A welding quality evaluation method and system based on a welding robot

Abstract

This application relates to the technical field of industrial data processing, and provides a welding quality assessment method and system based on a welding robot. The method includes: first, in response to a welding start command, rapidly acquiring the gap image information of the target workpiece using an industrial camera; then, in response to a welding completion command, effectively acquiring the weld seam image information of the target workpiece; next, accurately determining the gap baseline information based on the gap image information; and simultaneously, accurately determining the weld seam baseline information based on the weld seam image information; finally, effectively generating welding quality assessment information based on the gap baseline information and the weld seam baseline information. This application, based on laser automatic tracking technology, can accurately determine whether the weld seam deviates from the ideal position, effectively improving the reliability and consistency of the welding process. It not only facilitates the rapid identification and correction of welding defects but also further ensures product quality.

Description

Technical Field

[0001] This application relates to the technical field of industrial data processing, and more specifically, to a welding quality assessment method and system based on a welding robot. Background Technology

[0002] A welding robot is an automated device specifically designed for welding operations. Its main function is to improve the efficiency, precision, and safety of welding, and it can perform complex welding tasks in various welding situations.

[0003] Currently, after a welding robot completes a welding operation, a manual assessment of the welding quality is usually required. However, this assessment process is highly dependent on the personal experience of the workers, has a large degree of subjectivity, and suffers from low reliability, which needs further improvement. Summary of the Invention

[0004] Based on this, embodiments of this application provide a welding quality assessment method and system based on a welding robot to solve the problem of low reliability in the prior art.

[0005] In a first aspect, embodiments of this application provide a welding quality assessment method based on a welding robot, the method comprising:

[0006] In response to a welding start command, the gap image information of the target workpiece is acquired based on a preset industrial camera, wherein the welding start command is used to instruct the welding robot to start welding according to a preset laser trajectory;

[0007] In response to the welding completion command, the weld seam image information of the target workpiece is acquired;

[0008] Based on the void image information, the void baseline information is determined, and based on the weld image information, the weld baseline information is determined.

[0009] Welding quality assessment information is generated based on the gap baseline information and weld baseline information.

[0010] Compared with existing technologies, the beneficial effects are as follows: The welding quality assessment method based on a welding robot provided in this application allows the terminal device to first respond to a welding start command and quickly acquire the gap image information of the target workpiece using an industrial camera. Then, in response to a welding completion command, it effectively acquires the weld image information of the target workpiece. Based on the gap image information, it accurately determines the gap baseline information, and simultaneously, based on the weld image information, it accurately determines the weld baseline information. Finally, based on the gap baseline information and the weld baseline information, it effectively generates welding quality assessment information, thereby achieving accurate judgment of whether the weld deviates from the ideal position, reducing subjective judgment, effectively improving reliability, and to a certain extent solving the problem of low reliability in the current system.

[0011] Secondly, embodiments of this application provide a welding quality assessment system based on a welding robot, the system comprising:

[0012] Void image information acquisition module: In response to the welding start command, it acquires void image information of the target workpiece based on a preset industrial camera;

[0013] Weld seam image information acquisition module: used to acquire weld seam image information of the target workpiece in response to the welding completion command;

[0014] Weld reference line information determination module: used to determine the gap reference line information based on the gap image information, and to determine the weld reference line information based on the weld image information;

[0015] Welding quality assessment information generation module: used to generate welding quality assessment information based on the void baseline information and weld baseline information.

[0016] Thirdly, embodiments of this application provide a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method described in the first aspect above.

[0017] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method described in the first aspect above.

[0018] It is understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below.

