Girth weld contour geometric dimension identification method and device, electronic equipment and medium

By processing and analyzing images of welded joint samples, and using MATLAB and AutoCAD software, the problems of large errors and long time consumption in the identification of weld contour geometry in traditional methods have been solved, realizing fast and accurate identification of weld contour geometry, which is suitable for intelligent inspection of oil and gas pipelines.

CN118941610APending Publication Date: 2024-11-12CHINA PETROLEUM PIPELINE RES INST CO LTD +2
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310532170.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-12
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

Traditional methods suffer from large errors and long processing times in weld contour geometry identification, making it difficult to accurately and quickly determine weld contour geometry.

Method used

By acquiring sampled images of welded joint specimens, normalization, image enhancement, and thinning processes are performed. Using two-dimensional wavelet decomposition and reconstruction, combined with MATLAB and AutoCAD software, the coordinates of contour edge points are extracted to generate the geometric shape of the welded joint specimen.

Benefits of technology

It enables rapid and accurate identification of the circumferential weld contour and its geometric dimensions in welded joint samples, shortens the measurement cycle, reduces complexity, and improves identification accuracy, which is in line with the trend of intelligent development.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118941610A_ABST
    Figure CN118941610A_ABST
Patent Text Reader

Abstract

The embodiment of the invention relates to the field of pipeline circumferential weld detection, and provides a circumferential weld contour geometric dimension identification method and device, electronic equipment and a medium, and the method comprises the steps: obtaining a sampling image of a welding joint sample, the sampling image comprising a complete image of a circumferential weld in the welding joint sample; performing normalization processing on the sampling image, and converting the sampling image into a preset format to obtain a normalized image; performing image enhancement and graph refinement processing on the normalized image to obtain a geometric structure image of the contour of the circumferential weld; decomposing and reconstructing the geometric structure image of the circumferential weld contour to obtain a reconstructed image; performing coordinate extraction on contour edge points in the reconstructed image to obtain a contour edge point coordinate set; and according to the contour edge point coordinate set, generating a welding joint sample geometric figure including the contour pattern of the circumferential weld and the geometric size thereof. According to the embodiment of the invention, rapid and accurate identification of the contour and the geometric dimension of the circumferential weld in the welded joint sample is effectively realized, and the identification precision is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of pipeline girth weld detection, and in particular to a girth weld contour geometric dimension recognition method and device, electronic equipment, and medium. Background Art

[0002] Driven by economic development, the construction of oil and gas pipelines is booming. At the same time, the safety issues of oil and gas pipelines are becoming increasingly prominent. The failure of girth welds has become one of the important factors threatening the safe operation of pipelines, and once the girth welds fail, the consequences will be very serious. Therefore, in order to accurately study the integrity of pipeline welding structures and the reliability of the system, it is necessary to strengthen the research on girth welds.

[0003] The identification and determination of the geometric dimensions of the weld contour is one of the important prerequisites for the study of girth welds. In order to identify and delineate the geometric dimensions of the weld contour, the traditional approach is generally to manually delineate the weld contour on the weld joint specimen, and then use geometric measurement tools such as a ruler to measure the geometric dimensions. However, this traditional approach easily leads to large errors in the geometric dimensions of the weld contour obtained, and the geometric dimension measurement process takes a long time. Summary of the invention

[0004] The present disclosure aims to solve at least one of the problems existing in the prior art and provides a method and device for identifying the geometric dimensions of a girth weld contour, an electronic device, and a medium.

[0005] In one aspect of the present disclosure, a method for identifying geometric dimensions of a girth weld profile is provided, the method comprising:

[0006] Acquire a sampling image of the weld joint sample, wherein the sampling image includes a complete image of the girth weld in the weld joint sample;

[0007] Normalizing the sampled image, converting the sampled image into a preset format, and obtaining a normalized image;

[0008] Performing image enhancement and graphic refinement processing on the normalized image to obtain a geometric structure image of the girth weld contour;

[0009] Decomposing and reconstructing the geometric structure image of the girth weld contour to obtain a reconstructed image;

[0010] Extracting the coordinates of the contour edge points in the reconstructed image to obtain a contour edge point coordinate set;

[0011] A welding joint sample geometry is generated according to the contour edge point coordinate set, wherein the welding joint sample geometry includes a contour pattern of the girth weld and its geometric dimensions.

