Large-diameter straight-seam double-sided submerged arc welding steel pipe detection method and system

Abstract

The application provides a large-diameter straight-seam double-sided submerged arc welding steel pipe detection method and system, belonging to the technical field of industrial image processing. The method obtains thermal source images of the same position of the steel pipe at different times through two infrared thermal imaging sensors, determines a target area by using image processing and analysis technology, and judges the welding quality based on the characteristics of the target area, thereby realizing real-time monitoring and quality detection of the welding process. The method can obtain images in real time during the welding process and analyze them, timely discovers welding quality defects through changes in the surface temperature, and facilitates operators to timely adjust welding parameters, thereby improving the welding quality.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of industrial image processing, and in particular to a large-diameter straight-seam double-sided submerged arc welded steel pipe detection method and system. BACKGROUND

[0002] Large-diameter straight-seam double-sided submerged arc welded steel pipes are widely used in many fields such as petroleum, natural gas, and water conservancy, and the welding quality thereof is directly related to the safety and reliability of the project. During the welding process, various quality defects such as cracks, incomplete fusion, and pores may occur, and these defects may cause serious safety accidents if not detected in time.

[0003] When the local temperature rises too slowly, the gas in the molten pool cannot escape in time and is wrapped by the solidified metal, forming pores. Such defects are formed in the material and cannot be directly identified. SUMMARY

[0004] The embodiments of the present application provide a large-diameter straight-seam double-sided submerged arc welded steel pipe detection method and system to improve the above problems.

[0005] To achieve the above purpose, the technical scheme is as follows:

[0006] In a first aspect, the present application provides a large-diameter straight-seam double-sided submerged arc welded steel pipe detection method, which is applicable to a steel pipe welding system including a first infrared thermal imaging sensor, a second infrared thermal imaging sensor, a welding device, and a control terminal. The welding device moves along a first direction in which the steel pipe extends and welds one side surface of the steel pipe. The welding device, the first infrared thermal imaging sensor, and the second infrared thermal imaging sensor are arranged in a second direction opposite to the first direction in sequence. The method is applicable to the control terminal and includes:

[0007] Obtaining a first heat source image based on the first infrared thermal imaging sensor and a second heat source image based on the second infrared sensor, the positions of the first heat source image and the second heat source image on the steel pipe being the same;

[0008] Determining a target region from the second heat source image based on the first heat source image and the second heat source image;

[0009] Determining whether a quality defect occurs in the welding process of the steel pipe based on the region features of the target region.

[0010] In combination with the first aspect, the first heat source image is obtained based on the first infrared thermal imaging sensor, and the second heat source image is obtained based on the second infrared sensor, the positions of the first heat source image and the second heat source image on the steel pipe being the same, and the method includes:

[0011] the first video acquired by the first infrared thermal image sensor and the second video acquired by the second infrared thermal image sensor;

[0012] an interval distance between the first infrared thermal image sensor and the second infrared thermal image sensor, and a welding speed of the welding device when welding the steel pipe;

[0013] determining the first heat source image and the second heat source image based on the first video, the second video, the interval distance and the welding speed.

[0014] With reference to the first aspect, optionally, determining the first heat source image and the second heat source image based on the first video, the second video, the interval distance and the welding speed comprises:

[0015] determining an Mth frame image in the first video as the first heat source image and an Nth frame image in the second video as the second heat source image, wherein a difference between a shooting time corresponding to the Mth frame image and a shooting time corresponding to the Nth frame image is an interval time, and the interval time is equal to the interval distance divided by the welding speed.

[0016] With reference to the first aspect, optionally, determining the target region from the second heat source image based on the first heat source image and the second heat source image comprises:

[0017] determining a predicted heat source image based on the first heat source image;

[0018] comparing the predicted heat source image with the second heat source image, and determining the target region from the second heat source image according to a comparison result.

[0019] With reference to the first aspect, optionally, determining the predicted image based on the first heat source image comprises:

[0020] segmenting the first heat source image to form a plurality of sub heat source images, and determining temperature data corresponding to each sub heat source image based on the first heat source image;

[0021] acquiring a steel pipe heat diffusion model, and corresponding each sub heat source image with a plurality of target volume regions on the steel pipe heat diffusion model based on position information of each sub heat source image;

[0022] acquiring a target heat diffusion model based on the steel pipe heat diffusion model;

[0023] determining second temperature data corresponding to the plurality of sub heat source images based on second temperature data corresponding to the plurality of target volume regions in the target heat diffusion model;

[0024] determining the predicted heat source image based on the plurality of second temperature data.