[0020] Figure 1 This is a schematic flowchart of a welding quality assessment method provided in an embodiment of this application;

[0021] Figure 2 This is a schematic diagram of a gap provided in an embodiment of this application;

[0022] Figure 3 This is a first schematic diagram of a weld provided in an embodiment of this application;

[0023] Figure 4 This is a flowchart illustrating step S300 in a welding quality assessment method provided in an embodiment of this application;

[0024] Figure 5 This is a schematic diagram of the target workpiece provided in an embodiment of this application;

[0025] Figure 6 This is a schematic diagram of the distance information provided in one embodiment of this application;

[0026] Figure 7 This is a flowchart illustrating step S391 of a welding quality assessment method provided in an embodiment of this application;

[0027] Figure 8 This is a second schematic diagram of a weld provided in an embodiment of this application;

[0028] Figure 9 This is a schematic diagram of reference point information provided in an embodiment of this application;

[0029] Figure 10 This is a schematic diagram of the weld reference line tolerance range information provided in an embodiment of this application;

[0030] Figure 11 This is a flowchart illustrating step S400 in a welding quality assessment method provided in an embodiment of this application;

[0031] Figure 12 This is a block diagram of a welding quality assessment system provided in one embodiment of this application;

[0032] Figure 13 This is a schematic diagram of a terminal device provided in an embodiment of this application. Detailed Implementation

[0033] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0034] In the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0035] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0036] To illustrate the technical solution described in this application, specific embodiments are provided below.

[0037] Please see Figure 1 , Figure 1 This is a flowchart illustrating the welding quality assessment method based on a welding robot provided in this embodiment. In this embodiment, the executing entity of the welding quality assessment method is a terminal device. It is understood that the types of terminal devices include, but are not limited to, mobile phones, tablets, laptops, Ultra-Mobile Personal Computers (UMPCs), netbooks, Personal Digital Assistants (PDAs), etc. This embodiment does not impose any restrictions on the specific type of terminal device.

[0038] Please see Figure 1 The welding quality assessment method provided in this application includes, but is not limited to, the following steps:

[0039] In S100, in response to the welding start command, the gap image information of the target workpiece is acquired based on a preset industrial camera.

[0040] Specifically, the terminal device can first respond to the welding start command and quickly acquire the gap image information of the target workpiece based on the preset industrial camera. The welding start command is used to instruct the welding robot to start welding according to the preset laser trajectory; the target workpiece is used to describe the aluminum alloy door panel to be welded; and the gap image information is used to describe the image obtained after the industrial camera takes a picture of the gap of the target workpiece.

[0041] Without loss of generality, during the welding process of the welding robot arm following the preset laser trajectory, the terminal equipment can use preset high-precision sensors (such as laser displacement sensors or vision sensors) to monitor the position and status of the welding head in real time, calculate the deviation between the welding head and the laser trajectory, and then dynamically control the movement trajectory of the welding robot arm according to the specific deviation to ensure that the welding head always stays on the laser trajectory.

[0042] It should be noted that welding in the middle of the gap ensures that the welding heat is evenly distributed throughout the welding area, reducing deformation or stress concentration caused by localized overheating or uneven cooling. This also results in a more uniform weld, ensuring that the weld's mechanical properties and strength meet design requirements. Therefore, the ideal position for the weld is in the middle of the gap; that is, when the centerline of the weld coincides with the centerline of the gap, the weld is in the ideal position. While theoretically, the welding robot can perform welding in the middle of the gap by following the laser trajectory, in actual processing, factors such as initial positioning errors or sensor malfunctions may cause the welding head's movement trajectory to deviate from the laser trajectory, leading to the welding point deviating from the ideal position, and consequently, the weld itself deviating from the ideal position.

[0043] In S200, in response to the welding completion command, the weld seam image information of the target workpiece is acquired.

[0044] Specifically, after the terminal device acquires the gap image information, it can respond to the welding completion command and acquire the weld seam image information of the target workpiece. The welding completion command is used to instruct the welding robot to complete the welding work; the weld seam image information is used to describe the image obtained by the industrial camera after taking a picture of the weld seam of the target workpiece.

[0045] In S300, the gap baseline information is determined based on the gap image information, and the weld baseline information is determined based on the weld image information.

[0046] Specifically, after the terminal device acquires the weld seam image information, it can accurately determine the gap baseline information based on the gap image information, and accurately determine the weld seam baseline information based on the weld seam image information.

[0047] In some possible implementations, for accurate determination of the gap baseline information, please refer to [link / reference]. Figure 4 Step S300 includes, but is not limited to, the following steps:

[0048] In S310, based on a preset edge detection algorithm, edge detection processing is performed on the gap image information to generate first gap edge line information and second gap edge line information.