[0012] Optionally, the normalizing the sampled image to convert the sampled image into a preset format to obtain a normalized image includes:

[0013] The sampled image is subjected to grayscale normalization processing so that the grayscale value of each pixel is distributed between [0, 255], thereby obtaining the normalized image.

[0014] Optionally, decomposing and reconstructing the geometric structure image of the girth weld contour to obtain a reconstructed image includes:

[0015] Based on two-dimensional wavelet, the geometric structure image of the girth weld contour is decomposed and reconstructed multiple times to obtain the reconstructed image.

[0016] Optionally, extracting the coordinates of the contour edge points in the reconstructed image to obtain a set of contour edge point coordinates includes:

[0017] MATLAB software is used to extract the coordinates of each of the contour edge points in the reconstructed image, and the extracted coordinates are formed into an Excel file.

[0018] Optionally, generating a weld joint specimen geometry according to the contour edge point coordinate set includes:

[0019] Based on the Excel file, generate coordinate values ​​corresponding to each of the contour edge points;

[0020] The coordinate values ​​are imported into Auto CAD software to generate the geometric figure of the weld joint specimen.

[0021] Optionally, before acquiring the sampling image of the welding joint sample, the identification method further includes:

[0022] Cutting the weld joint sample to be processed from the pipeline;

[0023] Mechanically grinding and polishing the weld joint sample to obtain the weld joint sample after treatment;

[0024] Using a nitric acid alcohol solution of a preset concentration to erode the treated weld joint sample to highlight the contour shape of the girth weld, thereby obtaining the eroded weld joint sample;

[0025] The welded joint specimens after etching are rinsed and blown dry.

[0026] Optionally, obtaining a sampling image of the welding joint sample includes:

[0027] The welding joint sample after the rinsing and drying treatment is photographed and sampled to obtain the sampling image.

[0028] Another aspect of the present disclosure provides a device for identifying geometric dimensions of a girth weld profile, the device comprising:

[0029] An acquisition module, used for acquiring a sampling image of a weld joint sample, wherein the sampling image includes a complete image of a girth weld in the weld joint sample;

[0030] A normalization module, used for performing normalization processing on the sampled image, converting the sampled image into a preset format, and obtaining a normalized image;

[0031] A refinement module, used for performing image enhancement and image refinement processing on the normalized image to obtain a geometric structure image of the girth weld contour;

[0032] A reconstruction module, used for decomposing and reconstructing the geometric structure image of the girth weld contour to obtain a reconstructed image;

[0033] An extraction module, used for extracting the coordinates of the contour edge points in the reconstructed image to obtain a coordinate set of the contour edge points;

[0034] A generation module is used to generate a welding joint sample geometry figure according to the contour edge point coordinate set, wherein the welding joint sample geometry figure includes the contour pattern of the girth weld and its geometric dimensions.

[0035] Optionally, the normalization module is used to perform normalization processing on the sampled image, convert the sampled image into a preset format, and obtain a normalized image, including:

[0036] The normalization module is specifically used for:

[0037] The sampled image is subjected to grayscale normalization processing so that the grayscale value of each pixel is distributed between [0, 255], thereby obtaining the normalized image.

[0038] Optionally, the reconstruction module is used to decompose and reconstruct the geometric structure image of the girth weld contour to obtain a reconstructed image, including:

[0039] The reconstruction module is specifically used for:

[0040] Based on two-dimensional wavelet, the geometric structure image of the girth weld contour is decomposed and reconstructed multiple times to obtain the reconstructed image.

[0041] Optionally, the extraction module is used to extract the coordinates of the contour edge points in the reconstructed image to obtain a contour edge point coordinate set, including:

[0042] The extraction module is specifically used for:

[0043] MATLAB software is used to extract the coordinates of each of the contour edge points in the reconstructed image, and the extracted coordinates are formed into an Excel file.