[0025] Optionally, in combination with the first aspect, the target region is determined from the second heat source image based on a comparison result of the predicted heat source image and the second heat source image, and the determining includes:

[0026] The second heat source image is segmented to form a plurality of sub-target images, and the plurality of sub-target images correspond to the plurality of sub heat source images;

[0027] Each of the sub-target images is compared with the sub heat source image, and a region formed by sub-target images different from the corresponding sub heat source images in the plurality of sub-target images is determined as the target region.

[0028] Optionally, in combination with the first aspect, the target region is determined from the second heat source image based on the first heat source image and the second heat source image, and the determining includes:

[0029] The first heat source image is segmented to form a plurality of sub heat source images, and temperature data corresponding to each of the sub heat source images is determined based on the first heat source image;

[0030] The second heat source image is segmented to form a plurality of sub-target images, and the plurality of sub-target images correspond to the plurality of sub heat source images, and target temperature data corresponding to each of the sub-target images is determined based on the second heat source image;

[0031] Based on the corresponding relationship between the sub-target images and the sub heat source images, a temperature difference value of each pair of corresponding sub-target images and sub heat source images is determined;

[0032] Based on the position information of each of the sub-target images, a difference value of the temperature difference value of each pair of corresponding sub-target images and sub heat source images and the temperature difference values of all adjacent pairs of sub-target images and sub heat source images is determined;

[0033] A preset difference value is obtained, and the preset difference value is compared with the temperature difference value, and if the temperature difference value of a pair of sub-target images and sub heat source images is greater than the preset difference value, the sub-target image is determined as a target region boundary sub-image;

[0034] Based on the position information of the target region boundary sub-image in the second heat source image, a corresponding boundary of the target region is fitted, and the target region is determined.

[0035] Optionally, in combination with the first aspect, based on the region feature of the target region, it is determined whether a quality defect occurs in the welding process of the steel pipe, and the determining includes:

[0036] The region feature of the target region is obtained, and the region feature includes an area of the target region, temperature data in the target region, and a shape of the target region;

[0037] Obtain the preset area threshold, preset temperature range, and preset shape parameter range;

[0038] The regional characteristics are compared with preset area thresholds, preset temperature ranges, and preset shape parameter ranges. Based on the comparison results, it is determined whether the steel pipe has quality defects.

[0039] Secondly, this application proposes a large-diameter straight-seam double-sided submerged arc welded steel pipe inspection system, including a first infrared thermal imaging sensor, a second infrared thermal imaging sensor, a welding device, and a control terminal. The welding device moves along a first direction extending from the steel pipe and welds one side surface of the steel pipe. The welding device, the first infrared thermal imaging sensor, and the second infrared thermal imaging sensor are sequentially and collinearly arranged in a second direction opposite to the first direction. The system is configured as follows:

[0040] A first heat source image is acquired based on a first infrared thermal imaging sensor, and a second heat source image is acquired based on a second infrared sensor. The first heat source image and the second heat source image are located at the same position on the steel pipe.

[0041] Based on the first heat source image and the second heat source image, the target area is determined from the second heat source image;

[0042] Based on the regional characteristics of the target area, determine whether quality defects occur in the steel pipe during the welding process.

[0043] Optionally, the system is configured as follows:

[0044] A first heat source image is acquired based on a first infrared thermal imaging sensor, and a second heat source image is acquired based on a second infrared sensor. The first and second heat source images are located at the same position on the steel pipe, including:

[0045] The first video acquired by the first infrared thermal imaging sensor and the second video acquired by the second infrared thermal imaging sensor;

[0046] The distance between the first infrared thermal image sensor and the second infrared thermal image sensor, as well as the welding speed of the welding device when welding along the steel pipe, are obtained.

[0047] The first heat source image and the second heat source image are determined based on the first video, the second video, the interval distance, and the welding speed.

[0048] Optionally, the system is configured as follows:

[0049] The first heat source image and the second heat source image are determined based on the first video, the second video, the interval distance, and the welding speed, including:

[0050] The Mth frame image is determined as the first heat source image from the first video, and the Nth frame image is determined as the second heat source image from the second video. The difference between the shooting time corresponding to the Mth frame image and the shooting time corresponding to the Nth frame image is the interval time, which is equal to the interval distance divided by the welding speed.

[0051] Optionally, the system is configured as follows:

[0052] Based on the first heat source image and the second heat source image, the target region is determined from the second heat source image, including:

[0053] Determine the predicted heat source image based on the first heat source image;

[0054] The predicted heat source image is compared with the second heat source image, and the target region is determined from the second heat source image based on the comparison results.

[0055] Optionally, the system is configured as follows:

[0056] The predicted image is determined based on the first heat source image, including:

[0057] The first heat source image is segmented to form multiple sub-heat source images, and the temperature data corresponding to each sub-heat source image is determined based on the first heat source image.