[0049] Specifically, the terminal device can perform edge detection processing on the gap image information based on a preset edge detection algorithm to generate first gap edge line information and second gap edge line information. The edge detection algorithm can be an edge detection algorithm based on the Roberts operator, an edge detection algorithm based on the Prewitt operator, or an edge detection algorithm based on the Sobel operator. For example, please refer to [link to example]. Figure 2 and Figure 5 The first gap edge line information is used to describe the edge of any one side of the gap; the second gap edge line information is used to describe the edge of any other side of the gap.

[0050] In S320, based on a preset division distance value, the edge line information of the first gap is divided to generate multiple first gap edge sub-line information, and based on the division distance value, the edge line information of the second gap is divided to generate multiple second gap edge sub-line information.

[0051] Specifically, after the terminal device generates the first gap edge line information and the second gap edge line information, the terminal device can perform equidistant division processing on the first gap edge line information based on a preset division distance value, quickly generating multiple first gap edge sub-line information. At the same time, based on the same division distance value, the terminal device can perform equidistant division processing on the second gap edge line information, efficiently generating multiple second gap edge sub-line information.

[0052] In S330, based on the preset curvature threshold information, it is determined whether the curvature between two adjacent first gap edge sub-line information is equal to the curvature threshold information.

[0053] Specifically, after the terminal device generates multiple first gap edge sub-line information and multiple second gap edge sub-line information, the terminal device can first calculate the curvature between two adjacent first gap edge sub-line information respectively. Then, based on the preset curvature threshold information, it sequentially determines whether the curvature between two adjacent first gap edge sub-line information is equal to the curvature threshold information. The specific value of the curvature threshold information can be customized by the operation and maintenance personnel. For example, for target workpieces with strict production requirements, the curvature threshold information can be set to 0. In one possible implementation, in order to improve the fault tolerance rate, the curvature threshold information can be set to 0.01.

[0054] In S340, if the curvature between two adjacent first gap edge sub-line information is equal to the curvature threshold information, then the two adjacent first gap edge sub-line information are merged to generate first gap edge combined line information.

[0055] Specifically, if the curvature between two adjacent first gap edge sub-line information is equal to the curvature threshold information, it indicates that the two adjacent first gap edge sub-line information are relatively straight and can be classified as the same object. Therefore, the terminal device can merge the two adjacent first gap edge sub-line information to generate first gap edge combination line information, thereby effectively determining the part that can be used as the reference for subsequent operations from the gap of the target workpiece. The first gap edge combination line information is used to describe the two adjacent first gap edge sub-line information after merging.

[0056] In S350, based on the curvature threshold information, it is determined whether the curvature between two adjacent second gap edge sub-line information is equal to the curvature threshold information.

[0057] Specifically, after the terminal device generates the first gap edge combination line information, the terminal device can determine whether the curvature between two adjacent second gap edge sub-line information is equal to the curvature threshold information based on the curvature threshold information. The specific judgment process can refer to similar content in step S330 above, so it will not be repeated here.

[0058] In S360, if the curvature between two adjacent second gap edge sub-line information is equal to the curvature threshold information, then the two adjacent second gap edge sub-line information are merged to generate second gap edge combined line information.

[0059] Specifically, if the curvature between two adjacent second gap edge sub-line information is equal to the curvature threshold information, it indicates that the two adjacent second gap edge sub-line information are relatively straight and can be classified as the same object. Therefore, the terminal device can merge the two adjacent second gap edge sub-line information to generate second gap edge combination line information. The second gap edge combination line information is used to describe the two adjacent second gap edge sub-line information after merging.

[0060] In S370, based on the preset spacing information, the first gap edge combination line information and the second gap edge combination line information are grouped and processed to generate multiple gap edge line set information.

[0061] Specifically, the terminal device can group the first gap edge combination line information and the second gap edge combination line information based on the preset spacing information to generate multiple gap edge line set information. The specific value of the spacing information can be customized by the maintenance personnel, and the preferred specific value of the spacing information is the measured width corresponding to the gap of the target workpiece. Each gap edge line set information includes a first gap edge combination line information and a second gap edge combination line information.

