Weld defect detection method, device, system and medium

Abstract

The invention relates to a welding seam defect detection method, a welding seam defect detection device, a welding seam defect detection system and a computer readable storage medium. The welding seam defect detection method comprises the following steps: acquiring a defect picture with a laser mark of a to-be-detected welding seam defect; and determining the type and size of the weld defect to be detected by using a first model according to the defect picture with the laser mark.

Description

Technical Field

[0001] The present disclosure relates to the technical field of weld appearance detection, and in particular to a weld defect detection method, a weld defect detection device, a weld defect detection system and a computer-readable storage medium. Background Art

[0002] Enterprises involved in steel structure welding and manufacturing must attach great importance to weld appearance inspection technology to provide the most basic guarantee for the overall performance and safety of welded structures. In the field of welding inspection technology, there are four major welding inspection methods, including UT (ultrasonic inspection), RT (radiograph), MT (magnetic particle inspection), and VT (visual inspection). Among them, VT has the widest application range, the most direct application method, and the best application effect. In the process of establishing a welding quality system based on ISO3834-2, it is generally required that the number of certified VT inspectors is at least 4, which is twice that of other inspection methods.

[0003] There are many problems in the practical application of the weld appearance defect detection method in the related technology. For example, the traditional weld appearance defect detection mainly relies on the visual inspection of the inspector, and the detection results of this method are easily affected by the subjectivity of the inspector. Different inspectors may have different defect recognition results for the same weld due to differences in experience, vision, attention and other factors, resulting in missed detection or false detection; the process of manual detection of weld appearance defects is time-consuming, especially in large-scale production or large-scale welding projects, the number of welds to be detected is huge, and the efficiency of manual detection is far from meeting the requirements of production progress; inspectors who conduct weld appearance defect detection need to undergo professional training, including but not limited to professional knowledge in welding technology, materials science, defect identification, and the operation skills of detection tools. This training is not only time-consuming, but also costly. In addition, due to the lack of professional talents, enterprises face great challenges in recruiting and maintaining certified inspection personnel. These problems limit the efficiency and effectiveness of weld quality inspection. Summary of the invention

[0004] In view of this, the embodiments of the present disclosure provide a weld defect detection method, a weld defect detection device, a weld defect detection system and a computer-readable storage medium, which help to improve the efficiency of weld appearance detection.

[0005] In one aspect of the present disclosure, a weld defect detection method is provided, comprising:

[0006] Obtain a laser-marked defect image of the weld defect to be detected;

[0007] Based on the defect picture with laser marking, the first model is used to determine the type and size of the weld defect to be detected.

[0008] In some embodiments, the weld defect detection method further includes:

[0009] Obtaining a first image sample, a weld defect type in the first image sample, and reference information for calculating a size of the weld defect in the first image sample;

[0010] Training a first model by using the first image sample, the type of weld defect in the first image sample, and the size of the weld defect in the first image sample to calculate reference information;

[0011] The first image sample includes a weld defect image with laser marking.

[0012] In some embodiments, obtaining the first image sample, the type of weld defect in the first image sample, and the reference information for calculating the size of the weld defect in the first image sample includes:

[0013] Obtain a second image sample;

[0014] Adding a plurality of parallel and equidistantly arranged laser scale lines to the second image sample to form a first image sample;

[0015] The endpoints of each laser scale line, the weld defect type and the endpoints of the weld defect in the first image sample are marked in the first image sample.

[0016] In some embodiments, obtaining the first image sample, the type of weld defect in the first image sample, and the reference information for calculating the size of the weld defect in the first image sample includes:

[0017] Obtaining the pixel spacing between two adjacent laser scale lines in the first image sample and the pixel spacing between two end points of each weld defect;

[0018] The actual size of the weld defect is obtained according to the numerical relationship between the pixel spacing between two adjacent laser scale lines in the first image sample and the pixel spacing between two end points of each weld defect and the actual spacing between two adjacent laser scale lines.