[0044] Optionally, the generating module is used to generate a welding joint specimen geometry according to the contour edge point coordinate set, including:

[0045] The generation module is specifically used for:

[0046] Based on the Excel file, generate coordinate values ​​corresponding to each of the contour edge points;

[0047] The coordinate values ​​are imported into Auto CAD software to generate the geometric figure of the weld joint specimen.

[0048] Optionally, the identification device further includes:

[0049] A cutting module, used for cutting the weld joint sample to be processed from the pipeline;

[0050] A polishing module, used for mechanically grinding and polishing the weld joint sample to obtain the processed weld joint sample;

[0051] An erosion module, used for etching the weld joint sample after treatment with a nitric acid alcohol solution of a preset concentration, highlighting the contour shape of the girth weld, and obtaining the weld joint sample after etching;

[0052] The flushing and drying module is used to flush and dry the weld joint sample after corrosion.

[0053] Optionally, the acquisition module is used to acquire a sampling image of the welding joint sample, including:

[0054] The acquisition module is specifically used for:

[0055] The welding joint sample after the rinsing and drying treatment is photographed and sampled to obtain the sampling image.

[0056] Another aspect of the present disclosure provides an electronic device, including:

[0057] at least one processor; and,

[0058] a memory communicatively connected to at least one processor; wherein,

[0059] The memory stores instructions that can be executed by at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for identifying the geometric dimensions of the girth weld profile described above.

[0060] Another aspect of the present disclosure provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method for identifying the geometric dimensions of the girth weld profile described above.

[0061] Compared with the prior art, the disclosed embodiments effectively realize the rapid and accurate identification of the girth weld contour and its geometric dimensions in the weld joint specimen, greatly shorten the measurement period of the girth weld contour geometric dimensions, reduce the complexity of the measurement, and improve the identification accuracy of the girth weld geometric dimensions. It has high practical application value for the identification of the weld contour geometric dimensions of the weld joint and is in line with the trend of intelligent development. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplifications do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0063] Figure 1 A flow chart of a method for identifying geometric dimensions of a girth weld profile provided in one embodiment of the present disclosure;

[0064] Figure 2 A flow chart of a method for identifying geometric dimensions of a girth weld profile provided in another embodiment of the present disclosure;

[0065] Figure 3 A flow chart of a method for identifying geometric dimensions of a girth weld profile provided in another embodiment of the present disclosure;

[0066] Figure 4 A schematic structural diagram of a device for identifying geometric dimensions of a girth weld profile provided by another embodiment of the present disclosure;

[0067] Figure 5 A schematic structural diagram of a device for identifying geometric dimensions of a girth weld profile provided by another embodiment of the present disclosure;

[0068] Figure 6 A schematic structural diagram of an electronic device provided in another embodiment of the present disclosure. DETAILED DESCRIPTION

[0069] In order to make the purpose, technical scheme and advantages of the embodiments of the present disclosure clearer, the embodiments of the present disclosure will be described in detail below in conjunction with the accompanying drawings. However, it can be understood by those skilled in the art that in each embodiment of the present disclosure, many technical details are proposed in order to enable readers to better understand the present disclosure. However, even without these technical details and various changes and modifications based on the following embodiments, the technical scheme claimed for protection in the present disclosure can also be implemented. The division of the following embodiments is for the convenience of description and should not constitute any limitation on the specific implementation of the present disclosure. The various embodiments can be combined and referenced with each other without contradiction.

[0070] One embodiment of the present disclosure relates to a method for identifying the geometric dimensions of a girth weld profile, the process of which is as follows: Figure 1 As shown, including:

[0071] Step S110, obtaining a sampling image of the weld joint sample, wherein the sampling image includes a complete image of the girth weld in the weld joint sample.

[0072] Specifically, in order to make the final recognition result more accurate, the sampled image should include a complete image of the girth weld, so that the complete outline and geometric dimensions of the girth weld can be identified in subsequent steps based on this.

[0073] Step S120 , normalizing the sampled image, converting the sampled image into a preset format, and obtaining a normalized image.

