Welding parameter adjustment method and device, storage medium, and electronic device

Abstract

The present invention provides a method and device for adjusting welding parameters, a storage medium, and an electronic device. The method comprises: after welding a target workpiece with welding equipment, obtaining a weld image of the interior of the weld seam of the target workpiece detected by an X-ray device; preprocessing the weld image to obtain a region of interest in the weld image; extracting fused features of the region of interest, wherein the fused features include geometric features, texture features, and deep learning features; inputting the fused features into a pretrained convolutional neural network (CNN) classifier to output welding defect information of the weld image, wherein the welding defect information includes the defect category and its confidence level; and adjusting the operating parameters of the welding equipment based on the welding defect information. This method solves the low technical problem of manual adjustment of welding equipment in related technologies, improves the automation and intelligence of welding production, reduces reliance on manual machine adjustment, and improves the production efficiency and product yield of workpiece welding.

Description

Technical Field

[0001] The present invention relates to the field of industrial control technology, and in particular to a method and device for adjusting welding parameters, a storage medium, and an electronic device. Background Art

[0002] Robotic welders are widely used in container production, but they often present internal weld quality issues. Currently, experienced companies often perform on-site adjustments to improve weld quality, adjusting parameters such as current, wire speed, and fixtures. However, this approach can be time-consuming, allowing some internal defects to go undetected. By the time engineers discover a problem, a significant number of defective products have already been produced, leading to the potential for defective products to enter the market.

[0003] For the above-mentioned problems existing in related technologies, no efficient and accurate solutions have been found yet. Summary of the Invention

[0004] The present invention provides a welding parameter adjustment method and device, a storage medium, and an electronic device to solve the above-mentioned technical problems existing in the related art.

[0005] According to one embodiment of the present invention, a method for adjusting welding parameters is provided, comprising: after welding of a target workpiece by a welding device is completed, obtaining a weld image of the inside of the weld of the target workpiece detected by an X-ray device; preprocessing the weld image to obtain a region of interest of the weld image; extracting fusion features of the region of interest, wherein the fusion features include geometric features, texture features, and deep learning features; inputting the fusion features into a pre-trained convolutional neural network (CNN) classifier, and outputting welding defect information of the weld image, wherein the welding defect information includes a defect category and its confidence level; and adjusting the working parameters of the welding equipment according to the welding defect information.

[0006] Optionally, before obtaining the weld image inside the weld of the target workpiece detected by the X-ray device, the method further includes: obtaining a weld spot image outside the weld of the target workpiece captured by a camera; judging whether the target workpiece has a welding defect based on the weld spot image; if the target workpiece has a welding defect, determining to obtain the weld image inside the weld of the target workpiece detected by the X-ray device.

[0007] Optionally, extracting the fusion features of the region of interest includes: detecting pores, cracks, and the covering area between the weld material and the base material in the region of interest; extracting the circularity of the pores and the linear length of the cracks, calculating the roughness of the covering area through a gray-level co-occurrence matrix, and extracting deep learning features of the region of interest using a deep residual network, wherein the geometric features include the circularity and the linear length, and the texture features include the roughness.

[0008] Optionally, calculating the roughness of the coverage area through the grayscale co-occurrence matrix includes: using a window of preset size to slide from the starting position to the ending position of the coverage area, and calculating the occurrence frequency of grayscale difference combinations of all pixel pairs in the window at each sliding position, wherein the grayscale difference combination is a pixel pair with different grayscale values; storing the occurrence frequency of all windows in a matrix to obtain a grayscale co-occurrence matrix; using the grayscale co-occurrence matrix to calculate the contrast intensity of the grayscale values ​​in the coverage area; converting the contrast intensity into the roughness of the coverage area, wherein the contrast intensity is positively correlated with the roughness.

[0009] Optionally, adjusting the operating parameters of the welding equipment according to the welding defect information includes: parsing the defect category and defect severity of the welding defect information; searching for first and second operating parameters of the welding equipment that match the defect category, and searching for first and second adjustment amounts that match the defect severity; adjusting the first operating parameter of the welding equipment based on the first adjustment amount, and adjusting the second operating parameter of the welding equipment based on the second adjustment amount.

[0010] Optionally, searching for the first working parameter and the second working parameter of the welding equipment that match the defect category includes: if the defect category is internal porosity, determining that the first working parameter of the welding equipment is the welding current and the shielding gas flow rate, and the second working parameter is the welding line speed and the welding material preheating temperature; if the defect category is internal cracks, determining that the first working parameter of the welding equipment is the welding material preheating temperature and the welding line speed, and the second working parameter is the weld interlayer temperature and the clamp tightness; if the defect category is lack of fusion, determining that the first working parameter of the welding equipment is the welding current and the welding angle, and the second working parameter is the welding line speed and the shielding gas flow rate; if the defect category is incomplete penetration, determining that the first working parameter of the welding equipment is the welding current and welding time, and the second working parameter is the welding line speed; if the defect category is welding inclusions, determining that the first working parameter of the welding equipment is the welding line speed and slag cleaning frequency, and the second working parameter is the shielding gas purity and arc voltage.