[0019] In some embodiments, the operation of obtaining the second image sample specifically includes:

[0020] Get an initial sample of images of weld defects;

[0021] Generate a second picture sample using a second model according to the initial picture sample;

[0022] Among them, the sample quantity of the initial image sample of the weld defect is less than the sample quantity of the second image sample.

[0023] In another aspect of the present disclosure, a weld defect detection device is provided, comprising:

[0024] Memory; and

[0025] A processor coupled to the memory executes the weld defect detection method of any of the above embodiments.

[0026] In another aspect of the present disclosure, a weld defect detection system is provided, comprising:

[0027] Mounting body;

[0028] A detection component is arranged on the mounting body, and the detection component comprises: a laser marking emitter and an image acquisition unit, wherein the laser marking emitter is configured to emit a laser mark around the weld defect, and the image acquisition unit is configured to acquire an image of the weld defect with the laser mark;

[0029] As in the weld defect detection device of the above embodiment, the processor is signal-connected to the image acquisition unit and the laser marking transmitter;

[0030] The laser marking includes a plurality of parallel and equidistant laser scale lines.

[0031] In some embodiments, the detection assembly is rotatable relative to the mounting body;

[0032] The detection components also include:

[0033] The laser rangefinders are symmetrically arranged on both sides of the laser marking transmitter and are configured to respectively obtain the distances to the weld defects;

[0034] The processor is connected to the laser rangefinder signal and is configured to adjust the angle of the detection component relative to the mounting body according to the distance information respectively obtained by the two laser rangefinders, so that the laser marking transmitter emits a vertical laser mark around the weld defect.

[0035] In another aspect of the present disclosure, a weld defect detection device is provided, comprising:

[0036] An image acquisition module is configured to acquire a defect image with a laser mark of the weld to be inspected;

[0037] The defect detection module is configured to determine the type and size of the weld to be detected based on the defect image with the laser mark using the first model.

[0038] In another aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the weld defect detection method of any of the above embodiments is implemented.

[0039] Therefore, according to the embodiment of the present disclosure, the first model can identify information such as the type and size of weld appearance defects based on photos of weld defects, thereby improving the efficiency of weld appearance inspection, realizing the automation and intelligence of the entire process of weld appearance inspection, and helping to enhance the accuracy of weld appearance inspection. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings, which constitute a part of the specification, illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0041] The present disclosure may be more clearly understood from the following detailed description with reference to the accompanying drawings, in which:

[0042] Figure 1 is a flow chart of some embodiments of the weld defect detection method according to the present disclosure;

[0043] Figure 2 is a schematic diagram of a defect picture with laser marking according to some embodiments of the weld defect detection method disclosed herein;

[0044] Figure 3 It is a schematic diagram of obtaining the type and size of weld defects based on weld defect images according to some embodiments of the weld defect detection method disclosed in the present invention;

[0045] Figure 4 is a schematic structural diagram of some embodiments of the weld defect detection system disclosed in the present invention;

[0046] Figure 5 It is a schematic diagram of the connection relationship of some embodiments of the weld defect detection system disclosed in the present invention.

[0047] In the figure:

[0048] 1. Processor; 2. Mounting body; 3. Detection component; 31. Laser marking transmitter; 32. Image acquisition unit; 33. Laser rangefinder.

[0049] It should be understood that the size of each part shown in the accompanying drawings is not drawn according to the actual proportional relationship. In addition, the same or similar reference numerals represent the same or similar components. DETAILED DESCRIPTION

[0050] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. The description of the exemplary embodiments is merely illustrative and is in no way intended to limit the present disclosure and its application or use. The present disclosure can be implemented in many different forms and is not limited to the embodiments described herein. These embodiments are provided to make the present disclosure thorough and complete and to fully express the scope of the present disclosure to those skilled in the art. It should be noted that unless otherwise specifically stated, the relative arrangement of the components and steps, the composition of the materials, the numerical expressions and the numerical values ​​set forth in these embodiments should be interpreted as being merely exemplary and not as limiting.

