Weld quality detection method and system, electronic device, storage medium

Abstract

The application discloses a kind of weld quality detection method and system, electronic equipment, storage medium, it respectively extracts two base material workpiece cross section profile straight line and fusion metal profile curve to each frame weld cross section profile point cloud data, and based on two base material workpiece cross section profile straight line and fusion metal profile curve, the weld feature of each frame weld cross section profile point cloud data is extracted, and according to the weld feature of extraction, whether the weld quality of each frame weld cross section is qualified is judged, since two base material workpiece cross section profile straight line is extracted, more weld features can be extracted for weld quality analysis, improve the weld quality detection accuracy of each frame weld cross section profile.And, according to the weld quality judgment result of multiple frame weld cross section, whether there is welding quality defect is comprehensively judged, further improve the accuracy of weld quality detection result.

Description

Technical Field

[0001] The present invention relates to the technical field of weld quality detection, and in particular to a weld quality detection method and system, electronic equipment, and a computer-readable storage medium. Background Art

[0002] Traditional weld surface quality inspection has a low degree of automation, relying primarily on manual visual judgment and simple measurement methods. This method is subject to many human influences, has poor consistency in inspection standards, and cannot meet the requirements of weld quality inspection. Furthermore, for weld quality inspection and judgment in confined spaces, the confined space is very unfavorable for human operation and presents many dangerous factors, greatly reducing the operability of weld inspection. Therefore, non-contact line laser sensors are currently used, which are placed after the welding gun to perform online inspection of the weld after welding, thereby improving the degree of automation and consistency of inspection standards for weld quality inspection. However, current weld quality inspection algorithms typically only perform fitting inspections on the contour curve of the weld cross section, without identifying the contour of the weld base material cross section, resulting in a low accuracy rate for weld quality inspection results. For example, patent CN104697467A discloses a method for detecting weld appearance shape and surface defects based on line laser scanning. It uses a line laser to obtain the actual contour curve of any cross-section of the weld, and performs high-dimensional fitting of the actual contour curve to obtain a fitted contour curve. If the difference between any point on the actual contour curve of the weld and the fitted contour curve exceeds a preset standard value, it is determined that there is a defect in the weld at that location; because it uses the least squares method to perform high-dimensional fitting of the actual contour curve of the weld cross-section to obtain the first-order derivative curve of the contour curve, and does not identify the contour of the cross-section of the weld parent material workpiece, it is easy to cause the difference between the point on the actual contour curve and the fitted contour curve to exceed the preset value due to interference from sensor scattered points and noise points, which will lead to misjudgment of welding defects. Summary of the Invention

[0003] The present invention provides a weld quality detection method and system, electronic equipment, and computer-readable storage medium, which can extract more weld features for weld quality analysis and comprehensively determine whether welding quality defects exist based on the weld quality judgment results of multiple frames of weld cross sections, greatly improving the accuracy of weld quality detection results.

[0004] According to one aspect of the present invention, a weld quality detection method is provided, comprising the following contents:

[0005] Continuously scan the weld to obtain multiple frames of weld cross-sectional contour point cloud data;

[0006] For each frame of weld cross-section contour point cloud data, two parent material workpiece cross-section contour lines and weld metal contour curves are extracted respectively;

[0007] Extract the weld features of each frame of weld cross-section contour point cloud data based on two straight lines of the parent material workpiece cross-section contour and the weld metal contour curve, and judge whether the weld quality of each frame of weld cross-section is qualified based on the extracted weld features;

[0008] The presence of welding quality defects is comprehensively determined based on the weld quality judgment results of multiple frames of weld cross sections.

[0009] Furthermore, the process of extracting two straight lines of the cross-sectional contour of the parent material workpiece includes the following:

[0010] The point cloud data of the cross-sectional contour of each frame of the weld is stored in the first register queue, the point cloud data of the cross-sectional contour of each frame of the weld is discretized, the discretized point cloud data is rounded in the X and Z coordinate planes and stored in the second register queue, and a one-to-one mapping is performed with the point cloud data in the first register queue;

[0011] Set the resolution of the Hough space and the accumulator matrix, convert the rectangular coordinates of all points in the second register queue into polar coordinates, find the corresponding unit in the Hough space based on the converted polar coordinates and add 1 to the accumulator of the unit;

[0012] Filter out the two accumulators with the largest values ​​in the accumulator matrix, find the corresponding points in the second register queue, and then find the corresponding points in the first register queue based on the mapping relationship to construct two new point cloud sets;

[0013] Linear fitting is performed on the two new point cloud sets respectively to obtain two cross-sectional contour lines of the parent material workpiece.

