from the preset standard welding image, including: obtaining a preset conversion matrix, determining a preset standard welding image according to the preset conversion matrix, obtaining a cross-sectional profile of the weld from the preset standard welding image, wherein the cross-sectional profile of the weld is a cross-sectional profile at different angles, and fitting the cross-sectional profile of the weld to obtain a standard welding profile; Calculating the absolute value of the height difference between each pixel point of the plane to be detected of the actual welding profile and the standard welding profile; The grayscale values ​​of the pixels whose height difference is greater than the convex threshold and the pixel whose height difference is less than the concave threshold are set to a first value, and the grayscale values ​​of the remaining pixels are set to a second value, wherein the first value and the second value are different, the first value is 255, and the second value is 0; Fill the corresponding values ​​of each pixel point into the two-dimensional detection image to obtain a two-dimensional height grayscale image; Connecting adjacent pixel points with a first grayscale value in the two-dimensional height grayscale image to obtain a connected region; For each of the connected regions, the area of ​​the minimum circumscribed rectangle is calculated. Calculate whether the area of ​​the minimum circumscribed rectangle of the connected region is greater than a threshold; If so, the connected area is determined to be a defect area.

2. The method according to claim 1, characterized in that The method further comprises: The area of ​​the minimum circumscribed rectangle of each defect area is marked on each defect area.

3. A device for detecting welding defects, characterized in that: The method according to any one of claims 1 to 2, wherein the device comprises: A first acquisition module is used to acquire a three-dimensional welding image of the welded object; an extraction module is used to extract the actual weld contour from the three-dimensional welding image; A first determining module is used to determine a plane to be inspected of the weld and project the plane to be inspected to obtain a two-dimensional inspection image; a second acquisition module, acquiring a preset standard welding image and extracting a standard welding contour from the preset standard welding image; A third acquisition module is used to obtain a preset conversion matrix; A third determining module is used to determine a preset standard welding image according to the preset conversion matrix; a fourth acquisition module, configured to acquire a cross-sectional profile of the weld from the preset standard welding image, wherein the cross-sectional profile of the weld is a cross-sectional profile at different angles; A fitting module, configured to fit the cross-sectional profile of the weld to obtain a standard weld profile; A calculation module, configured to calculate the absolute value of the height difference between each pixel point of the plane to be detected of the actual welding profile and the standard welding profile; A setting module, configured to set the grayscale values ​​of the pixels whose height difference is greater than a convex threshold and whose height difference is less than a concave threshold to a first value, and set the grayscale values ​​of the remaining pixels to a second value, wherein the first value and the second value are different, the first value is 255, and the second value is 0; A connection module, configured to connect adjacent pixel points with a first grayscale value in the two-dimensional height grayscale image to obtain a connected area; A second determining module is used to determine a defective area based on the connected area; The marking module is used to mark the area of ​​the minimum circumscribed rectangle of each defect area on each defect area.

4. A welding defect detection system, characterized in that: include: 3D profilometer; Memory; A controller is connected to the 3D profiler and the memory respectively, the controller includes at least one processor, the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 2.

5. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the method according to any one of claims 1 to 2.

Images