[0051] The words "first", "second" and similar words used in this disclosure do not indicate any order, quantity or importance, but are only used to distinguish different parts. The words "include" or "comprise" and similar words mean that the elements before the word include the elements listed after the word, and do not exclude the possibility of including other elements. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0052] In the present disclosure, when a specific device is described as being located between a first device and a second device, there may or may not be an intermediate device between the specific device and the first device or the second device. When a specific device is described as being connected to other devices, the specific device may be directly connected to the other device without an intermediate device, or may not be directly connected to the other device but have an intermediate device.

[0053] All terms (including technical terms or scientific terms) used in the present disclosure have the same meanings as those understood by ordinary technicians in the field to which the present disclosure belongs, unless otherwise specifically defined. It should also be understood that terms defined in general dictionaries, such as general dictionaries, should be interpreted as having meanings consistent with their meanings in the context of the relevant technology, and should not be interpreted in an idealized or extremely formal sense, unless explicitly defined herein.

[0054] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0055] Enterprises involved in steel structure welding and manufacturing must attach great importance to weld appearance inspection technology to provide the most basic guarantee for the overall performance and safety of welded structures. In the field of welding inspection technology, there are four major welding inspection methods, including UT (ultrasonic inspection), RT (radiograph), MT (magnetic particle inspection), and VT (visual inspection). Among them, VT has the widest application range, the most direct application method, and the best application effect. In the process of establishing a welding quality system based on ISO3834-2, it is generally required that the number of certified VT inspectors is at least 4, which is twice that of other inspection methods.

[0056] There are many problems in the practical application of the weld appearance defect detection method in the related art, such as:

[0057] Subjectivity of test results: Traditional weld appearance defect detection mainly relies on visual inspection by inspectors. The test results of this method are easily affected by the subjectivity of inspectors. Different inspectors may have different defect recognition results for the same weld due to differences in experience, vision, attention, etc., which may lead to missed detection or false detection.

[0058] Low detection efficiency: The process of manual inspection of weld appearance defects takes a long time, especially in large-scale production or large welding projects, where the number of welds that need to be inspected is huge, and the efficiency of manual inspection is far from meeting the requirements of production progress;

[0059] High cost of personnel training: Inspectors who conduct weld appearance defect inspections need to undergo professional training, including but not limited to professional knowledge in welding technology, materials science, defect identification, and the operation skills of inspection tools. This type of training is not only time-consuming but also costly. In addition, due to the lack of professional talents, companies face great challenges in recruiting and maintaining certified inspection personnel.

[0060] These problems limit the efficiency and effectiveness of weld quality inspection. In recent years, many automated appearance defect detection methods have emerged, mainly including contour detection methods based on line lasers and target detection methods based on pure vision.

[0061] Practical applications have found that line laser scanning systems usually require more complex hardware configurations, including laser marker transmitters, optical lenses, CCD cameras, etc. The detection range is relatively narrow and is not suitable for large-size weld detection of large structural parts. It is not effective for detecting certain types of defects, for example, it is difficult to detect small cracks.

[0062] Therefore, the contour detection method based on line laser has the problems of "large equipment size, high cost, and narrow detection range", which results in the equipment being large in size and relatively high in cost and cannot be applied to large-size weld detection of large structural parts.

[0063] The target detection method based on pure vision still requires human intervention in precise dimensional measurement and quality grade evaluation, which limits the improvement of its automation level and cannot effectively improve the efficiency of weld appearance inspection.

[0064] In view of this, in one aspect of an embodiment of the present disclosure, a weld defect detection method is provided to help improve the efficiency of weld appearance detection.

[0065] Figure 1 is a flow chart of some embodiments of the weld defect detection method disclosed in the present invention, Figure 2 is a schematic diagram of a defect picture with laser marking according to some embodiments of the weld defect detection method disclosed in the present invention, Figure 3 is a schematic diagram of obtaining the type and size of weld defects based on weld defect images according to some embodiments of the weld defect detection method disclosed in the present invention, Figure 2 A in the equation is the weld defect. Figure 2 B in the figure is laser marking, see Figure 1~Figure 3 , a weld defect detection method includes steps S1 to S2.