[0062] For example, please refer to Figure 6 The terminal device can first determine the midpoint of the second gap edge combination line information, and then form a retrieval area with the midpoint as the center and the distance information as the radius. This retrieval area is... Figure 6 If any first gap edge combination line information intersects or is tangent to the search area within the area enclosed by the dotted line, then the first gap edge combination line information and the second gap edge combination line information corresponding to the midpoint of the search area are determined to be the same group, that is, the first gap edge combination line information and the second gap edge combination line information corresponding to the midpoint of the search area are determined to be a gap edge line set information.

[0063] In S380, for each gap edge line set information: based on the first gap edge combination line information and the second gap edge combination line information, the gap midpoint information is determined.

[0064] Specifically, after the terminal device generates multiple gap edge line set information, the terminal device can perform the following processing for each gap edge line set information: determine the gap midpoint information based on the first gap edge combination line information and the second gap edge combination line information, wherein the gap midpoint information is used to describe the midpoint corresponding to the shortest perpendicular line between the first gap edge combination line information and the second gap edge combination line information.

[0065] In S390, gap baseline information is generated based on the midpoint information of multiple gaps.

[0066] Specifically, after the terminal device determines the gap midpoint information, the terminal device can generate gap baseline information based on multiple gap midpoint information. The gap baseline information is used to describe the line segments connected by multiple gap midpoint information. For example, the terminal device can first generate multiple line segments with a gap midpoint information as one endpoint and another adjacent gap midpoint information as the other endpoint, and then connect the multiple line segments to generate the gap baseline information.

[0067] In S391, the weld reference line information is determined based on the weld image information.

[0068] Specifically, after the terminal device generates the gap baseline information, it can effectively determine the weld baseline information based on the weld image information, which helps to effectively assess the welding quality by measuring the degree of deviation between the weld baseline information and the gap baseline information.

[0069] In some possible implementations, for effectively determining weld baseline information, please refer to [link / reference]. Figure 7 Step S391 includes, but is not limited to, the following steps:

[0070] In S3911, edge detection processing is performed on the weld seam image information based on the edge detection algorithm to generate the first weld seam edge line information and the second weld seam edge line information.

[0071] Specifically, the terminal device can perform edge detection processing on the weld image information based on the edge detection algorithm to generate first weld edge line information and second weld edge line information. The specific selection of the edge detection algorithm can refer to the relevant content in step S310 above. The first weld edge line information is used to describe the edge of any one side of the weld. The first weld edge line information is used to describe the edge of any other side of the weld.

[0072] In S3912, based on a preset target point detection algorithm, multiple first welding intersection information are determined according to the first weld edge line information.

[0073] Specifically, after the terminal device generates the first weld edge line information and the second weld edge line information, the terminal device can determine multiple first welding intersection point information based on a preset target point detection algorithm and the first weld edge line information. The target point detection algorithm can be the YOLO v8 algorithm. The first welding intersection point information describes the intersection points between different weld points in the first weld edge line information. For example, please refer to [link to example]. Figure 3 and Figure 8 , Figure 8 The dots marked "A", "B" and "C" inside the center indicate the information of the first welding intersection.

[0074] In S3913, the shortest distance between each first welding intersection information and the second weld edge line information is calculated to generate the shortest distance information.

[0075] Specifically, after the terminal device determines multiple first welding intersection information, the terminal device can calculate the shortest distance between each first welding intersection information and the second weld edge line information, and quickly generate the shortest distance information.

[0076] In S3914, the mean shortest distance information is generated based on multiple shortest distance information.

[0077] Specifically, after the terminal device generates the shortest distance information, the terminal device can first calculate the sum of multiple shortest distance information, and then divide the sum by the total number of multiple shortest distance information to generate the average shortest distance information. The average shortest distance information is used to describe the average value of multiple shortest distance information.

[0078] In S3915, the first welding intersection information corresponding to the shortest distance information with the largest number is determined as the target reference point information.

[0079] Specifically, after the terminal device generates the average shortest distance information, it can determine the first welding intersection information corresponding to the most numerous shortest distance information as the target reference point information, thereby determining a representative reference point. For example, when there are 8 first welding intersection information with a shortest distance of 0.73 cm and 12 first welding intersection information with a shortest distance of 0.78 cm, the terminal device can determine the first welding intersection information with a shortest distance of 0.78 cm as the target reference point information.