[0058] The heat diffusion model of the steel pipe is obtained, and based on the location information of each sub-heat source image, each sub-heat source image is associated with multiple target volume regions on the heat diffusion model of the steel pipe.

[0059] Based on the thermal diffusion model of steel pipe, obtain the target thermal diffusion model;

[0060] Based on the second temperature data corresponding to multiple target volume regions in the target heat diffusion model, the second temperature data corresponding to multiple sub-heat source images are determined.

[0061] The predicted heat source image is determined based on multiple secondary temperature data.

[0062] Optionally, the system is configured as follows:

[0063] The predicted heat source image is compared with the second heat source image. Based on the comparison results, the target region is determined from the second heat source image, including:

[0064] The second heat source image is segmented to form multiple sub-target images, and the multiple sub-target images correspond to multiple sub-heat source images;

[0065] Each sub-target image is compared with the sub-heat source image, and the region composed of sub-target images that are different from the corresponding sub-heat source image is identified as the target region.

[0066] Optionally, the system is configured as follows:

[0067] Based on the first heat source image and the second heat source image, the target region is determined from the second heat source image, including:

[0068] The first heat source image is segmented to form multiple sub-heat source images, and the temperature data corresponding to each sub-heat source image is determined based on the first heat source image.

[0069] The second heat source image is segmented to form multiple sub-target images, which correspond to multiple sub-heat source images. The target temperature data corresponding to each sub-target image is determined based on the second heat source image.

[0070] Based on the correspondence between sub-target images and sub-heat source images, the temperature difference between each pair of corresponding sub-target images and sub-heat source images is determined.

[0071] Based on the location information of each sub-target image, determine the temperature difference between each pair of corresponding sub-target images and sub-heat source images, and the difference between the temperature difference between each pair of adjacent sub-target images and sub-heat source images;

[0072] Obtain a preset difference value and compare the preset difference value with the temperature difference value. If the temperature difference value between a pair of sub-target images and sub-heat source images is greater than the temperature difference value between two adjacent pairs of sub-target images and sub-heat source images, then the sub-target image is determined to be the target region boundary sub-image.

[0073] Based on the location information of the target region boundary sub-image in the second heat source image, the corresponding boundary of the target region is fitted, and the target region is determined.

[0074] Optionally, the system is configured as follows:

[0075] Based on the regional characteristics of the target area, determine whether quality defects occur in the steel pipe during the welding process, including:

[0076] Extract the regional features of the target region, which include the area of ​​the target region, the temperature data within the target region, and the shape of the target region.

[0077] Obtain the preset area threshold, preset temperature range, and preset shape parameter range;

[0078] The regional characteristics are compared with preset area thresholds, preset temperature ranges, and preset shape parameter ranges. Based on the comparison results, it is determined whether the steel pipe has quality defects.

[0079] A third aspect of this invention provides an electronic device, which includes:

[0080] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method proposed in the first aspect of the present invention.

[0081] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method as described in the first aspect of the present invention.

[0082] In summary, the above methods and systems have the following technical effects:

[0083] The large-diameter straight-seam double-sided submerged arc welded steel pipe inspection system provided in this application acquires heat source images of the same location on the steel pipe at different times using two infrared thermal imaging sensors. Image processing and analysis techniques are then used to determine the target area, and the welding quality is judged based on the characteristics of the target area, achieving real-time monitoring and quality inspection of the welding process. It can acquire and analyze images in real time during the welding process, promptly detecting welding quality defects through changes in surface temperature, facilitating timely adjustment of welding parameters by operators, and improving welding quality. Attached Figure Description

[0084] Figure 1 This is a flowchart illustrating a method for inspecting large-diameter straight-seam double-sided submerged arc welded steel pipes proposed in an embodiment of this application. Detailed Implementation

[0085] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0086] This application proposes a method for inspecting large-diameter straight-seam double-sided submerged arc welded steel pipes. The method is applicable to a steel pipe welding system, which includes a first infrared thermal imaging sensor, a second infrared thermal imaging sensor, a welding device, and a control terminal. The welding device moves along a first direction extending from the steel pipe and welds one side of the pipe. The welding device, the first infrared thermal imaging sensor, and the second infrared thermal imaging sensor are sequentially and collinearly arranged in a second direction opposite to the first direction. The method is applicable to the control terminal. (See attached image for details.) Figure 1 The method includes the following steps:

[0087] S101: Obtain a first heat source image based on a first infrared thermal imaging sensor, and obtain a second heat source image based on a second infrared sensor. The first heat source image and the second heat source image are located at the same position on the steel pipe.

[0088] Understandably, the first and second infrared thermal imaging sensors acquire images of the heat source at the same location on the steel pipe. Specifically, the two sensors first acquire a first video and a second video, respectively; then, the distance between the two sensors and the welding speed of the welding device are acquired; and finally, the first and second heat source images are determined based on these data.