[0014] Furthermore, the process of extracting weld features of each frame of weld cross-sectional contour point cloud data based on the two parent material workpiece cross-sectional contour lines and the weld metal contour curve includes the following:

[0015] Find the intersection of the two parent material workpiece cross-sectional contour lines as the first intersection point, find the intersection of the first parent material workpiece cross-sectional contour line and the weld metal contour curve as the second intersection point, find the intersection of the second parent material workpiece cross-sectional contour line and the weld metal contour curve as the third intersection point, and calculate the envelope area S enclosed by the first intersection point, the second intersection point, the third intersection point, and the weld metal contour curve;

[0016] Connect the second and third intersection points into a straight line as the reference line, select the point in the weld metal profile curve that is above the reference line and farthest from the reference line, and calculate the farthest distance D H ;

[0017] Count the number of contour points N located above the reference straight line in the weld metal contour curve between the second intersection point and the third intersection point up and the number of contour points N below the reference line down ;

[0018] Calculate the distance D between the first intersection point and the second intersection point L , the distance D from the first intersection to the third intersection R ;

[0019] The envelope area S, the maximum distance D H , the number of contour points N located above the reference line up , the number of contour points N below the reference line down , the distance D between the first intersection point and the second intersection point L and the distance D from the first intersection to the third intersection R as a weld feature.

[0020] Furthermore, when S is less than the preset threshold and N down When it is greater than the preset threshold, it is determined that there is a weld sag, leak or arc pit; when |D L -D R When | is greater than the preset threshold, it is determined that there is a weld deviation; when S is less than the preset threshold and D H When it is greater than the preset threshold, it is determined that there is a weld nodule; when D H When it is greater than the preset threshold, it is determined that there is excess height deviation; when D L or D R When it is less than the preset threshold, it is determined that there is unilateral non-fusion; when N down When it is greater than the preset threshold, it is determined that there is a crack.

[0021] Furthermore, the process of comprehensively determining whether there are welding quality defects based on the weld quality judgment results of multiple frames of weld cross sections includes the following:

[0022] The number of cross-sections with the same type of defects continuously present, the acquisition frame frequency, and the welding speed are counted, and the defect length is calculated based on the following formula: Where L represents the defect length, N represents the number of cross-sections with the same type of defect continuously present, F represents the acquisition frame frequency, and V represents the welding speed. When the defect length is greater than the preset threshold, it is determined that this type of welding quality defect exists.

[0023] Furthermore, after obtaining multiple frames of weld cross-section contour point cloud data, median filtering is performed on the point cloud data.

[0024] Furthermore, the process of extracting the weld metal contour curve includes the following:

[0025] Two new point cloud sets are removed from each frame of weld cross-section contour point cloud data, and the remaining point cloud data are fitted using the least squares method to obtain the weld metal contour curve.

[0026] In addition, the present invention also provides a weld quality detection system, comprising:

[0027] Point cloud data acquisition module, used to continuously scan the weld and obtain multiple frames of weld cross-sectional contour point cloud data;

[0028] The contour extraction module is used to extract two straight lines of the cross-sectional contour of the parent material and the workpiece and the weld metal contour curve from each frame of the weld cross-sectional contour point cloud data;

[0029] The weld quality judgment module is used to extract the weld features of each frame of weld cross-section contour point cloud data based on two parent material workpiece cross-section contour lines and the weld metal contour curve, and judge whether the weld quality of each frame of weld cross-section is qualified based on the extracted weld features;

[0030] The comprehensive judgment module is used to comprehensively judge whether there are welding quality defects based on the weld quality judgment results of multiple frames of weld cross sections.

[0031] In addition, the present invention also provides an electronic device, including a processor and a memory, wherein the memory stores a computer program, and the processor is configured to execute the steps of the above method by calling the computer program stored in the memory.

[0032] In addition, the present invention also provides a computer-readable storage medium for storing a computer program for performing weld quality inspection, wherein the computer program executes the steps of the above-mentioned method when running on a computer.