[0011] Optionally, adjusting the first operating parameter of the welding equipment based on the first adjustment amount, and adjusting the second operating parameter of the welding equipment based on the second adjustment amount include: adjusting the first operating parameter of the welding equipment based on the first adjustment amount; obtaining a test image obtained by welding a test workpiece after the adjustment of the welding equipment is completed; judging whether there is test defect information in the test image, wherein the test defect information at least includes the welding defect information; if there is test defect information in the test image, continuing to adjust the second operating parameter of the welding equipment based on the second adjustment amount.

[0012] According to another embodiment of the present invention, a device for adjusting welding parameters is provided, including: a first acquisition module, used to acquire defect description text, a defect mask, and noise parameters, wherein the defect description text is used to characterize the position, size, and defect category of the defect image to be generated; an encoding module, used to encode the defect description text using a text encoder and a defect category generator, respectively, to obtain a defect feature vector and defect category parameters; a generation module, used to generate the defect image based on the defect mask, the noise parameters, the defect feature vector, and the defect category parameters.

[0013] Optionally, the device also includes: a second acquisition module, used to obtain a weld spot image outside the weld of the target workpiece captured by a camera before obtaining a weld image inside the weld of the target workpiece detected by an X-ray device; a judgment module, used to judge whether the target workpiece has a welding defect based on the weld spot image; and a determination module, used to determine whether to obtain a weld spot image inside the weld of the target workpiece detected by an X-ray device if the target workpiece has a welding defect.

[0014] Optionally, the extraction module includes: a detection unit for detecting pores, cracks, and the covering area between the weld material and the base material in the area of ​​interest; a processing unit for extracting the circularity of the pores and the linear length of the cracks, calculating the roughness of the covering area through a gray level co-occurrence matrix, and extracting deep learning features of the area of ​​interest using a deep residual network, wherein the geometric features include the circularity and the linear length, and the texture features include the roughness.

[0015] Optionally, the processing unit includes: a first calculation subunit, used to use a window of preset size to slide from the starting position to the ending position of the coverage area, and calculate the occurrence frequency of grayscale difference combinations of all pixel pairs in the window at each sliding position, wherein the grayscale difference combination is a pixel pair with different grayscale values; a storage subunit, used to store the occurrence frequency of all windows into a matrix to obtain a grayscale co-occurrence matrix; a second calculation subunit, used to use the grayscale co-occurrence matrix to calculate the contrast intensity of the grayscale values ​​in the coverage area; a conversion subunit, used to convert the contrast intensity into the roughness of the coverage area, wherein the contrast intensity is positively correlated with the roughness.

[0016] Optionally, the adjustment module includes: a parsing unit for parsing the defect category and defect severity of the welding defect information; a search unit for searching for a first operating parameter and a second operating parameter of the welding equipment that match the defect category, and for searching for a first adjustment amount and a second adjustment amount that match the defect severity; an adjustment unit for adjusting the first operating parameter of the welding equipment based on the first adjustment amount, and adjusting the second operating parameter of the welding equipment based on the second adjustment amount.

[0017] Optionally, the search unit includes: a first search sub-unit, used to determine, if the defect category is internal porosity, that the first working parameters of the welding equipment are welding current and shielding gas flow, and the second working parameters are welding line speed and welding material preheating temperature; a second search sub-unit, used to determine, if the defect category is internal crack, that the first working parameters of the welding equipment are welding material preheating temperature and welding line speed, and the second working parameters are weld interlayer temperature and fixture tightness; a third search sub-unit, used to determine, if the defect category is lack of fusion, that the first working parameters of the welding equipment are welding current and welding angle, and the second working parameters are welding line speed and shielding gas flow; a fourth search sub-unit, used to determine, if the defect category is incomplete penetration, that the first working parameters of the welding equipment are welding current and welding time, and the second working parameter is welding line speed; a fifth search sub-unit, used to determine, if the defect category is welding inclusion, that the first working parameters of the welding equipment are welding line speed and slag cleaning frequency, and the second working parameters are shielding gas purity and arc voltage.

[0018] Optionally, the adjustment unit includes: a first adjustment subunit, used to adjust the first working parameter of the welding equipment based on the first adjustment amount; an acquisition subunit, used to obtain a test image obtained by welding a test workpiece after the adjustment of the welding equipment is completed; a judgment subunit, used to judge whether there is test defect information in the test image, wherein the test defect information at least includes the welding defect information; and a second adjustment subunit, used to continue to adjust the second working parameter of the welding equipment based on the second adjustment amount if there is test defect information in the test image.

[0019] According to yet another embodiment of the present invention, a storage medium is provided, in which a computer program is stored. The computer program is configured to execute the steps of any one of the above-mentioned apparatus embodiments when run.

[0020] According to another embodiment of the present invention, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to perform the steps in any of the above device embodiments.