[0066] In step S1, a defect image with a laser mark of the weld defect to be detected is obtained. Obtaining a defect image with a laser mark of the weld defect to be detected includes but is not limited to emitting a laser mark B around the weld defect A by a laser mark emitter 31, taking a weld image on site, and including the weld defect A and the laser mark B around it in one image.

[0067] In step S2, the type and size of the weld defect to be detected are determined using the first model based on the defect image with laser marking. The type and size of the defect can be obtained based on the defect image with laser marking taken using the first model. The first model includes but is not limited to a weld appearance defect recognition model.

[0068] The size of a weld defect includes, but is not limited to, the distance between the two ends of a weld defect or the distance between the starting position and the end position of a weld defect. Weld defects include, but are not limited to, appearance defects such as cracks, pores, and slag inclusions.

[0069] In this embodiment, the first model can identify information such as the type and size of weld appearance defects based on photos of weld defects, thereby improving the efficiency of weld appearance inspection, realizing automation and intelligence of the entire process of weld appearance inspection, and helping to enhance the accuracy of weld appearance inspection.

[0070] refer to Figure 1~Figure 3 In some embodiments, the weld defect detection method further includes: step S3 to step S4.

[0071] In step S3, a first image sample, a weld defect type in the first image sample, and reference information for calculating the size of the weld defect in the first image sample are obtained. The source of the first image sample includes, but is not limited to, weld appearance defect photos collected online, weld appearance defect photos taken on site, weld appearance defect photos and / or videos obtained by a weld defect detection system in the early stage, etc. If it is a video, frames are extracted at fixed intervals.

[0072] In step S4, the first model is trained using the first image sample, the type of weld defect in the first image sample, and the size of the weld defect in the first image sample. The method of training the first model includes but is not limited to deep learning training based on a convolutional neural network.

[0073] The first image sample includes images of weld defects with laser markings, such as Figure 2 As shown in the photo, the laser mark on the first image sample simulates the image formed by the laser mark transmitter 31 projected onto the workpiece surface. The weld defect type and weld defect size calculation reference information in the first image sample includes but is not limited to being added to the first image sample in response to user input.

[0074] In this embodiment, the first model is trained by calculating reference information based on the first image sample, the type of weld defects in the first image sample, and the size of the weld defects in the first image sample, so that the first model can identify the size and type of defects in the image based on the image of the weld appearance defect, which helps to achieve accurate and efficient weld appearance detection.

[0075] refer to Figure 2 and Figure 3 In some embodiments, obtaining a first image sample, a weld defect type in the first image sample, and reference information for calculating the size of the weld defect in the first image sample includes: obtaining a second image sample; adding a plurality of parallel and equidistant laser scale lines in the second image sample to form a first image sample; marking the endpoints of each laser scale line, the weld defect type in the first image sample, and the endpoints of the weld defect in the first image sample, and the endpoints of the weld defect are used as reference points for calculating the weld size.

[0076] In response to the user's input, a laser mark is added to the second image sample. The laser mark includes but is not limited to a plurality of parallel and equidistantly spaced laser scale lines. The laser mark is used to compare with the weld defect size in the first image sample to obtain defect size calculation reference information, and then obtain the actual size of the weld defect according to the defect size calculation reference information and the actual distance between the laser scale lines.

[0077] The endpoints of the laser scale lines include, but are not limited to, adding Figure 3 C in Figure 3 The green “+” symbol in the middle. Types of weld defects include but are not limited to those marked as Figure 3 D in Figure 3 The word "Crack" is shown in red and the word "Hole" is shown in blue.

[0078] End points of weld defects include but are not limited to those marked as Figure 3 The E in Figure 3 The two red "+" symbols and the blue "+" symbols are respectively set at the two end points of the crack marked as "Crack", and the two end points of the crack include but are not limited to the starting point and the end point of the crack marked along the extension direction of the crack. The two blue "+" symbols are respectively set at the two end points marked as "Hole", and the two end points of the pore include but are not limited to the edge of the pore marked along the direction of the longest pore diameter.