[0089] Because the welding device and the two sensors are positioned along a specific direction, and the welding device is in motion, to ensure that the two images correspond to the same position on the steel pipe, an interval time needs to be calculated—the interval time is equal to the distance between the two sensors divided by the welding speed. Then, the Mth frame is selected from the first video as the first heat source image, and the Nth frame is selected from the second video as the second heat source image, ensuring that the time difference between the capture of these two frames is exactly equal to the aforementioned interval time. This guarantees that they are positioned identically on the steel pipe, providing a precise comparison basis for subsequent detection.

[0090] Specifically, based on the first video acquired by the first infrared thermal imaging sensor and the second video acquired by the second infrared thermal imaging sensor, the distance between the first and second infrared thermal imaging sensors and the welding speed of the welding device when welding along the steel pipe can be obtained. Then, the first heat source image and the second heat source image can be determined based on the first video, the second video, the distance, and the welding speed.

[0091] S102: Based on the first heat source image and the second heat source image, determine the target area from the second heat source image.

[0092] Based on the first heat source image and the second heat source image, the target region is determined from the second heat source image.

[0093] One implementation method involves determining a predicted heat source image based on a first heat source image, and then comparing it with a second heat source image. Specifically, the first heat source image is first segmented into multiple sub-heat source images, and the temperature data of each sub-image is obtained. Then, using a steel pipe heat diffusion model, the sub-heat source images are mapped to target volume regions on the model. The model is used to obtain the second temperature data corresponding to each sub-heat source image, thereby determining the predicted heat source image. Next, the second heat source image is also segmented into multiple sub-target images corresponding to the sub-heat source images. Each sub-target image is compared with its corresponding sub-heat source image; the region formed by the sub-target images that show differences is the target region.

[0094] For example, in this embodiment, the predicted heat source image can be determined based on the first heat source image;

[0095] The predicted heat source image is compared with the second heat source image, and the target region is determined from the second heat source image based on the comparison results.

[0096] Specifically, the first heat source image can be segmented to form multiple sub-heat source images, and the temperature data corresponding to each sub-heat source image can be determined based on the first heat source image to obtain a steel pipe heat diffusion model. Based on the position information of each sub-heat source image, each sub-heat source image is associated with multiple target volume regions on the steel pipe heat diffusion model. Based on the steel pipe heat diffusion model, a target heat diffusion model is obtained. Then, based on the second temperature data corresponding to the multiple target volume regions in the target heat diffusion model, the second temperature data corresponding to the multiple sub-heat source images is determined. Finally, the predicted heat source image is determined based on the multiple second temperature data.

[0097] Understandably, the first heat source image is divided into multiple sub-heat source images and the corresponding temperature data is obtained. Combined with the steel pipe heat diffusion model, the target heat diffusion model and related second temperature data are obtained by matching the sub-heat source image location information with the target volume region on the model to determine the predicted heat source image.

[0098] Then, the second heat source image is segmented to form multiple sub-target images, and the multiple sub-target images correspond to multiple sub-heat source images;

[0099] Each sub-target image is compared with the sub-heat source image, and the region composed of sub-target images that are different from the corresponding sub-heat source image is identified as the target region.

[0100] Understandably, segmenting the sub-heat source image allows for more detailed temperature data acquisition. The correspondence between this sub-image and the target volume region in the steel pipe heat diffusion model ensures that temperature change predictions closely match the heat transfer characteristics during steel pipe welding. Based on this, the resulting predicted heat source image accurately reflects the expected heat source distribution at the same location over subsequent times, laying a precise foundation for comparison with the second heat source image and significantly reducing misjudgments of the target area due to prediction bias. Simultaneously, the systematic data processing and prediction using the heat diffusion model replaces manual speculation on complex heat source changes, rapidly generating predicted heat source images and improving the overall efficiency of target area determination.

[0101] In some other implementations, the target area may be determined by the following steps.

[0102] S201: Divide the first heat source image into multiple sub-heat source images, and determine the temperature data corresponding to each sub-heat source image based on the first heat source image.

[0103] Specifically, the first heat source image is divided into multiple sub-heat source images according to preset rules (such as uniform grid division). This decomposes the original overall heat source information into smaller units, facilitating more detailed analysis of temperature distribution. Simultaneously, based on the temperature field information contained in the first heat source image, temperature data corresponding to each sub-heat source image is extracted. This temperature data accurately reflects the thermal status of that sub-region at the time of capture, laying a data foundation for subsequent comparison with sub-regions of the second heat source image.