[0021] According to the embodiment of the present invention, after the welding equipment completes welding of the target workpiece, a weld image of the inside of the weld of the target workpiece detected by the X-ray equipment is obtained; the weld image is preprocessed to obtain a region of interest of the weld image; fusion features of the region of interest are extracted, wherein the fusion features include geometric features, texture features, and deep learning features; the fusion features are input into a pre-trained convolutional neural network (CNN) classifier, and welding defect information of the weld image is output, wherein the welding defect information includes defect categories and their confidence levels; the working parameters of the welding equipment are adjusted according to the welding defect information, and by detecting the welding defect information inside the weld of the target workpiece and adaptively adjusting the working parameters of the welding equipment in real time, efficiency is improved and the lag of welding defect processing is reduced, thereby solving the technical problem of low efficiency of manually adjusting the welding equipment in the related art, improving the automation and intelligence of welding production, reducing dependence on manual machine adjustment, and improving the production efficiency and product yield of workpiece welding. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0023] Figure 1 This is a hardware structure block diagram of a computer according to an embodiment of the present invention;

[0024] Figure 2is a flow chart of a method for adjusting welding parameters according to an embodiment of the present invention;

[0025] Figure 3 This is a flow chart based on X-ray vision detection and intelligent machine adjustment in an embodiment of the present invention;

[0026] Figure 4 4 is a structural block diagram of a device for adjusting welding parameters according to an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of this application. It should be noted that, in the absence of conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] Example 1

[0030] The method embodiment provided in the first embodiment of the present application can be executed in a computing device such as a server, a computer, or a camera. For example, Figure 1 This is a hardware structure diagram of a computer according to an embodiment of the present invention. Figure 1 As shown, the computer may include one or more ( Figure 1 Only one is shown) a processor 102 (the processor 102 may include but is not limited to a microprocessor MCU or a programmable logic device FPGA and other processing devices) and a memory 104 for storing data. Optionally, the computer may also include a transmission device 106 and an input / output device 108 for communication functions. It will be understood by those skilled in the art that Figure 1The structure shown is only for illustration and does not limit the structure of the above-mentioned computer. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0031] Memory 104 can be used to store computer programs, such as application software programs and modules, such as a computer program corresponding to a welding parameter adjustment method in an embodiment of the present invention. Processor 102 executes the computer program stored in memory 104 to execute various functional applications and data processing, thereby implementing the aforementioned method. Memory 104 can include high-speed random access memory (RAM) and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, memory 104 may further include memory located remotely from processor 102, which can be connected to the computer via a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0032] Transmission device 106 is used to receive or transmit data via a network. A specific example of the aforementioned network may include a wireless network provided by a computer's communications provider. In one embodiment, transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0033] In this embodiment, a method for adjusting welding parameters is provided. Figure 2 FIG. 1 is a flow chart of a method for adjusting welding parameters according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0034] Step S202, after the welding equipment completes welding the target workpiece, obtaining a weld seam image of the interior of the weld seam of the target workpiece detected by an X-ray device;

[0035] Optionally, the target workpiece may be a metal workpiece such as a container.

[0036] Step S204, preprocessing the weld image to obtain a region of interest of the weld image;

[0037] Optionally, the image preprocessing process includes denoising, enhancement, and segmentation. Denoising includes using Gaussian filtering to remove X-ray image noise. Enhancement includes contrast stretching to highlight the weld area. Segmentation includes extracting the weld ROI (Region of Interest) based on threshold segmentation.

[0038] Step S206, extracting fusion features of the region of interest, wherein the fusion features include geometric features, texture features, and deep learning features;

[0039] Step S208: inputting the fusion features into a pre-trained convolutional neural network (CNN) classifier to output welding defect information of the weld image, wherein the welding defect information includes a defect category and its confidence level;

[0040] An X-ray internal flaw detection visual inspection module is installed on the welding device to capture real-time image information of the weld interior. The captured images are processed and analyzed using an algorithm model to identify various defects within the weld.

[0041] Optionally, defect categories include internal weld porosity, internal inclusions, internal cracks, incomplete penetration, lack of fusion, etc.

[0042] Deep learning models based on X-ray images (such as convolutional neural networks (CNN)) learn the characteristic expressions of internal defects in welds through training sets, and combine traditional image processing techniques (edge ​​detection and grayscale analysis) to assist in locating abnormal areas with welding defects and identify defect categories.

[0043] After the welding defect information of the weld image is output, the defect boundary may be optimized in combination with morphological operations (erosion / expansion) to update the welding defect information.

[0044] Step S210: adjusting the operating parameters of the welding equipment according to the welding defect information.

[0045] The optional working parameters may be parameters such as the current, wire speed, and fixture of the welding equipment.