[0074] Specifically, step S120 can convert the sampled image into a unique standard form, i.e., a preset format to resist various transformations, thereby eliminating the appearance differences between different shapes in the sampled image and making the geometric contour features in the sampled image have an image standard form with invariant properties under a given transformation.

[0075] Exemplarily, step S120 includes: performing grayscale normalization processing on the sampled image so that the grayscale value of each pixel is distributed between [0, 255] to obtain a normalized image.

[0076] Specifically, step S120 can use MATLAB software to perform grayscale normalization processing on the sampled image, convert the grayscale value of each pixel in the sampled image to between [0, 255], and obtain a normalized image, thereby avoiding interference with subsequent image processing caused by insufficient image contrast angle.

[0077] Step S130, performing image enhancement and graphic refinement processing on the normalized image to obtain a geometric structure image of the girth weld contour.

[0078] Specifically, step S130 can selectively enhance or suppress the information in the normalized image through the image enhancement and graphic refinement process, thereby improving the image visual effect. At the same time, step S130 can also accurately obtain the contour geometry of the girth weld and convert the normalized image into a form more suitable for machine processing, thereby facilitating the recognition and extraction of image data and ensuring the accuracy and reliability of subsequent image processing calculation results.

[0079] It should be noted that this embodiment does not limit the specific steps of image enhancement and graphic refinement processing, as long as the corresponding image of the girth weld contour geometry structure, i.e., the girth weld contour geometry structure image, can be obtained by performing image enhancement and graphic refinement processing on the normalized image.

[0080] Step S140, decomposing and reconstructing the geometric structure image of the girth weld contour to obtain a reconstructed image.

[0081] Exemplarily, step S140 includes: based on two-dimensional wavelet, performing multiple decompositions and reconstructions on the geometric structure image of the girth weld contour to obtain a reconstructed image.

[0082] Specifically, step S140 can use the geometric structure image of the girth weld contour as the original image, decompose the original image multiple times using two-dimensional wavelets, and reconstruct the image multiple times according to the decomposed images to obtain the final reconstructed image, thereby achieving the purpose of eliminating noise.

[0083] Step S150 , extracting the coordinates of the contour edge points in the reconstructed image to obtain a contour edge point coordinate set.

[0084] Specifically, step S150 may extract the two-dimensional coordinates of each contour edge point in the reconstructed image respectively, and compose the extracted two-dimensional coordinates into a contour edge point coordinate set.

[0085] Exemplarily, step S150 includes: using MATLAB software to extract coordinates of each contour edge point in the reconstructed image, and forming an Excel file with the extracted coordinates.

[0086] Specifically, step S150 may import the reconstructed image into MATLAB software to extract the coordinates of the contour edge points, and then export the extracted coordinates into an Excel file.

[0087] By using MATLAB software to extract the coordinates of each contour edge point in the reconstructed image, the effective information in the image can be accurately obtained, further shortening the recognition cycle of the geometric dimensions of the girth weld contour and reducing the recognition complexity.

[0088] Step S160, generating a welding joint sample geometry figure according to the contour edge point coordinate set, wherein the welding joint sample geometry figure includes a contour pattern of the girth weld and its geometric dimensions.

[0089] Exemplarily, step S160 includes: generating coordinate values ​​corresponding to each contour edge point based on the Excel file; and importing the coordinate values ​​into Auto CAD software to generate a geometric figure of the weld joint specimen.

[0090] Specifically, since the Excel file includes the coordinates of each contour edge point, step S160 can generate the coordinate values ​​corresponding to each contour edge point based on the coordinates of each contour edge point in the Excel file, and import the Excel file containing the coordinate values ​​into the Auto CAD software, so that the Auto CAD software generates a geometric figure of the welding joint specimen including the contour pattern of the girth weld and its geometric dimensions based on the coordinate values. Therefore, based on the Excel file, the MATLAB software and the Auto CAD software can flexibly exchange the geometric dimension data information of the welding joint specimen image, thereby completing the rapid and accurate identification of the girth weld contour and its geometric dimensions in the welding joint specimen.