[0033] The present invention has the following beneficial effects:

[0034] The weld quality detection method of the present invention extracts two parent material workpiece cross-sectional contour lines and a weld metal contour curve from each frame of weld cross-sectional contour point cloud data, extracts weld features from each frame of weld cross-sectional contour point cloud data based on the two parent material workpiece cross-sectional contour lines and the weld metal contour curve, and judges whether the weld quality of each frame of weld cross-sectional contour is qualified based on the extracted weld features. Since the two parent material workpiece cross-sectional contour lines are extracted, more weld features can be extracted for weld quality analysis, thereby improving the accuracy of weld quality detection for each frame of weld cross-sectional contour. In addition, the presence of welding quality defects is comprehensively determined based on the weld quality judgment results of multiple frames of weld cross-sectional contours, further improving the accuracy of weld quality detection results.

[0035] In addition, the weld quality detection system of the present invention also has the above advantages.

[0036] In addition to the above-described objects, features and advantages, the present invention has other objects, features and advantages. The present invention will be further described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings, which constitute part of this application, are intended to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are intended to explain the present invention and do not constitute an undue limitation of the present invention. In the accompanying drawings:

[0038] Figure 1 It is a flow chart of the weld quality detection method of the preferred embodiment of the present application.

[0039] Figure 2 yes Figure 1 Schematic diagram of the sub-process of step S2 in FIG.

[0040] Figure 3 It is a schematic diagram of mapping point cloud data in two register queues in a preferred embodiment of the present application.

[0041] Figure 4 It is a schematic diagram of the calculation principle of the accumulator matrix in the preferred embodiment of the present application.

[0042] Figure 5 yes Figure 1 Schematic diagram of the sub-process of step S3 in FIG.

[0043] Figure 6 It is a schematic diagram of weld feature extraction in a preferred embodiment of the present application.

[0044] Figure 7 It is a schematic diagram of the module structure of a weld quality inspection system according to another embodiment of the present application. DETAILED DESCRIPTION

[0045] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0046] Reference Figure 1 The preferred embodiment of the present application provides a weld quality detection method, comprising the following contents:

[0047] Step S1: Continuously scan the weld to obtain multiple frames of weld cross-sectional contour point cloud data;

[0048] Step S2: for each frame of weld cross-section contour point cloud data, extract two parent material workpiece cross-section contour lines and a weld metal contour curve respectively;

[0049] Step S3: extracting weld features from each frame of weld cross-section contour point cloud data based on the two parent material workpiece cross-section contour lines and the weld metal contour curve, and judging whether the weld quality of each frame of weld cross-section is qualified based on the extracted weld features;

[0050] Step S4: comprehensively determine whether there are welding quality defects based on the weld quality judgment results of multiple frames of weld cross sections.

[0051] It can be understood that the weld quality inspection method of this embodiment extracts two parent material workpiece cross-sectional contour lines and a weld metal contour curve from each frame of weld cross-sectional contour point cloud data. The weld features of each frame of weld cross-sectional contour point cloud data are extracted based on the two parent material workpiece cross-sectional contour lines and the weld metal contour curve. The weld quality of each frame of weld cross-sectional contour point cloud data is then determined based on the extracted weld features. The extraction of two parent material workpiece cross-sectional contour lines allows for the extraction of more weld features for weld quality analysis, thereby improving the accuracy of weld quality inspection for each frame of weld cross-sectional contour. Furthermore, the presence of welding quality defects is comprehensively determined based on the weld quality judgment results of multiple frames of weld cross-sectional contours, further improving the accuracy of weld quality inspection results.

[0052] It will be appreciated that in step S1, the line laser sensor positioned after the welding torch continuously scans the newly formed weld to obtain multiple frames of weld cross-sectional profile point cloud data. Optionally, after obtaining the multiple frames of weld cross-sectional profile point cloud data, the point cloud data is also subjected to median filtering to remove some noise points, thereby improving the accuracy of the point cloud data and reducing the amount of data processing.