[0046] Through the above steps, after the welding equipment completes welding the target workpiece, a weld image of the inside of the weld of the target workpiece detected by the X-ray equipment is obtained; the weld image is preprocessed to obtain a region of interest of the weld image; fusion features of the region of interest are extracted, wherein the fusion features include geometric features, texture features, and deep learning features; the fusion features are input into a pre-trained convolutional neural network (CNN) classifier to output welding defect information of the weld image, wherein the welding defect information includes defect categories and their confidence levels; the working parameters of the welding equipment are adjusted according to the welding defect information, and by detecting the welding defect information inside the weld of the target workpiece and adaptively adjusting the working parameters of the welding equipment in real time, efficiency is improved and the lag of welding defect processing is reduced, thereby solving the technical problem of low efficiency of manually adjusting welding equipment in related technologies, improving the automation and intelligence of welding production, reducing dependence on manual machine adjustment, and improving the production efficiency and product yield of workpiece welding.

[0047] In this embodiment, before obtaining the weld image inside the weld of the target workpiece detected by the X-ray device, it also includes: obtaining the weld spot image outside the weld of the target workpiece captured by the camera; judging whether the target workpiece has a welding defect based on the weld spot image; if the target workpiece has a welding defect, determining to obtain the weld image inside the weld of the target workpiece detected by the X-ray device.

[0048] Optionally, the camera may be a 2D camera or a 3D camera. When a welding defect exists inside the weld, the defect may extend to the outside or affect the external weld point.

[0049] In one implementation of this embodiment, extracting the fusion features of the region of interest includes: detecting pores, cracks, and the covering area between the weld material and the base material in the region of interest; extracting the circularity of the pores and the linear length of the cracks, calculating the roughness of the covering area through a gray-level co-occurrence matrix, and extracting deep learning features of the region of interest using a deep residual network, wherein the geometric features include the circularity and the linear length, and the texture features include the roughness.

[0050] In this embodiment, the geometric feature extraction process includes extracting the circularity of pores and the linear length of cracks. The texture feature extraction process includes analyzing the texture roughness of the unfused area (the overlapped area between the weld material and the base material) using a gray-level co-occurrence matrix (GLCM). The deep learning feature extraction process includes automatically extracting high-dimensional defect features using a CNN (ResNet-50 deep residual network) as the backbone network.

[0051] In one example, calculating the roughness of the coverage area using a grayscale co-occurrence matrix includes: using a window of preset size to slide from a starting position to an ending position of the coverage area, and calculating the frequency of occurrence of grayscale difference combinations of all pixel pairs in the window at each sliding position, wherein the grayscale difference combination is a pair of pixels with different grayscale values; storing the frequency of occurrence of all windows in a matrix to obtain a grayscale co-occurrence matrix; using the grayscale co-occurrence matrix to calculate the contrast intensity of the grayscale values ​​in the coverage area; converting the contrast intensity into the roughness of the coverage area, wherein the contrast intensity is positively correlated with the roughness.

[0052] Optionally, the preset window size may be 3x3, 5x5 (in pixels), etc., and the window is slid on the image of the coverage area.

[0053] In one example, using the gray level co-occurrence matrix to calculate the contrast intensity of the gray values ​​in the coverage area includes: using the following formula to calculate the contrast intensity of the gray values ​​in the coverage area:

[0054] ;

[0055] Among them, P(i,j) is the element in the i-th row and j-th column of the gray-level co-occurrence matrix, which represents the frequency of occurrence of pixel pairs with gray-level values ​​i and gray-level j.

[0056] The higher the contrast, the rougher the texture of the image. Image areas with high contrast indicate rough textures because the differences in grayscale values ​​are large. Image areas with low contrast indicate smooth textures because the differences in grayscale values ​​are small.

[0057] In one implementation of this embodiment, adjusting the operating parameters of the welding equipment according to the welding defect information includes: parsing the defect category and defect severity of the welding defect information; searching for first and second operating parameters of the welding equipment that match the defect category, and searching for first and second adjustment amounts that match the defect severity; adjusting the first operating parameter of the welding equipment based on the first adjustment amount, and adjusting the second operating parameter of the welding equipment based on the second adjustment amount.

[0058] The greater the severity of the defect, the larger the corresponding adjustment amount. For example, if the defect type is internal pores, the larger the size of the internal pores, the larger the adjusted current and gas flow rate. Conversely, the smaller the size of the internal pores, the smaller the adjusted current and gas flow rate.

[0059] Optionally, the first operating parameter is a direct operating parameter corresponding to the defect category, and the second operating parameter is an indirect operating parameter corresponding to the defect category.

[0060] In this embodiment, the operating parameters of the welding equipment can be adjusted using a machine adjustment model. The machine adjustment model stores the matching rules between welding defect information and the welding equipment's operating parameters. The machine adjustment model is connected to the visual inspection system. When the visual inspection system identifies a defect, it transmits the defect information to the machine adjustment model. The machine adjustment model then intelligently adjusts the welding equipment's operating parameters based on the defect type to improve welding quality. The machine adjustment model can also control the connections of the welding equipment's wire (welding material) feeding system, flexible fixture system, gas supply system, and other systems.