[0080] In S3916, benchmark reference point information is generated based on the target reference point information and half of the average shortest distance information.

[0081] Specifically, after the terminal device determines the target reference point information, the terminal device can use the target reference point information as the starting point and then use half of the average shortest distance information as the distance value to generate the benchmark reference point information. The benchmark reference point information is located on the shortest line between the first weld edge line information and the second weld edge line information, and the distance between the benchmark reference point information and the target reference point information is half of the average shortest distance information.

[0082] In S3917, weld baseline information is generated based on multiple reference points.

[0083] Specifically, after the terminal device generates the reference point information, it can generate the weld reference line information based on the multiple reference point information. The weld reference line information overlaps with the multiple reference point information and is used to describe the line segment formed by connecting the multiple reference point information.

[0084] For example, please refer to Figure 8 and Figure 9 , Figure 9 The dot marked with "D" inside indicates the reference point information corresponding to the first welding intersection marked with "A". Figure 9 The dot marked with "E" inside indicates the reference point information corresponding to the first welding intersection marked with "B". Figure 9The dot marked with "F" inside indicates the reference point information corresponding to the first welding intersection marked with "C".

[0085] In some possible implementations, since the edge line information of the first weld and the edge line information of the second weld are not perfectly straight lines in practical applications, in order to better fit the actual application scenario, after step S300, the method may include, but is not limited to, the following steps:

[0086] In S301, the weld reference line fault tolerance range information is generated based on the weld reference line information and the preset fault tolerance distance value.

[0087] Specifically, the terminal device can generate weld reference line tolerance range information based on the weld reference line information and a preset tolerance distance value. This tolerance range information describes the area enclosed by the weld reference line information as the center line and extending outwards to both sides by a tolerance distance value. The length of the tolerance range information is the same as the length of the weld reference line information, and the width is twice the tolerance distance value. For example, please refer to [link to example]. Figure 9 and Figure 10 , Figure 10 The area enclosed by the cross-sectional lines represents the tolerance range information of the weld reference line.

[0088] In S400, welding quality assessment information is generated based on the void baseline information and the weld baseline information.

[0089] Specifically, the terminal equipment can accurately generate welding quality assessment information based on the offset between the gap baseline information and the weld baseline information. The welding quality assessment information includes qualified quality information and abnormal quality information. Qualified quality information describes that the welding quality is qualified, while abnormal quality information describes that the welding quality is unqualified.

[0090] In some possible implementations, for accurate generation of welding quality assessment information, please refer to [link / reference]. Figure 11 Step S400 includes, but is not limited to, the following steps:

[0091] In S410, it is determined whether the gap baseline information is completely within the weld baseline tolerance range information.

[0092] Specifically, the terminal equipment can determine whether the gap baseline information is completely within the weld baseline tolerance range information.

[0093] In S420, if the gap baseline information is completely within the weld baseline tolerance range information, the welding quality assessment information is determined to be qualified quality information; otherwise, the welding quality assessment information is determined to be abnormal quality information.

[0094] Specifically, if the gap baseline information is completely within the weld baseline tolerance range information, it indicates that the specific position of the weld meets expectations and has not deviated from the ideal position. Therefore, the terminal equipment can determine that the welding quality assessment information is qualified quality information. Otherwise, it indicates that the specific position of the weld does not meet expectations and has deviated from the ideal position. Therefore, the terminal equipment can determine that the welding quality assessment information is abnormal quality information.

[0095] The implementation principle of the welding quality assessment method based on welding robots in this application embodiment is as follows: The terminal device can first respond to the welding start command and quickly acquire the gap image information of the target workpiece based on an industrial camera. Then, in response to the welding completion command, it can effectively acquire the weld image information of the target workpiece. Based on the gap image information, it can accurately determine the gap baseline information. At the same time, based on the weld image information, it can accurately determine the weld baseline information. Finally, based on the gap baseline information and the weld baseline information, it can effectively generate welding quality assessment information, thereby accurately judging whether the weld deviates from the ideal position and effectively improving reliability.