[0053] It is understandable that Figure 2 As shown, in step S2, the process of extracting two straight lines of the cross-sectional contour of the parent material workpiece includes the following:

[0054] Step S21: storing each frame of weld cross-sectional contour point cloud data in the first register queue, discretizing each frame of weld cross-sectional contour point cloud data, rounding the discretized point cloud data in the X and Z coordinate planes, and storing them in the second register queue, and performing a one-to-one mapping with the point cloud data in the first register queue;

[0055] Step S22: Set the resolution of the Hough space and the accumulator matrix, convert the rectangular coordinates of all points in the second register array into polar coordinates, find the corresponding unit in the Hough space according to the converted polar coordinates, and perform an increment operation on the accumulator of the unit;

[0056] Step S23: Filter out the two accumulators with the largest values ​​in the accumulator matrix, find the corresponding points in the second register queue, and then find the corresponding points in the first register queue according to the mapping relationship to construct two new point cloud sets;

[0057] Step S24: performing linear fitting on the two new point cloud sets respectively to obtain two straight lines of the cross-section contour of the parent material workpiece.

[0058] Specifically, each frame of weld cross-section contour point cloud data after median filtering is saved in the first register queue, and then each frame of weld cross-section contour point cloud data after median filtering is discretized. In the Cartesian coordinate system, the discretized point cloud data is rounded in the X and Z coordinate planes and saved in the second register queue, and mapped one-to-one with the point cloud data in the first register queue, as shown in the following example: Figure 3 Then, set the resolution of the Hough space and set the accumulator matrix, and initialize the data of all accumulators to 0. In order to avoid interference caused by fitting similar series of straight lines in the Hough space, choose to set a larger resolution, for example, quantize the Hough space to Units, θ represents the angle value, and ρ represents the radius value. Then convert the rectangular coordinates of all points in the second register queue into polar coordinates. The conversion formula is: ρ = x cosθ + z sinθ, ρ ≥ 0, 0 ≤ θ ≤ 2π. Then find the corresponding unit in the Hough space based on the converted polar coordinates and add 1 to the accumulator of the unit. When there are two straight lines of the parent material and workpiece cross section, the corresponding accumulator will have two maximum values. Therefore, the two accumulators with the largest values ​​in the accumulator matrix are selected. For example, Figure 4 Q A and Q B , and find the corresponding points in the second register queue, and find the corresponding points in the first register queue based on the mapping relationship, thereby constructing two new point cloud sets A and B. Finally, the least squares method is used to perform straight line fitting on the new point cloud sets A and B respectively, thereby obtaining two fitting lines, which are the two cross-sectional contour lines of the parent material workpiece.

[0059] It can be understood that the present invention repeatedly screens and accesses data by establishing two register queues. Although it expands the data storage capacity, it greatly reduces the algorithm calculation requirements, uses physical space in exchange for calculation speed, and uses Hough transform to preliminarily screen the straight line fitting point cloud, and then uses the least squares method to perform straight line fitting on the screened point cloud, thereby improving the accuracy of straight line extraction of the parent material workpiece cross section, reducing the calculation amount of data processing, and overcoming the high computing power requirement for real-time processing of the collected weld cross-section data. It can perform intensive collection of welds and online calculations for each frame, thereby improving the accuracy of weld quality detection.

[0060] It can be understood that in step S2, the process of extracting the weld metal contour curve includes the following:

[0061] Two new point cloud sets are removed from each frame of weld cross-section contour point cloud data, and the remaining point cloud data are fitted using the least squares method to obtain the weld metal contour curve.

[0062] Specifically, after extracting point cloud sets A and B, they are removed from the original point cloud data, and the remaining point cloud data is fitted using the least squares method to obtain the weld metal contour curve. Optionally, after removing point cloud sets A and B, the remaining point cloud data can also be subjected to nonlinear filtering, which can effectively suppress noise interference while preserving more contour information.

[0063] It is understandable that Figure 5 As shown, in the step S3, the process of extracting weld features of each frame of weld cross-sectional contour point cloud data based on two parent material workpiece cross-sectional contour lines and weld metal contour curve includes the following:

[0064] Step S31: Find the intersection of two parent material workpiece cross-sectional contour lines as the first intersection point, find the intersection of the first parent material workpiece cross-sectional contour line and the weld metal contour curve as the second intersection point, find the intersection of the second parent material workpiece cross-sectional contour line and the weld metal contour curve as the third intersection point, and calculate the area S of the envelope region enclosed by the first intersection point, the second intersection point, the third intersection point, and the weld metal contour curve;

[0065] Step S32: Connect the second intersection point and the third intersection point into a straight line as the reference line, select the point in the weld metal profile curve that is above the reference line and farthest from the reference line, and calculate the farthest distance D H ;

[0066] Step S33: Count the number of contour points N located above the reference straight line in the weld metal contour curve between the second intersection point and the third intersection point. up and the number of contour points N below the reference line down ;

[0067] Step S34: Calculate the distance D between the first intersection point and the second intersection point L , the distance D from the first intersection to the third intersection R ;

[0068] Step S35: The envelope area S, the maximum distance D H , the number of contour points N located above the reference line up , the number of contour points N below the reference line down, the distance D between the first intersection point and the second intersection point L and the distance D from the first intersection to the third intersection R as a weld feature.