[0091] Compared with the prior art, the disclosed embodiment obtains a sampling image including a complete image of the girth weld, processes the sampling image using image processing technology, and finally obtains a welding joint sample geometry including a girth weld contour pattern and its geometric dimensions, thereby effectively realizing rapid and accurate identification of the girth weld contour and its geometric dimensions in the welding joint sample, greatly shortening the measurement cycle of the girth weld contour geometry, reducing the complexity of the measurement, and improving the identification accuracy of the girth weld geometry. It has high practical application value for the identification of the contour geometry of the welding joint, conforms to the trend of intelligent development, and lays a foundation for further research on the girth weld problem of oil and gas pipelines.

[0092] For example, Figure 2 As shown, before step S110, the method for identifying the geometric dimensions of the girth weld profile further includes:

[0093] Step S101, cutting a weld joint sample to be processed from a pipeline.

[0094] Specifically, in step S101, a metallographic sample cutting machine may be used to cut a weld joint sample to be processed from an oil and gas pipeline, where the weld joint sample includes a girth weld.

[0095] Step S102, using a mechanical method to grind and polish the weld joint sample to obtain a processed weld joint sample.

[0096] Specifically, step S102 can adopt mechanical methods such as rough grinding, fine grinding, rough polishing, and fine polishing to grind the welding joint sample flat and polish the welding joint sample, so that the surface of the welding joint sample becomes a smooth mirror surface to improve the subsequent image recognition accuracy.

[0097] Step S103, using a nitric acid alcohol solution of a preset concentration to erode the treated weld joint sample to highlight the contour shape of the girth weld, thereby obtaining the eroded weld joint sample.

[0098] Specifically, in step S103, a 3% nitrate alcohol solution can be used to wipe the polished weld joint sample, and the wiping time can be flexibly adjusted according to the actual situation, as long as the polished weld joint sample can highlight the contour shape of the girth weld under the erosion of the nitrate alcohol solution, so that the subsequent steps can obtain a more accurate girth weld contour image, ensuring the accuracy of the subsequent image recognition results. Of course, those skilled in the art can also use nitrate alcohol solutions of other concentrations to erode the polished weld joint sample according to the material characteristics of the weld joint sample, and this embodiment does not limit this.

[0099] Step S104, rinsing and drying the eroded weld joint sample.

[0100] Specifically, step S104 can rinse the corroded welding joint sample with clean water and use hot air to blow dry the rinsed welding joint sample, thereby completing the rinsing and drying process of the corroded welding joint sample to further improve the accuracy of subsequent image recognition results.

[0101] Exemplarily, step S110 includes: taking photographs of the weld joint samples after the rinsing and drying processes to obtain a sampling image.

[0102] Specifically, when taking photos and sampling, the girth weld of the welded joint sample should be completely included in the field of view of the camera lens, so that the sampling image obtained by taking photos and sampling can include the complete image of the girth weld. In particular, the sampling image should include a complete front image of the girth weld without distortion, so as to further improve the accuracy of the geometric dimension recognition of the girth weld contour.

[0103] In order to enable those skilled in the art to better understand the above implementation, a specific example is used as an example for description below.

[0104] like Figure 3 As shown, a method for identifying the geometric dimensions of a girth weld profile comprises the following steps:

[0105] Step 1: cutting samples: using a metallographic sample cutting machine to cut the welder joint sample to be processed from the oil and gas pipeline, the welder joint sample including the girth weld.

[0106] Step 2: Grind and polish the sample: Use mechanical methods such as rough grinding, fine grinding, rough polishing, and fine polishing to remove the wear marks and deformation layer produced by grinding on the welder joint sample to ensure that the surface of the welder joint sample becomes a smooth mirror. Specifically, for welder joint samples with particularly poor surface quality, they can first be rough ground using a grinding wheel machine, a grinding wheel, etc.; then, sandpaper of different mesh sizes can be used to perform rough grinding, fine grinding, etc. on them. The final quality of the metallographic sample is determined by the polishing process, and polishing is a crucial part of the metallographic sample preparation process. Therefore, when polishing the welder joint sample after grinding, polishing fabrics, diamond spray polishing agents, etc. can be used to perform rough and fine polishing on the welder joint sample after grinding. For example, the welder joint sample after grinding is first rough polished to remove the polishing damage layer; then the welder joint sample after rough polishing is fine polished to remove the surface damage caused by rough polishing and minimize the polishing damage.