[0096] It should be noted that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0097] Embodiments of this application also provide a welding quality assessment system based on a welding robot. For ease of explanation, only the parts relevant to this application are shown, such as... Figure 12 As shown, the system 120 includes:

[0098] Void image information acquisition module 121: In response to the welding start command, it acquires void image information of the target workpiece based on a preset industrial camera;

[0099] Weld seam image information acquisition module 122: used to acquire weld seam image information of the target workpiece in response to the welding completion command;

[0100] Weld reference line information determination module 123: used to determine the gap reference line information based on the gap image information, and to determine the weld reference line information based on the weld image information;

[0101] Welding quality assessment information generation module 124: used to generate welding quality assessment information based on the gap baseline information and weld baseline information.

[0102] Optionally, the above-mentioned weld reference line information determination module 123 includes:

[0103] The gap edge line information generation submodule is used to perform edge detection processing on the gap image information based on a preset edge detection algorithm to generate first gap edge line information and second gap edge line information.

[0104] The gap edge sub-line information generation sub-module is used to divide the first gap edge line information based on a preset division distance value to generate multiple first gap edge sub-line information, and to divide the second gap edge line information based on the division distance value to generate multiple second gap edge sub-line information.

[0105] First Curvature Threshold Information Judgment Submodule: Based on preset curvature threshold information, it sequentially judges whether the curvature between two adjacent first gap edge sub-line information is equal to the curvature threshold information;

[0106] First gap edge combination line information generation submodule: If the curvature between two adjacent first gap edge sub-line information is equal to the curvature threshold information, then merge the two adjacent first gap edge sub-line information to generate first gap edge combination line information;

[0107] The second judgment submodule for curvature threshold information is used to determine, based on curvature threshold information, whether the curvature between two adjacent second gap edge sub-line information is equal to the curvature threshold information.

[0108] The second gap edge combination line information generation submodule is used to merge the two adjacent second gap edge sub-line information if the curvature between two adjacent second gap edge sub-line information is equal to the curvature threshold information, and generate the second gap edge combination line information.

[0109] The gap edge line set information generation submodule is used to group the first gap edge combination line information and the second gap edge combination line information based on the preset spacing information to generate multiple gap edge line set information.

[0110] The gap midpoint information determination submodule is used to determine the gap midpoint information based on the first gap edge line combination information and the second gap edge line combination information for each gap edge line set information.

[0111] Void baseline information generation submodule: used to generate void baseline information based on multiple void midpoint information;

[0112] Weld baseline information determination submodule: used to determine weld baseline information based on weld image information.

[0113] Optionally, the above-mentioned weld baseline information determination submodule includes:

[0114] Weld edge line information generation unit: used to perform edge detection processing on weld image information based on edge detection algorithm, and generate first weld edge line information and second weld edge line information;

[0115] Welding intersection information determination unit: used to determine multiple first welding intersection information based on the first weld edge line information according to the preset target point detection algorithm;

[0116] Shortest distance information generation unit: used to calculate the shortest distance between each first welding intersection information and the second weld edge line information, and generate shortest distance information;

[0117] Shortest distance mean information generation unit: used to generate shortest distance mean information based on multiple shortest distance information;

[0118] Target reference point information determination unit: used to determine the first welding intersection information corresponding to the shortest distance information with the largest number as the target reference point information;

[0119] Benchmark reference point information generation unit: used to generate benchmark reference point information based on target reference point information and half of the average shortest distance information, wherein the distance between the benchmark reference point information and the target reference point information is half of the average shortest distance information;

[0120] Weld reference line information generation unit: used to generate weld reference line information based on multiple reference point information, wherein the weld reference line information overlaps with the multiple reference point information.

[0121] Optionally, the system 120 also includes:

[0122] The weld reference line tolerance range information generation module is used to generate weld reference line tolerance range information based on weld reference line information and preset tolerance distance values. The weld reference line tolerance range information describes the area enclosed by the weld reference line information as the center line and the tolerance distance value as the width on both sides. The length of the weld reference line tolerance range information is the length of the weld reference line information, and the width of the weld reference line tolerance range information is twice the tolerance distance value.

[0123] Optionally, the welding quality assessment information includes qualified quality information and abnormal quality information; the system 120 also includes:

[0124] Void baseline information judgment module: used to determine whether the void baseline information is completely within the weld baseline tolerance range information;

[0125] Welding quality assessment information determination module: If the gap baseline information is completely within the weld baseline tolerance range information, the welding quality assessment information is determined to be qualified quality information; otherwise, the welding quality assessment information is determined to be abnormal quality information.