[0104] S202: The second heat source image is segmented to form multiple sub-target images, which correspond to multiple sub-heat source images. The target temperature data corresponding to each sub-target image is determined based on the second heat source image.

[0105] S203: Based on the correspondence between the sub-target image and the sub-heat source image, determine the temperature difference between each pair of corresponding sub-target images and sub-heat source images.

[0106] Understandably, based on the correspondence between the sub-target images and sub-heat source images established in S201 and S202, the temperature data of each pair of corresponding sub-target images and sub-heat source images are compared to obtain the temperature difference for each pair of sub-images. This temperature difference directly reflects the temperature change of the same sub-region at two different times, and is an important basis for judging whether there are any anomalies in the region.

[0107] S204: Based on the location information of each sub-target image, determine the temperature difference between each pair of corresponding sub-target images and sub-heat source images, and the difference between the temperature difference between each pair of adjacent sub-target images and sub-heat source images.

[0108] This is understandable. Based on the position information of each sub-target image in the second heat source image, the temperature difference value corresponding to its adjacent sub-target images is determined. Then, the difference value between the temperature difference value of each pair of sub-images and the temperature difference values ​​of all adjacent pairs of sub-images is calculated. This difference value can reflect the abrupt change in temperature. If the temperature difference value at a certain location shows a large abrupt change compared with the adjacent locations, then that location may be at the boundary of an abnormal region.

[0109] S205: Obtain a preset difference value and compare the preset difference value with the temperature difference value. If the temperature difference value between a pair of sub-target images and sub-heat source images is greater than the temperature difference value between two adjacent pairs of sub-target images and sub-heat source images, then determine the sub-target image as the target area boundary sub-image.

[0110] Understandably, the calculated difference value is compared with the preset difference value. If the temperature difference between a pair of sub-target images and the sub-heat source image is greater than the temperature difference between two adjacent pairs, it indicates that the temperature change at the location of the sub-target image has undergone an abnormal change. Therefore, the sub-target image is identified as the boundary sub-image of the target area. These boundary sub-images are the key elements constituting the boundary of the abnormal area.

[0111] S206: Based on the position information of the target region boundary sub-image in the second heat source image, fit the corresponding boundary of the target region and determine the target region.

[0112] Understandably, based on the positional information of all target region boundary sub-images obtained in S205 within the second heat source image, a suitable fitting algorithm (such as curve fitting, polygon fitting, etc.) is used to connect these boundary sub-images and fit the boundary corresponding to the target region. This boundary clearly defines the area in the second heat source image where abnormal heat distribution exists, thus identifying the target region. This target region is the key analysis object for subsequent judgment of whether there are quality defects in the steel pipe welding.

[0113] S103: Based on the regional characteristics of the target area, determine whether quality defects occur in the steel pipe during the welding process.

[0114] Specifically, the regional features of the target area can be obtained, including the area of ​​the target area, the temperature data within the target area, and the shape of the target area. Then, a preset area threshold, a preset temperature range, and a preset shape parameter range are obtained. Finally, the regional features are compared with the preset area threshold, preset temperature range, and preset shape parameter range, and the comparison results are used to determine whether the steel pipe has quality defects.

[0115] For example, if the area of ​​the target region is less than or equal to a preset area threshold, the temperature data within the target region is compared with a preset target temperature range. If the temperature data within the target region exceeds the preset temperature range, it is preliminarily determined that the steel pipe may have quality defects.

[0116] If the area of ​​the target region is less than or equal to the preset area threshold, and the temperature data within the target region is within the preset temperature range, then the shape of the target region is compared with the preset shape parameter range. If the shape of the target region exceeds the preset shape parameter range, then the steel pipe is determined to have a quality defect. If the shape of the target region is within the preset shape parameter range, then the steel pipe is determined not to have a quality defect.

[0117] Understandably, when defects such as pores appear inside a material, the actual cooling rate of the corresponding area will be affected to some extent. Due to the presence of defects, the cooling rate of the corresponding area may be slower than when there are no defects. Therefore, the temperature change in the corresponding area can indicate whether defects are present.

[0118] The method for inspecting large-diameter straight-seam double-sided submerged arc welded steel pipes provided in this application acquires heat source images of the same location on the steel pipe at different times using two infrared thermal imaging sensors. Image processing and analysis techniques are then used to determine the target area, and the welding quality is judged based on the characteristics of the target area, achieving real-time monitoring and quality inspection of the welding process. This method enables real-time image acquisition and analysis during the welding process, allowing for timely detection of welding quality defects through changes in surface temperature. This facilitates operators in adjusting welding parameters promptly, thereby improving welding quality.