[0107] Step 3: Sample erosion: Use 3% nitric acid alcohol solution (which can be configured according to the characteristics of the sample material) to wipe the polished surface of the weld joint sample. The wiping time is determined according to the specific situation. The erosion goal is to finally highlight the contour shape of the girth weld in the weld joint sample, so that a more accurate girth weld contour image can be obtained in the subsequent steps to ensure the accuracy of the subsequent results.

[0108] Step 4: Sample image acquisition: Rinse the corroded welding joint sample with clean water, and blow dry the rinsed welding joint sample with hot air, then take photos of the blow-dried welding joint sample to obtain a sampling image of the welding joint sample, which includes a complete front image of the circumferential weld in the welding joint sample without distortion.

[0109] Step 5: Image normalization: Convert the sampled image to a unique standard form to resist various transformations, thereby eliminating the appearance differences between different shapes. Specifically, use MATLAB software to perform grayscale normalization on the sampled image so that the grayscale value of each pixel in the sampled image is between 0 and 255, and obtain a normalized image, thereby avoiding interference with subsequent processing caused by insufficient image contrast angle. After normalization, the relative positions of the components in the welded joint sample can be easily obtained using the normalized image.

[0110] Step 6: Image enhancement and graphic refinement: By performing image enhancement and graphic refinement processing on the normalized image, the information in the image can be selectively enhanced or suppressed to obtain an image of the geometric structure of the girth weld contour, thereby improving the image visual effect, accurately obtaining the geometric structure of the girth weld contour in the image, and converting the image into a form more suitable for machine processing, facilitating data recognition and extraction, and ensuring the accuracy and reliability of subsequent calculation results.

[0111] Step 7: Image decomposition and reconstruction: Based on two-dimensional wavelet, the geometric structure image of the girth weld contour is decomposed multiple times, and the image is reconstructed multiple times according to the decomposed image, so as to realize the reconstruction of the original image, i.e., the geometric structure image of the girth weld contour, by two-dimensional wavelet decomposition to obtain a reconstructed image.

[0112] Step 8: Coordinate extraction: Use MATLAB software to extract the coordinates of each contour edge point in the reconstructed image, form an Excel file with the extracted coordinates, and generate the coordinate values ​​corresponding to each contour edge point in the Excel file, and convert the coordinate values ​​into a format that can be called and recognized by Auto CAD software.

[0113] Step 9: Export CAD file: Import the Excel file that can be called and recognized by Auto CAD software and includes the coordinate values ​​of each contour edge point into Auto CAD software, so that Auto CAD software can generate a weld joint specimen geometry including the contour pattern of the girth weld and its geometric dimensions based on the coordinate values.

[0114] Another embodiment of the present disclosure relates to a device for identifying the geometric dimensions of a girth weld profile, such as Figure 4 As shown, including:

[0115] An acquisition module 410 is used to acquire a sampling image of the weld joint sample, wherein the sampling image includes a complete image of the girth weld in the weld joint sample;

[0116] A normalization module 420 is used to perform normalization processing on the sampled image, convert the sampled image into a preset format, and obtain a normalized image;

[0117] A refinement module 430 is used to perform image enhancement and image refinement processing on the normalized image to obtain a geometric structure image of the girth weld contour;

[0118] A reconstruction module 440 is used to decompose and reconstruct the geometric structure image of the girth weld contour to obtain a reconstructed image;

[0119] An extraction module 450 is used to extract the coordinates of the contour edge points in the reconstructed image to obtain a coordinate set of the contour edge points;

[0120] The generation module 460 is used to generate a welding joint sample geometry figure according to a set of contour edge point coordinates, wherein the welding joint sample geometry figure includes a contour pattern of the girth weld and its geometric dimensions.