[0126] It should be noted that the information interaction and execution process between the above modules are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, which will not be repeated here.

[0127] This application also provides a terminal device, such as... Figure 13 As shown, the terminal device 130 of this embodiment includes: a processor 131, a memory 132, and a computer program 133 stored in the memory 132 and executable on the processor 131. When the processor 131 executes the computer program 133, it implements the steps in the above-described embodiment of the welding quality assessment method based on a welding robot, for example... Figure 1 The steps S100 to S400 are shown; or, when the processor 131 executes the computer program 133, it implements the functions of each module in the above-described device, for example... Figure 12 The functions of modules 121 to 124 are shown.

[0128] The terminal device 130 can be a desktop computer, laptop, handheld computer, cloud server, or other computing device. The terminal device 130 includes, but is not limited to, a processor 131 and a memory 132. Those skilled in the art will understand that... Figure 13 This is merely an example of terminal device 130 and does not constitute a limitation on terminal device 130. It may include more or fewer components than shown, or combine certain components, or different components. For example, terminal device 130 may also include input / output devices, network access devices, buses, etc.

[0129] The processor 131 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.; the general-purpose processor can be a microprocessor or any conventional processor, etc.

[0130] The memory 132 can be an internal storage unit of the terminal device 130, such as the hard disk or memory of the terminal device 130. The memory 132 can also be an external storage device of the terminal device 130, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the terminal device 130. Furthermore, the memory 132 can include both internal storage units and external storage devices of the terminal device 130. The memory 132 can also store computer program 133 and other programs and data required by the terminal device 130. The memory 132 can also be used to temporarily store data that has been output or will be output.

[0131] One embodiment of this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium can include any entity or device capable of carrying computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0132] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the methods, principles and structures of this application should be covered within the scope of protection of this application.

Claims

1. A welding quality assessment method based on a welding robot, characterized in that, The method includes: In response to a welding start command, the gap image information of the target workpiece is acquired based on a preset industrial camera, wherein the welding start command is used to instruct the welding robot to start welding according to a preset laser trajectory; In response to the welding completion command, the weld seam image information of the target workpiece is acquired; Based on the void image information, the void baseline information is determined, and based on the weld image information, the weld baseline information is determined. Based on the gap baseline information and weld baseline information, welding quality assessment information is generated; The step of determining the void baseline information based on the void image information and determining the weld baseline information based on the weld image information includes: Based on a preset edge detection algorithm, edge detection processing is performed on the gap image information to generate first gap edge line information and second gap edge line information. Based on a preset division distance value, the edge line information of the first gap is divided to generate multiple first gap edge sub-line information, and based on the division distance value, the edge line information of the second gap is divided to generate multiple second gap edge sub-line information. Based on the preset curvature threshold information, it is sequentially determined whether the curvature between two adjacent first gap edge sub-line information is equal to the curvature threshold information. If the curvature between two adjacent first gap edge sub-line information is equal to the curvature threshold information, then the two adjacent first gap edge sub-line information are merged to generate first gap edge combined line information. Based on the curvature threshold information, it is sequentially determined whether the curvature between two adjacent second gap edge sub-line information is equal to the curvature threshold information; If the curvature between two adjacent second gap edge sub-line information is equal to the curvature threshold information, then the two adjacent second gap edge sub-line information are merged to generate second gap edge combined line information. Based on the preset spacing information, the first gap edge combination line information and the second gap edge combination line information are grouped and processed to generate multiple gap edge line set information. For each set of gap edge lines: determine the gap midpoint information based on the first gap edge combination line information and the second gap edge combination line information; Based on the midpoint information of multiple gaps, generate gap baseline information; Based on the weld image information, the weld baseline information is determined.