[0061] In one example, searching for the first and second working parameters of the welding equipment that match the defect category includes: if the defect category is internal porosity, determining that the first working parameters of the welding equipment are welding current and shielding gas flow, and the second working parameters are welding line speed and welding material preheating temperature; if the defect category is internal crack, determining that the first working parameters of the welding equipment are welding material preheating temperature and welding line speed, and the second working parameters are weld interlayer temperature and fixture tightness; if the defect category is lack of fusion, determining that the first working parameters of the welding equipment are welding current and welding angle, and the second working parameters are welding line speed and shielding gas flow; if the defect category is incomplete penetration, determining that the first working parameters of the welding equipment are welding current and welding time, and the second working parameter is welding line speed; if the defect category is welding inclusion, determining that the first working parameters of the welding equipment are welding line speed and slag cleaning frequency, and the second working parameters are shielding gas purity and arc voltage.

[0062] When internal pores exist, adjust the welding current by increasing it by 5%-8% to increase heat input, prolong the liquid time of the molten pool, and promote gas escape; adjust the shielding gas flow rate by increasing it by 15%-20% to enhance the molten pool protection effect and reduce air mixing (especially for Ar / CO2 mixed gas scenarios); adjust the welding line speed by reducing it to 85%-90% of the current value to slow the cooling rate of the molten pool and provide a longer time window for gas escape; adjust the welding material pretreatment temperature (preheat temperature) to 120°C-150°C to dry the welding material and reduce the moisture on the welding wire surface (requires linkage with the wire feeding system).

[0063] When internal cracks exist, adjust the preheat temperature to 120°C-150°C, dry the welding material, and reduce the moisture on the surface of the welding wire (requires linkage with the wire feeding system); adjust the welding line speed to 60%-70% of the current value, slow down the cooling rate, and prevent cracks caused by uneven shrinkage between the molten pool and the base material; adjust the temperature between weld layers to maintain 150°C-200°C, and avoid excessively low interlayer temperatures during multi-pass welding to reduce residual stress; adjust the tightness of the fixture and reduce the clamping force by 10%-15% to release the internal stress of the base material caused by thermal expansion (requires linkage with the flexible fixture system).

[0064] When there is incomplete fusion, adjust the welding current by increasing it by 5%-10% to increase heat input and promote fusion adjustment between the base material and the molten pool; reduce the welding line speed to 70%-80% of the current value, slow down the movement speed, extend the molten pool residence time, and ensure sufficient fusion; adjust the welding gun angle to an inclination of 15°-25° to optimize the flow direction of the molten pool and avoid uneven coverage of the molten pool (for example: adjust from vertical to forward inclination); adjust the shielding gas flow rate by increasing it by 10%-15% to enhance the gas protection effect, reduce molten pool oxidation, and improve wettability.

[0065] When there is incomplete penetration, adjust the welding current and increase it by 10%-15% to directly improve the penetration ability and ensure the penetration of the base material; adjust the welding time and extend it by 10%-20%. For intermittent welding, extend the arc action time and increase the penetration depth; adjust the welding line speed and reduce it to 60%-70% of the current value, slow down the moving speed, and increase the heat input per unit length.

[0066] When welding inclusions exist, adjust the welding line speed and reduce it to 80%-85% of the current value to slow down the solidification rate of the molten pool and prolong the slag floating time; adjust the slag cleaning frequency and increase it by 50%-100%, increase the movement frequency of the slag cleaning robot arm, and promptly remove the welding slag on the surface of the molten pool; adjust the purity of the shielding gas and switch to a high-purity gas source to reduce the mixing of gas impurities into the molten pool (the gas supply system needs to be linked); adjust the arc voltage and increase it by 5%-8% to enhance the arc blowing force and promote the disturbance of the molten pool and the floating of impurities.

[0067] Optionally, adjusting the first operating parameter of the welding equipment based on the first adjustment amount, and adjusting the second operating parameter of the welding equipment based on the second adjustment amount include: adjusting the first operating parameter of the welding equipment based on the first adjustment amount; obtaining a test image obtained by welding a test workpiece after the adjustment of the welding equipment is completed; judging whether there is test defect information in the test image, wherein the test defect information at least includes the welding defect information; if there is test defect information in the test image, continuing to adjust the second operating parameter of the welding equipment based on the second adjustment amount.

[0068] The test picture of this embodiment is a weld image of the inside of the weld of the test workpiece detected by the X-ray device after the welding equipment completes welding the test workpiece based on the adjusted working parameters.

[0069] If the welding defect of the test workpiece has disappeared after adjusting the first working parameter, there is no need to continue adjusting the second working parameter, so as to avoid new defects caused by excessive adjustment of the working parameters of the welding equipment.

[0070] The solution of this embodiment proposes a container welding quality control system and method based on X-ray vision inspection and intelligent machine adjustment. It aims to solve internal quality problems that occur during the welding process of existing robotic arms, such as the appearance of pores in the weld, residual unmelted weld slag or other impurities in the weld, cracks in the weld, partial lack of fusion caused by incomplete penetration of the weld metal into the parent material, incomplete fusion between the weld metal and the parent material or between weld metal layers, and other first-line internal weld defects. These problems are solved by achieving real-time welding quality detection and automatic adjustment of welding equipment parameters through intelligent means, thereby improving welding quality and ensuring product yield.