[0119] Based on the same inventive concept, this application also proposes a large-diameter straight-seam double-sided submerged arc welded steel pipe inspection system, including a first infrared thermal imaging sensor, a second infrared thermal imaging sensor, a welding device, and a control terminal. The welding device moves along a first direction of the steel pipe extension and welds one side surface of the steel pipe. The welding device, the first infrared thermal imaging sensor, and the second infrared thermal imaging sensor are sequentially and collinearly arranged in a second direction opposite to the first direction. The system is configured as follows:

[0120] A first heat source image is acquired based on a first infrared thermal imaging sensor, and a second heat source image is acquired based on a second infrared sensor. The first heat source image and the second heat source image are located at the same position on the steel pipe.

[0121] Based on the first heat source image and the second heat source image, the target area is determined from the second heat source image;

[0122] Based on the regional characteristics of the target area, determine whether quality defects occur in the steel pipe during the welding process.

[0123] Optionally, the system is configured as follows:

[0124] A first heat source image is acquired based on a first infrared thermal imaging sensor, and a second heat source image is acquired based on a second infrared sensor. The first and second heat source images are located at the same position on the steel pipe, including:

[0125] The first video acquired by the first infrared thermal imaging sensor and the second video acquired by the second infrared thermal imaging sensor;

[0126] The distance between the first infrared thermal image sensor and the second infrared thermal image sensor, as well as the welding speed of the welding device when welding along the steel pipe, are obtained.

[0127] The first heat source image and the second heat source image are determined based on the first video, the second video, the interval distance, and the welding speed.

[0128] Optionally, the system is configured as follows:

[0129] The first heat source image and the second heat source image are determined based on the first video, the second video, the interval distance, and the welding speed, including:

[0130] The Mth frame image is determined as the first heat source image from the first video, and the Nth frame image is determined as the second heat source image from the second video. The difference between the shooting time corresponding to the Mth frame image and the shooting time corresponding to the Nth frame image is the interval time, which is equal to the interval distance divided by the welding speed.

[0131] Optionally, the system is configured as follows:

[0132] Based on the first heat source image and the second heat source image, the target region is determined from the second heat source image, including:

[0133] Determine the predicted heat source image based on the first heat source image;

[0134] The predicted heat source image is compared with the second heat source image, and the target region is determined from the second heat source image based on the comparison results.

[0135] Optionally, the system is configured as follows:

[0136] The predicted image is determined based on the first heat source image, including:

[0137] The first heat source image is segmented to form multiple sub-heat source images, and the temperature data corresponding to each sub-heat source image is determined based on the first heat source image.

[0138] The heat diffusion model of the steel pipe is obtained, and based on the location information of each sub-heat source image, each sub-heat source image is associated with multiple target volume regions on the heat diffusion model of the steel pipe.

[0139] Based on the thermal diffusion model of steel pipe, obtain the target thermal diffusion model;

[0140] Based on the second temperature data corresponding to multiple target volume regions in the target heat diffusion model, the second temperature data corresponding to multiple sub-heat source images are determined.

[0141] The predicted heat source image is determined based on multiple secondary temperature data.

[0142] Optionally, the system is configured as follows:

[0143] The predicted heat source image is compared with the second heat source image. Based on the comparison results, the target region is determined from the second heat source image, including:

[0144] The second heat source image is segmented to form multiple sub-target images, and the multiple sub-target images correspond to multiple sub-heat source images;

[0145] Each sub-target image is compared with the sub-heat source image, and the region composed of sub-target images that are different from the corresponding sub-heat source image is identified as the target region.

[0146] Optionally, the system is configured as follows:

[0147] Based on the first heat source image and the second heat source image, the target region is determined from the second heat source image, including:

[0148] The first heat source image is segmented to form multiple sub-heat source images, and the temperature data corresponding to each sub-heat source image is determined based on the first heat source image.

[0149] The second heat source image is segmented to form multiple sub-target images, which correspond to multiple sub-heat source images. The target temperature data corresponding to each sub-target image is determined based on the second heat source image.

[0150] Based on the correspondence between sub-target images and sub-heat source images, the temperature difference between each pair of corresponding sub-target images and sub-heat source images is determined.

[0151] Based on the location information of each sub-target image, determine the temperature difference between each pair of corresponding sub-target images and sub-heat source images, and the difference between the temperature difference between each pair of adjacent sub-target images and sub-heat source images;

[0152] Obtain a preset difference value and compare the preset difference value with the temperature difference value. If the temperature difference value between a pair of sub-target images and sub-heat source images is greater than the temperature difference value between two adjacent pairs of sub-target images and sub-heat source images, then the sub-target image is determined to be the target region boundary sub-image.

[0153] Based on the location information of the target region boundary sub-image in the second heat source image, the corresponding boundary of the target region is fitted, and the target region is determined.