[0069] Specifically, if Figure 6 As shown, first find two straight lines L of the cross-section contour of the parent material and workpiece A and L B The intersection of the first parent material workpiece cross-sectional contour line and the weld metal contour curve is found as the first intersection point PK. The first intersection point of the second parent material workpiece cross-sectional contour line and the weld metal contour curve is found as the second intersection point PL. The first intersection point of the second parent material workpiece cross-sectional contour line and the weld metal contour curve is found as the third intersection point PR. The area S of the envelope formed by the first intersection point PK, the second intersection point PL, the third intersection point PR, and the weld metal contour curve is calculated. Then, the second intersection point PL and the third intersection point PR are connected into a straight line as the base line BaseLine. The point PH in the weld metal contour curve that is above the base line and farthest from the base line is selected, and the distance D from the point PH to the base line is calculated. H Next, count the number of contour points N located above the reference straight line in the weld metal contour curve between the second intersection point and the third intersection point. up and the number of contour points N below the reference line down , calculate the distance D between the first intersection point and the second intersection point L , the distance D from the first intersection to the third intersection R Therefore, the weld features extracted by the present invention include the envelope area S, the maximum distance D H , the number of contour points N located above the reference line up , the number of contour points N below the reference line down , the distance D between the first intersection point and the second intersection point L and the distance D from the first intersection to the third intersection R , and then perform weld quality assessment for each frame based on the extracted weld features. down When it is greater than the preset threshold, it is determined that there is a weld sag, leak or arc pit; when |D L -D R When | is greater than the preset threshold, it is determined that there is a weld deviation; when S is less than the preset threshold and D H When it is greater than the preset threshold, it is determined that there is a weld nodule; when D H When it is greater than the preset threshold, it is determined that there is excess height deviation; when D L or D R When it is less than the preset threshold, it is determined that there is unilateral non-fusion; when N downWhen the value is greater than a preset threshold, it is determined that a crack exists. The preset threshold value corresponding to each defect type can be the same or different, and is set according to actual conditions.

[0070] It can be understood that the present invention can extract the envelope area S, the maximum distance D and the cross-sectional contour line of the two parent material workpieces and the weld metal contour curve. H , the number of contour points N located above the reference line up , the number of contour points N below the reference line down , the distance D between the first intersection point and the second intersection point L and the distance D from the first intersection to the third intersection R The weld characteristics in multiple dimensions such as diameter and width can be analyzed to facilitate the analysis of weld quality from multiple dimensions, thereby improving the accuracy of weld quality detection.

[0071] In addition, in step S3, a plane coordinate system is constructed with BaseLine as the x-axis and the second intersection point PL as the origin. The contour points between the second intersection point PL and the third intersection point PR are mapped to the plane coordinate system to obtain a new contour CN. CN is then smoothed and parabola-fitted to obtain an analytical curve C. Contour points whose CN is below C and whose distance to C exceeds a set threshold are counted. If multiple contour points are below C and whose distance to C exceeds the set threshold appear continuously, it is determined that there is a pore. In addition, if S, D L and D R If all of the above defects are within the preset range and none of them exist, the weld quality of the frame is considered qualified.

[0072] It can be understood that in step S4, steps S2 and S3 are repeated for each frame of weld cross-sectional contour point cloud data to obtain weld quality inspection results for each frame of weld cross-section, and then a comprehensive determination is made based on the weld quality inspection results for the weld cross-section to determine whether a weld quality defect exists. Specifically, the process of comprehensively determining whether a weld quality defect exists based on the weld quality inspection results for multiple frames of weld cross-sections includes the following:

[0073] The number of cross-sections with the same type of defects continuously present, the acquisition frame frequency, and the welding speed are counted, and the defect length is calculated based on the following formula: Where L represents the defect length, N represents the number of cross-sections with the same type of defect continuously present, F represents the acquisition frame frequency, and V represents the welding speed. When the defect length is greater than the preset threshold, it is determined that this type of welding quality defect exists.