[0079] In this embodiment, the pixel size of the weld defect in the first image sample is obtained by marking the endpoints of the weld in the first image sample, and the pixel size between the laser scale lines is obtained by marking the endpoints of each laser scale line, so that the size information of the weld defect in the image can be quantified, so as to achieve quantitative detection of the weld defect. The size reference point and laser scale line of the weld defect are introduced into the annotation and model training of the data set, so that the laser marking feature points and the start and end points of the defect can be identified while the defect is identified, so as to obtain the real size of the defect through pixel comparison.

[0080] refer to Figure 2 and Figure 3 In some embodiments, obtaining the first image sample, the type of weld defect in the first image sample, and the reference information for calculating the size of the weld defect in the first image sample includes: obtaining the pixel spacing between two adjacent laser scale lines in the first image sample and the pixel spacing between two endpoints of each weld defect; obtaining the actual size of the weld defect based on the numerical relationship between the pixel spacing between two adjacent laser scale lines in the first image sample and the pixel spacing between two endpoints of each weld defect and the actual spacing between two adjacent laser scale lines.

[0081] The pixel spacing between two adjacent laser scale lines includes, but is not limited to, calculating the pixels between the ends of all two adjacent scale lines in the laser scale mark and taking an average value to obtain more accurate pixel spacing data of the laser scale lines.

[0082] In this embodiment, since the spacing of the scale lines emitted by the laser marking emitter around the weld defect is a constant and will not change due to the distance between the laser marking emitter and the weld defect, the actual size of the weld defect can be obtained through the numerical relationship between the pixel size of the weld defect in the first image sample and the pixel spacing of the laser scale lines and the actual spacing of the laser scale lines.

[0083] In some embodiments, the operation of obtaining the second image sample specifically includes: obtaining an initial image sample of the weld defect; generating a second image sample based on the initial image sample using a second model; wherein the sample number of the initial image sample of the weld defect is less than the sample number of the second image sample.

[0084] The initial image samples of weld defects include but are not limited to photos of weld appearance defects collected online, photos of weld appearance defects taken on site, photos and / or videos of weld appearance defects obtained in the early stage through a weld defect detection system, etc. If it is a video, frames are extracted at fixed intervals.

[0085] The second model includes but is not limited to a weld appearance defect model, which is obtained by fine-tuning training based on a diffusion model, a generative adversarial network (GAN) or a self-attention model (transformer).

[0086] The second model can expand the photos of weld appearance defects based on the initial image sample through reasonable prompt words to obtain more photos of weld appearance defects. The same type of weld appearance defects in the second image sample can have multiple pictures with different morphological structures. For example, input words such as carbon steel, arc crater crack, and dispersed shape, and / or words such as aluminum alloy, surface, and diffuse pores to expand the data set.

[0087] In this embodiment, based on the initial image samples, the second model can expand the types of weld defects in the samples so that the first model can be trained based on richer samples, thereby being able to identify more diverse weld defects and obtain more accurate recognition results.

[0088] refer to Figure 1~Figure 3 In some embodiments, the method for establishing the first model specifically includes:

[0089] Collect photos of weld appearance defects, including pictures from the Internet, defect photos taken on site, and photos and videos taken by the previous weld defect detection system. If it is a video, extract frames at fixed intervals;

[0090] Fine-tune the training based on the diffusion model to obtain a second model dedicated to the welding vertical field, and expand the photos of weld appearance defects through reasonable prompt words;

[0091] All images are reviewed for rationality, and if qualified, a mark is added to the image, where the added mark is an image formed by the laser marking transmitter 31 projected onto the workpiece surface;

[0092] Manually annotate the images. The contents to be annotated include: weld defect type, defect size calculation reference point, and end point of each scale line on the laser mark, which are packaged into one piece of data;

[0093] Based on the convolutional neural network, deep learning training was carried out to obtain the first model.

[0094] In addition, the recognition results of the first model are processed to calculate the defect size. The pixels between the reference points are calculated, and the pixels between all two adjacent end points in the mark are calculated and averaged. After comparing the two, the actual size of the defect is obtained according to the actual spacing of the laser scale lines. The first model and the recognition result processing algorithm of the first model are packaged as a defect recognition measurement tool, and the confidence of defect recognition can also be obtained in combination with real measurement data.