[0071] Figure 3 This is a flow chart based on X-ray vision detection and intelligent machine adjustment in an embodiment of the present invention. After welding begins, the X-ray vision detection module performs real-time imaging and detects the weld image. The algorithm model classifies defects to determine whether defects are detected. If so, the defect type is transmitted to the machine adjustment model of the welding equipment. The machine adjustment model receives the defect type, matches the parameter adjustment rules, and adjusts the relevant working parameters of the welding equipment.

[0072] Integrating the visual inspection system and intelligent machine adjustment model into the welding control system enables real-time monitoring and intelligent adjustment of the welding process. This also improves the accuracy of defect identification and the effectiveness of machine adjustment model adjustments through continuous learning and optimization of the algorithm model, ultimately continuously enhancing welding quality.

[0073] This embodiment uses a visual inspection system to capture images of internal defects in welds in real time, accurately identify various defects, and provide a reliable basis for intelligent machine adjustment. The intelligent machine adjustment model can automatically adjust equipment parameters according to the defect type, achieve immediate improvement in welding quality, and reduce the production of defective products. The solution of this embodiment improves the automation and intelligence level of welding production, reduces dependence on manual machine adjustment, and improves production efficiency and product yield.

[0074] Through the description of the above embodiments, those skilled in the art will clearly understand that the methods according to the above embodiments can be implemented using software plus the necessary general-purpose hardware platform. Of course, hardware can also be used, but in many cases the former is a more preferred embodiment. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, or optical disk) and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in various embodiments of the present invention.

[0075] Example 2

[0076] This embodiment also provides a device for adjusting welding parameters, which is used to implement the above-mentioned embodiments and preferred embodiments. Details already described will not be repeated here. The term "module" used below refers to a combination of software and hardware that implements the specified functions. While the devices described in the following embodiments are preferably implemented in software, hardware, or a combination of software and hardware, is also contemplated.

[0077] Figure 4 This is a structural block diagram of a device for adjusting welding parameters according to an embodiment of the present invention. Figure 4 As shown, the device includes:

[0078] A first acquisition module 40 is configured to acquire a weld seam image of the weld seam of the target workpiece detected by an X-ray device after the welding device completes welding the target workpiece;

[0079] A processing module 42 is used to pre-process the weld image to obtain a region of interest of the weld image;

[0080] An extraction module 44 is configured to extract fusion features of the region of interest, wherein the fusion features include geometric features, texture features, and deep learning features;

[0081] An output module 46 is configured to input the fusion features into a pre-trained convolutional neural network (CNN) classifier and output welding defect information of the weld image, wherein the welding defect information includes a defect category and its confidence level;

[0082] The adjustment module 48 is configured to adjust the operating parameters of the welding equipment according to the welding defect information.

[0083] Optionally, the device also includes: a second acquisition module, used to obtain a weld spot image outside the weld of the target workpiece captured by a camera before obtaining a weld image inside the weld of the target workpiece detected by an X-ray device; a judgment module, used to judge whether the target workpiece has a welding defect based on the weld spot image; and a determination module, used to determine whether to obtain a weld spot image inside the weld of the target workpiece detected by an X-ray device if the target workpiece has a welding defect.

[0084] Optionally, the extraction module includes: a detection unit for detecting pores, cracks, and the covering area between the weld material and the base material in the area of ​​interest; a processing unit for extracting the circularity of the pores and the linear length of the cracks, calculating the roughness of the covering area through a gray level co-occurrence matrix, and extracting deep learning features of the area of ​​interest using a deep residual network, wherein the geometric features include the circularity and the linear length, and the texture features include the roughness.

[0085] Optionally, the processing unit includes: a first calculation subunit, used to use a window of preset size to slide from the starting position to the ending position of the coverage area, and calculate the occurrence frequency of grayscale difference combinations of all pixel pairs in the window at each sliding position, wherein the grayscale difference combination is a pixel pair with different grayscale values; a storage subunit, used to store the occurrence frequency of all windows into a matrix to obtain a grayscale co-occurrence matrix; a second calculation subunit, used to use the grayscale co-occurrence matrix to calculate the contrast intensity of the grayscale values ​​in the coverage area; a conversion subunit, used to convert the contrast intensity into the roughness of the coverage area, wherein the contrast intensity is positively correlated with the roughness.

[0086] Optionally, the adjustment module includes: a parsing unit for parsing the defect category and defect severity of the welding defect information; a search unit for searching for a first operating parameter and a second operating parameter of the welding equipment that match the defect category, and for searching for a first adjustment amount and a second adjustment amount that match the defect severity; an adjustment unit for adjusting the first operating parameter of the welding equipment based on the first adjustment amount, and adjusting the second operating parameter of the welding equipment based on the second adjustment amount.