[0074] In addition, since the relative position of the line laser sensor and the welding gun remains unchanged and the two move synchronously, the coordinates of the line laser sensor can be converted according to the coordinates of the welding gun, and then the position of the weld detection point can be calculated by the coordinates of the line laser sensor for easy tracing.

[0075] In addition, if Figure 7 As shown, another embodiment of the present invention further provides a weld quality detection system, preferably using the weld quality detection method as described above, comprising:

[0076] Point cloud data acquisition module, used to continuously scan the weld and obtain multiple frames of weld cross-sectional contour point cloud data;

[0077] The contour extraction module is used to extract two straight lines of the cross-sectional contour of the parent material and the workpiece and the weld metal contour curve from each frame of the weld cross-sectional contour point cloud data;

[0078] The weld quality judgment module is used to extract the weld features of each frame of weld cross-section contour point cloud data based on two parent material workpiece cross-section contour lines and the weld metal contour curve, and judge whether the weld quality of each frame of weld cross-section is qualified based on the extracted weld features;

[0079] The comprehensive judgment module is used to comprehensively judge whether there are welding quality defects based on the weld quality judgment results of multiple frames of weld cross sections.

[0080] It can be understood that the weld quality inspection system of this embodiment extracts two parent material workpiece cross-sectional contour lines and a weld metal contour curve for each frame of weld cross-sectional contour point cloud data. Based on these two parent material workpiece cross-sectional contour lines and the weld metal contour curve, weld features are extracted from each frame of weld cross-sectional contour point cloud data. The weld quality of each frame of weld cross-sectional contour is then determined based on the extracted weld features. Because two parent material workpiece cross-sectional contour lines are extracted, more weld features can be extracted for weld quality analysis, thereby improving the accuracy of weld quality inspection for each frame of weld cross-sectional contour. Furthermore, the presence of welding quality defects is comprehensively determined based on the weld quality judgment results of multiple frames of weld cross-sectional contours, further improving the accuracy of weld quality inspection results.

[0081] In addition, another embodiment of the present invention further provides an electronic device, including a processor and a memory, wherein the memory stores a computer program, and the processor is configured to execute the steps of the above method by calling the computer program stored in the memory.

[0082] In addition, another embodiment of the present invention further provides a computer-readable storage medium for storing a computer program for performing weld quality inspection, wherein the computer program executes the steps of the above-described method when running on a computer.

[0083] Common computer-readable storage media include: floppy disks, flexible disks, hard disks, magnetic tape, any other magnetic media, CD-ROMs, any other optical media, punch cards, paper tape, any other physical medium with a pattern of holes, random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), flash-erasable programmable read-only memory (FLASH-EPROM), any other memory chip or cartridge, or any other medium that can be read by a computer. Instructions can further be transmitted or received via a transmission medium. The term transmission medium may include any tangible or intangible medium that can be used to store, encode, or carry instructions for execution by a machine, and includes digital or analog communication signals or other intangible media that facilitate communication of such instructions. Transmission media include coaxial cables, copper wire, and fiber optics, including the wires of a bus used to transmit a computer data signal.

[0084] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiment of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal translation scripting language JavaScript, etc.

[0085] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0086] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0087] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0088] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0089] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