[0121] Exemplarily, the normalization module 420 is used to perform normalization processing on the sampled image, convert the sampled image into a preset format, and obtain a normalized image, including:

[0122] The normalization module 420 is specifically used to perform grayscale normalization processing on the sampled image so that the grayscale value of each pixel is distributed between [0, 255] to obtain a normalized image.

[0123] Exemplarily, the reconstruction module 440 is used to decompose and reconstruct the girth weld contour geometric structure image to obtain a reconstructed image, including:

[0124] The reconstruction module 440 is specifically used to perform multiple decompositions and reconstructions on the geometric structure image of the girth weld contour based on two-dimensional wavelets to obtain a reconstructed image.

[0125] Exemplarily, the extraction module 450 is used to extract the coordinates of the contour edge points in the reconstructed image to obtain a contour edge point coordinate set, including:

[0126] The extraction module 450 is specifically used to: use MATLAB software to extract the coordinates of each contour edge point in the reconstructed image, and form an Excel file with the extracted coordinates.

[0127] Exemplarily, the generating module 460 is used to generate the welding joint specimen geometry according to the contour edge point coordinate set, including:

[0128] The generation module 460 is specifically used for: generating coordinate values ​​corresponding to each contour edge point based on the Excel file; and importing the coordinate values ​​into the Auto CAD software to generate the geometric figure of the welding joint sample.

[0129] For example, Figure 5 As shown, the device for identifying the geometric dimensions of the girth weld profile also includes:

[0130] A cutting module 401 is used to cut the weld joint sample to be processed from the pipeline;

[0131] The polishing module 402 is used to grind and polish the weld joint sample by mechanical method to obtain the processed weld joint sample;

[0132] The etching module 403 is used to use a nitric acid alcohol solution of a preset concentration to perform etching on the treated weld joint sample to highlight the contour shape of the girth weld and obtain the weld joint sample after etching;

[0133] The flushing and drying module 404 is used to flush and dry the weld joint sample after corrosion.

[0134] Exemplarily, the acquisition module 410 is used to acquire a sampling image of a welding joint sample, including:

[0135] The acquisition module 410 is specifically used to take photos and samples of the welding joint samples after the washing and drying treatments to obtain the sampling images.

[0136] The specific implementation method of the device for identifying the geometric dimensions of the girth weld contour provided in the embodiment of the present disclosure can be found in the method for identifying the geometric dimensions of the girth weld contour provided in the embodiment of the present disclosure, and will not be repeated here.

[0137] Compared with the prior art, the disclosed embodiments effectively realize the rapid and accurate identification of the girth weld contour and its geometric dimensions in the weld joint specimen, greatly shorten the measurement period of the girth weld contour geometric dimensions, reduce the complexity of the measurement, and improve the identification accuracy of the girth weld geometric dimensions. It has high practical application value for the identification of the geometric dimensions of the weld contour of the weld joint, and is in line with the trend of intelligent development.

[0138] Another embodiment of the present disclosure relates to an electronic device, such as Figure 6 As shown, including:

[0139] at least one processor 601; and,

[0140] A memory 602 is communicatively connected to at least one processor 601; wherein,

[0141] The memory 602 stores instructions that can be executed by at least one processor 601. The instructions are executed by at least one processor 601 so that the at least one processor 601 can execute the method for identifying the geometric dimensions of the girth weld profile described in the above embodiment.

[0142] Among them, the memory and the processor are connected in a bus manner, and the bus may include any number of interconnected buses and bridges, and the bus connects various circuits of one or more processors and memories together. The bus can also connect various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be one element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on a transmission medium. The data processed by the processor is transmitted on a wireless medium via an antenna, and further, the antenna also receives data and transmits the data to the processor.

[0143] The processor is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory can be used to store data used by the processor when performing operations.

[0144] Another embodiment of the present disclosure relates to a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method for identifying the geometric dimensions of the girth weld profile described in the above embodiment.