[0087] Optionally, the search unit includes: a first search sub-unit, used to determine, if the defect category is internal porosity, that the first working parameters of the welding equipment are welding current and shielding gas flow, and the second working parameters are welding line speed and welding material preheating temperature; a second search sub-unit, used to determine, if the defect category is internal crack, that the first working parameters of the welding equipment are welding material preheating temperature and welding line speed, and the second working parameters are weld interlayer temperature and fixture tightness; a third search sub-unit, used to determine, if the defect category is lack of fusion, that the first working parameters of the welding equipment are welding current and welding angle, and the second working parameters are welding line speed and shielding gas flow; a fourth search sub-unit, used to determine, if the defect category is incomplete penetration, that the first working parameters of the welding equipment are welding current and welding time, and the second working parameter is welding line speed; a fifth search sub-unit, used to determine, if the defect category is welding inclusion, that the first working parameters of the welding equipment are welding line speed and slag cleaning frequency, and the second working parameters are shielding gas purity and arc voltage.

[0088] Optionally, the adjustment unit includes: a first adjustment subunit, used to adjust the first working parameter of the welding equipment based on the first adjustment amount; an acquisition subunit, used to obtain a test image obtained by welding a test workpiece after the adjustment of the welding equipment is completed; a judgment subunit, used to judge whether there is test defect information in the test image, wherein the test defect information at least includes the welding defect information; and a second adjustment subunit, used to continue to adjust the second working parameter of the welding equipment based on the second adjustment amount if there is test defect information in the test image.

[0089] It should be noted that the above modules can be implemented through software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0090] Example 3

[0091] An embodiment of the present invention further provides a storage medium storing a computer program, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0092] Optionally, in this embodiment, the storage medium may be configured to store a computer program for executing:

[0093] S1, after the welding equipment completes welding of the target workpiece, obtaining a weld seam image inside the weld seam of the target workpiece detected by an X-ray device;

[0094] S2, preprocessing the weld image to obtain a region of interest of the weld image;

[0095] S3, extracting fusion features of the region of interest, wherein the fusion features include geometric features, texture features, and deep learning features;

[0096] S4, inputting the fusion feature into a pre-trained convolutional neural network (CNN) classifier, and outputting welding defect information of the weld image, wherein the welding defect information includes a defect category and its confidence level;

[0097] S5: Adjust the working parameters of the welding equipment according to the welding defect information.

[0098] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store computer programs.

[0099] An embodiment of the present invention further provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0100] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0101] Optionally, in this embodiment, the processor may be configured to execute the following steps through a computer program:

[0102] S1, after the welding equipment completes welding of the target workpiece, obtaining a weld seam image inside the weld seam of the target workpiece detected by an X-ray device;

[0103] S2, preprocessing the weld image to obtain a region of interest of the weld image;

[0104] S3, extracting fusion features of the region of interest, wherein the fusion features include geometric features, texture features, and deep learning features;

[0105] S4, inputting the fusion feature into a pre-trained convolutional neural network (CNN) classifier, and outputting welding defect information of the weld image, wherein the welding defect information includes a defect category and its confidence level;

[0106] S5: Adjust the working parameters of the welding equipment according to the welding defect information.

[0107] Optionally, specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0108] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0109] In the above embodiments of the present application, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0110] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0111] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0112] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0113] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the existing technology, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, magnetic disk, or optical disk, etc., various media that can store program code.

[0114] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for adjusting welding parameters, characterized in that: include: After the welding equipment completes welding the target workpiece, obtaining a weld seam image of the inside of the weld seam of the target workpiece detected by the X-ray equipment; Preprocessing the weld image to obtain a region of interest of the weld image; Extracting fusion features of the region of interest, wherein the fusion features include geometric features, texture features, and deep learning features; Inputting the fusion features into a pre-trained convolutional neural network (CNN) classifier to output welding defect information of the weld image, wherein the welding defect information includes a defect category and its confidence level; adjusting the working parameters of the welding equipment according to the welding defect information; Adjusting the operating parameters of the welding equipment according to the welding defect information includes: parsing the defect category and defect severity of the welding defect information; searching for first and second operating parameters of the welding equipment that match the defect category, and searching for first and second adjustment amounts that match the defect severity; adjusting the first operating parameter of the welding equipment based on the first adjustment amount, and adjusting the second operating parameter of the welding equipment based on the second adjustment amount; Wherein, searching for the first working parameter and the second working parameter of the welding equipment that match the defect category includes: if the defect category is internal porosity, determining that the first working parameter of the welding equipment is the welding current and the shielding gas flow rate, and the second working parameter is the welding line speed and the welding material preheating temperature; if the defect category is internal crack, determining that the first working parameter of the welding equipment is the welding material preheating temperature and the welding line speed, and the second working parameter is the weld interlayer temperature and the clamp tightness; if the defect category is lack of fusion, determining that the first working parameter of the welding equipment is the welding current and the welding angle, and the second working parameter is the welding line speed and the shielding gas flow rate; if the defect category is lack of penetration, determining that the first working parameter of the welding equipment is the welding current and the welding time, and the second working parameter is the welding line speed; if the defect category is welding inclusion, determining that the first working parameter of the welding equipment is the welding line speed and the slag cleaning frequency, and the second working parameter is the shielding gas purity and the arc voltage; Among them, adjusting the first operating parameter of the welding equipment based on the first adjustment amount and adjusting the second operating parameter of the welding equipment based on the second adjustment amount include: adjusting the first operating parameter of the welding equipment based on the first adjustment amount; obtaining a test picture obtained by welding a test workpiece after the adjustment of the welding equipment is completed; judging whether there is test defect information in the test picture, wherein the test defect information at least includes the welding defect information; if test defect information exists in the test picture, continuing to adjust the second operating parameter of the welding equipment based on the second adjustment amount.