[0095] The workflow is compiled, including obtaining laser-marked defect images of the weld defects to be detected from the image acquisition unit 32, using defect recognition and measurement tools to perform recognition and measurement, summarizing the detection results, and compiling a detection report, which can eventually form a complete weld appearance defect detection intelligent agent application.

[0096] The weld defect detection method can be implemented based on an intelligent agent application. The image acquisition unit 32 scans and photographs the weld defects during movement, and transmits the video information stream to the intelligent agent application deployed on the computer. The intelligent agent application mainly includes weld appearance defect recognition measurement tools and workflow arrangement. The intelligent agent will summarize information and compile inspection reports based on the measurement results, thereby greatly improving the efficiency and accuracy of weld appearance inspection and effectively avoiding the adverse effects of problematic structural parts on subsequent production and use.

[0097] In another aspect of the embodiments of the present disclosure, a weld defect detection device is provided, comprising: a memory and a processor 1 coupled to the memory, wherein the processor 1 executes a weld defect detection method as described in any of the above embodiments.

[0098] The processor 1 described herein may include a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. The general-purpose processor 1 may be a microprocessor, but in an alternative, the processor 1 may be any conventional processor, controller, microcontroller, or state machine. The processor 1 may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors cooperating with a DSP core, or any other such configuration.

[0099] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by the processor 1, or in a combination of the two. The software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0100] Figure 4 is a schematic diagram of the structure of some embodiments of the weld defect detection system disclosed in the present invention, Figure 5 is a schematic diagram of the connection relationship of some embodiments of the weld defect detection system disclosed in the present invention, with reference to Figure 4 and Figure 5 In another aspect of the embodiments of the present disclosure, a weld defect detection system is provided, comprising a mounting body 2, a detection component 3 and a weld defect detection device as described in the above embodiments.

[0101] The detection component 3 is arranged on the mounting body 2, and the mounting body 2 can be connected to the end picker. The detection component 3 includes a laser marking emitter 31 and an image acquisition unit 32. The laser marking emitter 31 is configured to emit a laser mark around the weld defect, and the image acquisition unit 32 is configured to obtain an image of the weld defect with the laser mark.

[0102] The processor 1 is signal-connected to the image acquisition unit 32 and the laser marking transmitter 31. The laser marking includes a plurality of parallel and equidistant laser scale lines, the intervals of the laser scale lines can be adjusted by an internal lens, and there are at least 20 laser scale lines. The image acquisition unit 32 includes but is not limited to a camera.

[0103] In this embodiment, the weld defect detection system emits equally spaced and parallel laser beams on the surface of the workpiece through the laser marking emitter 31, and takes pictures of the weld appearance defects with laser markings through the image acquisition unit 32. Based on the pictures of the weld appearance defects with laser markings, the weld defect detection device can obtain information such as the type and size of the weld appearance defects, thereby realizing quantitative detection of weld appearance defects, effectively improving detection efficiency and detection accuracy, and realizing efficient and automated detection of weld appearance defects.

[0104] refer to Figure 4 In some embodiments, the detection assembly 3 can rotate relative to the mounting body 2. The detection assembly 3 further includes a laser rangefinder 33, which is symmetrically arranged on both sides of the laser marking emitter 31 and is configured to obtain the distance to the weld defect.

[0105] The processor 1 is connected to the laser rangefinder 33 by signal, and is configured to adjust the angle of the detection component 3 relative to the mounting body 2 according to the distance information respectively obtained by the two laser rangefinders 33, so that the laser marking emitter 31 emits a vertical laser mark around the weld defect.

[0106] The mounting body 2 includes but is not limited to a cubic shape, the detection component 3 includes but is not limited to a cylindrical shape, and the detection component 3 can rotate around its own axis relative to the mounting body 2. The laser rangefinder 33, the image acquisition unit 32 and the laser marking transmitter 31 are arranged on the end surface of the detection component 3.