[0145] That is, those skilled in the art can understand that all or part of the steps in the method described in the above embodiments can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including several instructions for making a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

[0146] Those skilled in the art will appreciate that the above-mentioned embodiments are specific embodiments for implementing the present disclosure, and in actual applications, various changes may be made thereto in form and detail without departing from the spirit and scope of the present disclosure.

Claims

1. A method for identifying the geometric dimensions of a girth weld profile, characterized in that: The identification method comprises: Acquire a sampling image of the weld joint sample, wherein the sampling image includes a complete image of the girth weld in the weld joint sample; Normalizing the sampled image, converting the sampled image into a preset format, and obtaining a normalized image; Performing image enhancement and graphic refinement processing on the normalized image to obtain a geometric structure image of the girth weld contour; Decomposing and reconstructing the geometric structure image of the girth weld contour to obtain a reconstructed image; Extracting the coordinates of the contour edge points in the reconstructed image to obtain a contour edge point coordinate set; A welding joint sample geometry is generated according to the contour edge point coordinate set, wherein the welding joint sample geometry includes a contour pattern of the girth weld and its geometric dimensions.

2. The identification method according to claim 1, characterized in that: The normalizing the sampled image to convert the sampled image into a preset format to obtain a normalized image includes: The sampled image is subjected to grayscale normalization processing so that the grayscale value of each pixel is distributed between [0, 255], thereby obtaining the normalized image.

3. The identification method according to claim 1, characterized in that: Decomposing and reconstructing the geometric structure image of the girth weld contour to obtain a reconstructed image includes: Based on two-dimensional wavelet, the geometric structure image of the girth weld contour is decomposed and reconstructed multiple times to obtain the reconstructed image.

4. The identification method according to any one of claims 1 to 3, characterized in that: The step of extracting the coordinates of the contour edge points in the reconstructed image to obtain a set of contour edge point coordinates includes: MATLAB software is used to extract the coordinates of each of the contour edge points in the reconstructed image, and the extracted coordinates are formed into an Excel file.

5. The identification method according to claim 4, characterized in that: The step of generating a weld joint specimen geometry according to the contour edge point coordinate set comprises: Based on the Excel file, generate coordinate values ​​corresponding to each of the contour edge points; The coordinate values ​​are imported into Auto CAD software to generate the geometric figure of the weld joint specimen.

6. The identification method according to any one of claims 1 to 3, characterized in that: Before acquiring the sampling image of the welding joint sample, the identification method further includes: Cutting the weld joint sample to be processed from the pipeline; Mechanically grinding and polishing the weld joint sample to obtain the weld joint sample after treatment; Using a nitric acid alcohol solution of a preset concentration to erode the treated weld joint sample to highlight the contour shape of the girth weld, thereby obtaining the eroded weld joint sample; The welded joint specimens after etching are rinsed and blown dry.

7. The identification method according to claim 6, characterized in that: The method of obtaining a sampling image of a welding joint sample comprises: The welding joint sample after the rinsing and drying treatment is photographed and sampled to obtain the sampling image.

8. A device for identifying the geometric dimensions of a girth weld profile, characterized in that: The identification device comprises: An acquisition module, used for acquiring a sampling image of a weld joint sample, wherein the sampling image includes a complete image of a girth weld in the weld joint sample; A normalization module, used for performing normalization processing on the sampled image, converting the sampled image into a preset format, and obtaining a normalized image; A refinement module, used for performing image enhancement and image refinement processing on the normalized image to obtain a geometric structure image of the girth weld contour; A reconstruction module, used for decomposing and reconstructing the geometric structure image of the girth weld contour to obtain a reconstructed image; An extraction module, used for extracting the coordinates of the contour edge points in the reconstructed image to obtain a coordinate set of the contour edge points; A generation module is used to generate a welding joint sample geometry figure according to the contour edge point coordinate set, wherein the welding joint sample geometry figure includes the contour pattern of the girth weld and its geometric dimensions.

9. An electronic device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method for identifying the geometric dimensions of the girth weld profile according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for identifying the geometric dimensions of the girth weld profile according to any one of claims 1 to 7 is implemented.