[0090] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A weld quality detection method, characterized in that: Includes the following: Continuously scan the weld to obtain multiple frames of weld cross-sectional contour point cloud data; For each frame of weld cross-section contour point cloud data, two parent material workpiece cross-section contour lines and weld metal contour curves are extracted respectively; Extract the weld features of each frame of weld cross-section contour point cloud data based on two straight lines of the parent material workpiece cross-section contour and the weld metal contour curve, and judge whether the weld quality of each frame of weld cross-section is qualified based on the extracted weld features; Comprehensively determine whether there are welding quality defects based on the weld quality judgment results of multiple frames of weld cross sections; The process of extracting two straight lines of the cross-sectional contour of the parent material workpiece includes the following: The point cloud data of the cross-sectional contour of each frame of the weld is stored in the first register queue, the point cloud data of the cross-sectional contour of each frame of the weld is discretized, the discretized point cloud data is rounded in the X and Z coordinate planes and stored in the second register queue, and a one-to-one mapping is performed with the point cloud data in the first register queue; Set the resolution of the Hough space and the accumulator matrix, convert the rectangular coordinates of all points in the second register queue into polar coordinates, find the corresponding unit in the Hough space based on the converted polar coordinates and add 1 to the accumulator of the unit; Filter out the two accumulators with the largest values ​​in the accumulator matrix, find the corresponding points in the second register queue, and then find the corresponding points in the first register queue based on the mapping relationship to construct two new point cloud sets; Perform linear fitting on the two new point cloud sets respectively to obtain two straight lines of the cross-section contour of the parent material and workpiece; The process of extracting weld features of each frame of weld cross-sectional contour point cloud data based on two parent material workpiece cross-sectional contour lines and a weld metal contour curve includes the following: Find the intersection of the two parent material workpiece cross-sectional contour lines as the first intersection point, find the intersection of the first parent material workpiece cross-sectional contour line and the weld metal contour curve as the second intersection point, find the intersection of the second parent material workpiece cross-sectional contour line and the weld metal contour curve as the third intersection point, and calculate the envelope area S enclosed by the first intersection point, the second intersection point, the third intersection point, and the weld metal contour curve; Connect the second and third intersection points into a straight line as the reference line, select the point in the weld metal profile curve that is above the reference line and farthest from the reference line, and calculate the farthest distance D H ; Count the number of contour points N located above the reference straight line in the weld metal contour curve between the second intersection point and the third intersection point up and the number of contour points N below the reference line down ; Calculate the distance D between the first intersection point and the second intersection point L , the distance D from the first intersection to the third intersection R ; The envelope area S, the maximum distance D H , the number of contour points N located above the reference line up , the number of contour points N below the reference line down , the distance D between the first intersection point and the second intersection point L and the distance D from the first intersection to the third intersection R As a weld feature; When S is less than the preset threshold and N down When it is greater than the preset threshold, it is determined that there is a weld sag, leak or arc pit; when |D L -D R When | is greater than the preset threshold, it is determined that there is a weld deviation; when S is less than the preset threshold and D H When it is greater than the preset threshold, it is determined that there is a weld nodule; when D H When it is greater than the preset threshold, it is determined that there is excess height deviation; when D L or D R When it is less than the preset threshold, it is determined that there is unilateral non-fusion; when N down When it is greater than the preset threshold, it is determined that there is a crack; The process of extracting the weld metal contour curve includes the following: Two new point cloud sets are removed from each frame of weld cross-section contour point cloud data, and the remaining point cloud data are fitted using the least squares method to obtain the weld metal contour curve.

2. The weld quality detection method according to claim 1, wherein: The process of comprehensively determining whether there are welding quality defects based on the weld quality judgment results of multiple frames of weld cross sections includes the following: The number of cross-sections with the same type of defects continuously present, the acquisition frame frequency, and the welding speed are counted, and the defect length is calculated based on the following formula: , where L represents the defect length, N represents the number of cross sections with the same type of defects continuously present, F represents the acquisition frame frequency, and V represents the welding speed. When the defect length is greater than the preset threshold, it is determined that there is a welding quality defect.

3. The weld quality detection method according to claim 1, wherein: After obtaining multiple frames of weld cross-section contour point cloud data, the point cloud data is also subjected to median filtering.

4. A weld quality inspection system, applied to the weld quality inspection method according to any one of claims 1 to 3, characterized in that: include: Point cloud data acquisition module, used to continuously scan the weld and obtain multiple frames of weld cross-sectional contour point cloud data; The contour extraction module is used to extract two straight lines of the cross-sectional contour of the parent material and the workpiece and the weld metal contour curve from each frame of the weld cross-sectional contour point cloud data; The weld quality judgment module is used to extract the weld features of each frame of weld cross-section contour point cloud data based on two parent material workpiece cross-section contour lines and the weld metal contour curve, and judge whether the weld quality of each frame of weld cross-section is qualified based on the extracted weld features; The comprehensive judgment module is used to comprehensively judge whether there are welding quality defects based on the weld quality judgment results of multiple frames of weld cross sections.

5. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores a computer program, and the processor is configured to execute the steps of the method according to any one of claims 1 to 3 by calling the computer program stored in the memory.

6. A computer-readable storage medium for storing a computer program for performing weld quality inspection, characterized in that: When the computer program is run on a computer, the computer program executes the steps of the method according to any one of claims 1 to 3.

Images