2. The method according to claim 1, characterized in that, The step of determining the weld reference line information based on the weld image information includes: Based on the edge detection algorithm, edge detection processing is performed on the weld seam image information to generate first weld seam edge line information and second weld seam edge line information; Based on a preset target point detection algorithm, multiple first welding intersection points are determined according to the first weld edge line information; Calculate the shortest distance between each of the first welding intersection information and the second weld edge line information to generate the shortest distance information; Based on the multiple shortest distance information, generate the mean shortest distance information; The first welding intersection information corresponding to the shortest distance information with the largest number is determined as the target reference point information; Based on the target reference point information and half of the average shortest distance information, a benchmark reference point information is generated, wherein the distance between the benchmark reference point information and the target reference point information is half of the average shortest distance information; Weld reference line information is generated based on multiple reference point information, wherein the weld reference line information overlaps with the multiple reference point information.

3. The method according to claim 1, characterized in that, After determining the gap baseline information based on the gap image information and the weld baseline information based on the weld image information, the method further includes: Based on the weld reference line information and the preset tolerance distance value, weld reference line tolerance range information is generated. The weld reference line tolerance range information describes the area enclosed by the weld reference line information as the center line and the tolerance distance value as the width, expanding outwards to both sides. The length of the weld reference line tolerance range information is the length of the weld reference line information, and the width of the weld reference line tolerance range information is twice the tolerance distance value.

4. The method according to claim 3, characterized in that, The welding quality assessment information includes qualified quality information and abnormal quality information; the generation of welding quality assessment information based on the void baseline information and weld baseline information includes: Determine whether the gap baseline information is completely within the weld baseline tolerance range information; If the gap baseline information is completely within the weld baseline tolerance range information, then the welding quality assessment information is determined to be qualified quality information; otherwise, the welding quality assessment information is determined to be abnormal quality information.

5. A welding quality assessment system based on a welding robot, characterized in that, The system includes: Void image information acquisition module: In response to the welding start command, it acquires void image information of the target workpiece based on a preset industrial camera; Weld seam image information acquisition module: used to acquire weld seam image information of the target workpiece in response to the welding completion command; Weld reference line information determination module: used to determine the gap reference line information based on the gap image information, and to determine the weld reference line information based on the weld image information; Welding quality assessment information generation module: used to generate welding quality assessment information based on the void baseline information and weld baseline information; The weld seam baseline information determination module includes: The gap edge line information generation submodule is used to perform edge detection processing on the gap image information based on a preset edge detection algorithm to generate first gap edge line information and second gap edge line information. The gap edge sub-line information generation sub-module is used to divide the first gap edge line information based on a preset division distance value to generate multiple first gap edge sub-line information, and to divide the second gap edge line information based on the division distance value to generate multiple second gap edge sub-line information. First Curvature Threshold Information Judgment Submodule: Based on preset curvature threshold information, it sequentially judges whether the curvature between two adjacent first gap edge sub-line information is equal to the curvature threshold information; First gap edge combination line information generation submodule: If the curvature between two adjacent first gap edge sub-line information is equal to the curvature threshold information, then merge the two adjacent first gap edge sub-line information to generate first gap edge combination line information. The second judgment submodule for curvature threshold information is used to determine, based on the curvature threshold information, whether the curvature between two adjacent second gap edge sub-line information is equal to the curvature threshold information. The second gap edge combination line information generation submodule is used to merge the two adjacent second gap edge sub-line information if the curvature between two adjacent second gap edge sub-line information is equal to the curvature threshold information, and generate the second gap edge combination line information. The gap edge line set information generation submodule is used to group the first gap edge combination line information and the second gap edge combination line information based on the preset spacing information to generate multiple gap edge line set information. The gap midpoint information determination submodule is used to determine the gap midpoint information based on the first gap edge combination line information and the second gap edge combination line information for each of the gap edge line set information. Void baseline information generation submodule: used to generate void baseline information based on multiple void midpoint information; Weld reference line information determination submodule: used to determine weld reference line information based on the weld image information.

6. The system according to claim 5, characterized in that, The system also includes: Weld reference line tolerance range information generation module: used to generate weld reference line tolerance range information based on the weld reference line information and a preset tolerance distance value. The weld reference line tolerance range information describes the area enclosed by the weld reference line information as the center line and the tolerance distance value as the width on both sides. The length of the weld reference line tolerance range information is the length of the weld reference line information, and the width of the weld reference line tolerance range information is twice the tolerance distance value.

7. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 4.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 4.

Images