[0107] The two laser rangefinders 33 are symmetrically distributed relative to a vertical axis passing through the center of the detection component 3 , and the image acquisition unit 32 and the laser marking transmitter 31 are arranged on the vertical axis passing through the center of the detection component 3 .

[0108] In this embodiment, during the image acquisition of the weld appearance defect, two laser rangefinders 33 are used to simultaneously measure the distance to the workpiece. When the difference between the two is greater than a preset value, it indicates that the current mounting body 2 is skewed. The processor 1 rotates the mounting body 2 until the difference between the distances measured by the two laser rangefinders 33 to the workpiece is less than a preset value, so that the laser mark emitted by the laser mark emitter 31 to the periphery of the weld defect is vertical. The preset value can be selected as 2 mm.

[0109] The automated inspection process based on the weld defect inspection system does not require manual intervention. The inspection hardware is compact and simple, which can improve the inspection speed. Especially in large-scale production, it can effectively shorten the inspection cycle and improve production efficiency. By using laser marking, the system can accurately measure the size of the defect, providing important data support for subsequent defect analysis and processing.

[0110] refer to Figure 2~Figure 5In some embodiments, the steps of using a weld defect detection system to detect weld appearance defects include:

[0111] First, the mounting body 2 is mounted on the robot end shaft, and the detection component 3 communicates with the processor 1;

[0112] Place a ruler with a scale at a distance of about 20 cm from the end face of the image acquisition unit 32, adjust the interval of the laser scale lines emitted by the laser marking emitter 31, ensure that all laser scale lines are within the picture taken by the image acquisition unit 32, and ensure that the laser scale lines completely overlap with the scale lines of the ruler, so that the spacing of the laser scale lines is consistent with the actual value to improve the accuracy of laser marking. The spacing between adjacent laser scale lines is selected according to the actual situation, which can be 1mm or 5mm;

[0113] Move the detection component 3 to a space range of 10cm to 40cm from the weld surface to avoid the laser mark becoming thicker due to the large distance, which affects the accuracy. The laser mark emitter 31, the image acquisition unit 32 and the laser rangefinder 33 are facing the weld. After the detection starts, the two laser rangefinders 33 measure the distance to the workpiece at the same time. When the difference between the two is greater than the preset value, it indicates that the installation body 2 is currently skewed. The installation body 2 is rotated until the difference between the distances measured by the two laser rangefinders 33 to the workpiece is less than the preset value, so that the laser mark emitted by the laser mark emitter 31 to the surrounding of the weld defect is vertical to calibrate the accuracy;

[0114] When the detection component 3 moves along the direction of the weld, the weld defect detection device will be directly called after the obtained image information flow, and then the obtained detection results will be summarized and the information will be deduplicated. When all welds are inspected, the large language model will be called to compile the detection report based on the final measurement results.

[0115] In another aspect of the embodiments of the present disclosure, a weld defect detection device is provided, comprising an image acquisition module and a defect detection module. The image acquisition module is configured to acquire a defect image with a laser mark of a weld to be detected, and the defect detection module is configured to determine the type and size of the weld to be detected based on the defect image with the laser mark using a first model.

[0116] In this embodiment, the defect detection module can identify information such as the type and size of the weld appearance defects based on the photos of the weld defects obtained by the image acquisition module, thereby improving the efficiency of weld appearance detection, realizing the automation and intelligence of the entire process of weld appearance detection, and helping to enhance the accuracy of weld appearance detection.

[0117] In another aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by the processor 1, the weld defect detection method of any of the above embodiments is implemented.

[0118] In one or more exemplary embodiments, the functions described may be implemented in hardware, software, firmware, or any combination thereof. If implemented as a computer program product in software, each function may be stored on or transmitted by means of a computer-readable medium as one or more instructions or codes. Computer-readable media include both computer storage media and communication media, including any medium that facilitates the transfer of a computer program from one place to another. Storage media may be any available medium that can be accessed by a computer. As an example and not limitation, such a computer-readable medium may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, disk storage or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer. Any connection is also properly referred to as a computer-readable medium. For example, if the software is transmitted from a website, server, or other remote source using a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwaves, the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwaves are included in the definition of the medium. Disk and disc as used herein include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk and Blu-ray disc, where disks usually reproduce data magnetically, while discs reproduce data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0119] So far, various embodiments of the present disclosure have been described in detail. In order to avoid obscuring the concept of the present disclosure, some details known in the art are not described. Based on the above description, those skilled in the art can fully understand how to implement the technical solution disclosed here.