[0154] Optionally, the system is configured as follows:

[0155] Based on the regional characteristics of the target area, determine whether quality defects occur in the steel pipe during the welding process, including:

[0156] Extract the regional features of the target region, which include the area of ​​the target region, the temperature data within the target region, and the shape of the target region.

[0157] Obtain the preset area threshold, preset temperature range, and preset shape parameter range;

[0158] The regional characteristics are compared with preset area thresholds, preset temperature ranges, and preset shape parameter ranges. Based on the comparison results, it is determined whether the steel pipe has quality defects.

[0159] The large-diameter straight-seam double-sided submerged arc welded steel pipe inspection system provided in this application acquires heat source images of the same location on the steel pipe at different times using two infrared thermal imaging sensors. Image processing and analysis techniques are used to determine the target area, and the welding quality is judged based on the characteristics of the target area, achieving real-time monitoring and quality inspection of the welding process. It can acquire and analyze images in real time during the welding process, promptly detecting welding quality defects through changes in surface temperature, facilitating timely adjustment of welding parameters by operators, and improving welding quality.

[0160] Based on the same inventive concept, embodiments of this application also propose an electronic device, which includes:

[0161] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the large-diameter straight-seam double-sided submerged arc welded steel pipe inspection method of the present application embodiments.

[0162] Furthermore, to achieve the above objectives, embodiments of this application also propose a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method for detecting large-diameter straight-seam double-sided submerged arc welded steel pipes according to embodiments of this application.

[0163] The following is a detailed introduction to the various components of the electronic device:

[0164] In this context, the processor is the control center of the electronic device. It can be a single processor or a collective term for multiple processing elements. For example, a processor can be one or more central processing units (CPUs), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention, such as one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs).

[0165] Alternatively, the processor can perform various functions of the electronic device by running or executing software programs stored in memory and by calling data stored in memory.

[0166] The memory is used to store the software program that executes the solution of the present invention, and the execution is controlled by the processor. The specific implementation method can be referred to the above method embodiment, which will not be repeated here.

[0167] Optionally, the memory can be read-only memory (ROM) or other types of static storage devices capable of storing static information and instructions, random access memory (RAM) or other types of dynamic storage devices capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory can be integrated with the processor or exist independently and coupled to the processor through the interface circuit of the electronic device; the embodiments of the present invention do not specifically limit this.

[0168] A transceiver is used to communicate with network devices or with terminal devices.

[0169] Optionally, the transceiver may include a receiver and a transmitter. The receiver is used to implement the receiving function, and the transmitter is used to implement the sending function.

[0170] Optionally, the transceiver can be integrated with the processor or exist independently and coupled to the processor through the router's interface circuit. This embodiment of the invention does not specifically limit this.

[0171] Furthermore, the technical effects of the electronic device can be referred to the technical effects of the data transmission method in the above method embodiments, and will not be repeated here.

[0172] It should be understood that the processor in the embodiments of the present invention can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0173] It should also be understood that the memory in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0174] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the flow or function according to the embodiments of the present invention is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. A computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. Available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. Semiconductor media can be solid-state drives.

[0175] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0176] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0177] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0178] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

Claims

1. A method for inspecting large-diameter straight-seam double-sided submerged arc welded steel pipes, characterized in that, The method is applicable to a steel pipe welding system, which includes a first infrared thermal imaging sensor, a second infrared thermal imaging sensor, a welding device, and a control terminal. The welding device moves along a first direction of the steel pipe extension and welds one side surface of the steel pipe. The welding device, the first infrared thermal imaging sensor, and the second infrared thermal imaging sensor are sequentially and collinearly arranged in a second direction opposite to the first direction. The method is applicable to the control terminal, including: A first heat source image is acquired based on the first infrared thermal imaging sensor, and a second heat source image is acquired based on the second infrared thermal imaging sensor. The first heat source image and the second heat source image are located at the same position on the steel pipe. Based on the first heat source image and the second heat source image, a target region is determined from the second heat source image, wherein determining a predicted heat source image based on the first heat source image includes: The first heat source image is segmented to form multiple sub-heat source images, and the temperature data corresponding to each sub-heat source image is determined based on the first heat source image. A heat diffusion model of the steel pipe is obtained, and based on the position information of each sub-heat source image, each sub-heat source image is associated with multiple target volume regions on the heat diffusion model of the steel pipe. Based on the aforementioned steel pipe thermal diffusion model, the target thermal diffusion model is obtained; Based on the second temperature data corresponding to multiple target volume regions in the target heat diffusion model, the second temperature data corresponding to multiple sub-heat source images are determined. The predicted heat source image is determined based on multiple sets of the second temperature data; The predicted heat source image is compared with the second heat source image, and the target region is determined from the second heat source image based on the comparison result. Alternatively, the first heat source image can be segmented to form multiple sub-heat source images, and the temperature data corresponding to each sub-heat source image can be determined based on the first heat source image. The second heat source image is segmented to form multiple sub-target images, and the multiple sub-target images correspond to the multiple sub-heat source images. The target temperature data corresponding to each sub-target image is determined based on the second heat source image. Based on the correspondence between the sub-target image and the sub-heat source image, the temperature difference between each pair of corresponding sub-target images and sub-heat source images is determined; Based on the location information of each sub-target image, determine the temperature difference value between each pair of corresponding sub-target images and sub-heat source images, and the difference value between the temperature difference values ​​of all adjacent pairs of sub-target images and sub-heat source images; Obtain a preset difference value and compare the preset difference value with the temperature difference value. If the temperature difference value of a pair of sub-target images and sub-heat source images is greater than the temperature difference value of two adjacent pairs of sub-target images and sub-heat source images, then the sub-target image is determined to be a target region boundary sub-image. Based on the position information of the target region boundary sub-image in the second heat source image, the corresponding boundary of the target region is fitted, and the target region is determined; Based on the regional characteristics of the target area, it is determined whether the steel pipe has quality defects during the welding process.