2. The method according to claim 1, characterized in that Before acquiring a weld image of the inside of the weld of the target workpiece detected by an X-ray device, the method further includes: Acquire a weld spot image outside the weld of the target workpiece captured by a camera; Determining whether the target workpiece has a welding defect based on the weld spot image; If the target workpiece has a welding defect, it is determined to obtain a weld image inside the weld of the target workpiece detected by an X-ray device.

3. The method according to claim 1, characterized in that Extracting the fusion features of the region of interest includes: Detecting pores, cracks, and overlapped areas between the weld material and the base material in the region of interest; The circularity of the pores and the linear length of the cracks are extracted, the roughness of the covered area is calculated using a gray-level co-occurrence matrix, and deep learning features of the region of interest are extracted using a deep residual network, wherein the geometric features include the circularity and the linear length, and the texture features include the roughness.

4. The method according to claim 3, characterized in that Calculating the roughness of the coverage area by using the gray level co-occurrence matrix includes: Sliding a window of a preset size from a starting position to an ending position of the coverage area, and calculating the frequency of occurrence of grayscale difference combinations of all pixel pairs within the window at each sliding position, wherein the grayscale difference combinations are pixel pairs with different grayscale values; Store the occurrence frequencies of all windows into a matrix to obtain the gray-level co-occurrence matrix; Calculating the contrast intensity of the grayscale values ​​in the coverage area using the gray level co-occurrence matrix; The contrast intensity is converted into the roughness of the coverage area, wherein the contrast intensity is positively correlated with the roughness.

5. A device for adjusting welding parameters, characterized in that: include: A first acquisition module is used to acquire a weld seam image of the inside of the weld seam of the target workpiece detected by an X-ray device after the welding equipment completes welding the target workpiece; a processing module, configured to preprocess the weld image to obtain a region of interest of the weld image; An extraction module, configured to extract fusion features of the region of interest, wherein the fusion features include geometric features, texture features, and deep learning features; An output module, configured to input the fusion features into a pre-trained convolutional neural network (CNN) classifier and output welding defect information of the weld image, wherein the welding defect information includes a defect category and its confidence level; An adjustment module, configured to adjust operating parameters of the welding equipment according to the welding defect information; The adjustment module includes: a parsing unit for parsing the defect category and defect severity of the welding defect information; a search unit for searching for a first operating parameter and a second operating parameter of the welding equipment that match the defect category, and for searching for a first adjustment amount and a second adjustment amount that match the defect severity; an adjustment unit for adjusting the first operating parameter of the welding equipment based on the first adjustment amount, and adjusting the second operating parameter of the welding equipment based on the second adjustment amount; Wherein, the search unit includes: a first search subunit, for determining, if the defect type is internal porosity, that the first operating parameters of the welding equipment are welding current and shielding gas flow, and the second operating parameters are welding line speed and welding material preheating temperature; a second search subunit, for determining, if the defect type is internal crack, that the first operating parameters of the welding equipment are welding material preheating temperature and welding line speed, and the second operating parameters are weld interlayer temperature and clamp tightness; a third search subunit, for determining, if the defect type is lack of fusion, that the first operating parameters of the welding equipment are welding current and welding angle, and the second operating parameters are welding line speed and shielding gas flow; a fourth search subunit, for determining, if the defect type is incomplete penetration, that the first operating parameters of the welding equipment are welding current and welding time, and the second operating parameter is welding line speed; a fifth search subunit, for determining, if the defect type is welding inclusion, that the first operating parameters of the welding equipment are welding line speed and slag cleaning frequency, and the second operating parameters are shielding gas purity and arc voltage; In which, the adjustment unit includes: a first adjustment subunit, used to adjust the first working parameter of the welding equipment based on the first adjustment amount; an acquisition subunit, used to obtain a test image obtained by welding a test workpiece after the adjustment of the welding equipment is completed; a judgment subunit, used to judge whether there is test defect information in the test image, wherein the test defect information at least includes the welding defect information; a second adjustment subunit, used to continue to adjust the second working parameter of the welding equipment based on the second adjustment amount if there is test defect information in the test image.

6. A storage medium, characterized in that The storage medium stores a computer program, wherein the computer program is configured to execute the method according to any one of claims 1 to 4 when run.

7. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to perform the method according to any one of claims 1 to 4.

Images