[0120] Although some specific embodiments of the present disclosure have been described in detail by way of examples, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. It should be understood by those skilled in the art that the above embodiments may be modified or some technical features may be replaced by equivalents without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A weld defect detection method, characterized in that: include: Obtain a laser-marked defect image of the weld defect to be detected; According to the defect picture with laser marking, the type and size of the weld defect to be detected are determined using the first model.

2. The weld defect detection method according to claim 1, characterized in that: Also includes: Acquire a first image sample, a type of weld defect in the first image sample, and reference information for calculating a size of the weld defect in the first image sample; Calculating reference information using the first image sample, the type of weld defect in the first image sample, and the size of the weld defect in the first image sample to train the first model; The first image sample includes a weld defect image with laser marking.

3. The weld defect detection method according to claim 2, characterized in that: Acquiring the first image sample, the type of weld defect in the first image sample, and reference information for calculating the size of the weld defect in the first image sample includes: Obtain a second image sample; Adding a plurality of parallel and equidistantly arranged laser scale lines to the second image sample to form the first image sample; The endpoints of each of the laser graticule lines, the weld defect type in the first image sample, and the endpoints of the weld defects are marked in the first image sample.

4. The weld defect detection method according to claim 3, characterized in that: Acquiring the first image sample, the type of weld defect in the first image sample, and reference information for calculating the size of the weld defect in the first image sample includes: Obtaining the pixel spacing between two adjacent laser graticule lines and the pixel spacing between two end points of each weld defect in the first image sample; The actual size of the weld defect is obtained according to the numerical relationship between the pixel spacing between two adjacent laser graticule lines in the first image sample and the pixel spacing between the two end points of each weld defect and the actual spacing between two adjacent laser graticule lines.

5. The weld defect detection method according to claim 3, characterized in that: The operation of obtaining the second image sample specifically includes: Get an initial sample of images of weld defects; Generate the second picture sample using the second model according to the initial picture sample; The number of samples of the initial image samples of the weld defects is less than the number of samples of the second image samples.

6. A weld defect detection device, characterized in that: include: Memory; and A processor (1) coupled to the memory, the processor (1) executing the weld defect detection method according to any one of claims 1 to 5.

7. A weld defect detection system, characterized in that: include: Mounting body (2); A detection component (3) is arranged on the mounting body (2), the detection component (3) comprising: a laser marking emitter (31) and an image acquisition unit (32), the laser marking emitter (31) being configured to emit a laser mark around the weld defect, and the image acquisition unit (32) being configured to acquire an image of the weld defect with the laser mark; The weld defect detection device according to claim 6, wherein the processor (1) is signal-connected to both the image acquisition unit (32) and the laser marking transmitter (31); Wherein, the laser mark includes a plurality of parallel and equidistant laser scale lines.

8. The weld defect detection system according to claim 7, characterized in that: The detection component (3) is capable of rotating relative to the mounting body (2); Wherein, the detection component (3) further comprises: Laser rangefinders (33) are symmetrically arranged on both sides of the laser marking transmitter (31) and are configured to respectively obtain distances to the weld defects; The processor (1) is connected to the laser rangefinder (33) by signal, and is configured to adjust the angle of the detection component (3) relative to the mounting body (2) according to the distance information respectively acquired by the two laser rangefinders (33), so that the laser marking emitter (31) emits a vertical laser mark around the weld defect.

9. A weld defect detection device, characterized in that: include: An image acquisition module is configured to acquire a defect image with a laser mark of the weld to be inspected; The defect detection module is configured to determine the type and size of the weld to be detected by using a first model based on the defect image with the laser mark.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, wherein when the program is executed by a processor (1), the weld defect detection method according to any one of claims 1 to 5 is implemented.

Images