2. The method for inspecting large-diameter straight-seam double-sided submerged arc welded steel pipes according to claim 1, characterized in that, A first heat source image is acquired based on the first infrared thermal imaging sensor, and a second heat source image is acquired based on the second infrared thermal imaging sensor. The first heat source image and the second heat source image are located at the same position on the steel pipe, including: Based on the first video acquired by the first infrared thermal imaging sensor and the second video acquired by the second infrared thermal imaging sensor; The distance between the first infrared thermal imaging sensor and the second infrared thermal imaging sensor, and the welding speed of the welding device when welding along the steel pipe are obtained; The first heat source image and the second heat source image are determined based on the first video, the second video, the interval distance, and the welding speed.

3. The method for inspecting large-diameter straight-seam double-sided submerged arc welded steel pipes according to claim 2, characterized in that, Determining the first heat source image and the second heat source image based on the first video, the second video, the interval distance, and the welding speed includes: The first heat source image is determined from the first video, and the second heat source image is determined from the second video. The difference between the shooting time corresponding to the Mth frame image and the shooting time corresponding to the Nth frame image is the interval time, which is equal to the interval distance divided by the welding speed.

4. The method for inspecting large-diameter straight-seam double-sided submerged arc welded steel pipes according to claim 1, characterized in that, The predicted heat source image is compared with the second heat source image, and the target region is determined from the second heat source image based on the comparison result, including: The second heat source image is segmented to form multiple sub-target images, and the multiple sub-target images correspond to the multiple sub-heat source images; Each sub-target image is compared with the sub-heat source image, and the region composed of the sub-target images that are different from the corresponding sub-heat source image is determined as the target region.

5. The method for inspecting large-diameter straight-seam double-sided submerged arc welded steel pipes according to claim 1, characterized in that, Based on the regional characteristics of the target area, determining whether quality defects occur in the steel pipe during the welding process includes: The regional features of the target region are obtained, including the area of ​​the target region, the temperature data within the target region, and the shape of the target region. Obtain the preset area threshold, preset temperature range, and preset shape parameter range; The regional features are compared with the preset area threshold, the preset temperature range, and the preset shape parameter range. Based on the comparison results, it is determined whether the steel pipe has quality defects.

6. A testing system for large-diameter straight-seam double-sided submerged arc welded steel pipes, characterized in that, The system includes a first infrared thermal image sensor, a second infrared thermal image sensor, a welding device, and a control terminal. The welding device moves along a first direction extending from the steel pipe and welds one side surface of the steel pipe. The welding device, the first infrared thermal image sensor, and the second infrared thermal image sensor are sequentially and collinearly arranged in a second direction opposite to the first direction. This system is used to execute a method for detecting large-diameter straight-seam double-sided submerged arc welded steel pipes as described in any one of claims 1-5. The system is configured as follows: A first heat source image is acquired based on the first infrared thermal imaging sensor, and a second heat source image is acquired based on the second infrared thermal imaging sensor. The first heat source image and the second heat source image are located at the same position on the steel pipe. Based on the first heat source image and the second heat source image, the target area is determined from the second heat source image; Based on the regional characteristics of the target area, it is determined whether the steel pipe has quality defects during the welding process.

7. An electronic device, characterized in that, include: At least one processor; And, a memory communicatively connected to at least one of the processors; The memory stores instructions that can be executed by at least one of the processors, which are executed by at least one of the processors to enable the at least one of the processors to perform a method for testing large-diameter straight-seam double-sided submerged arc welded steel pipes as claimed in any one of claims 1-5.

Images