Intelligent identification system and method for oil pipeline defects

Abstract

The invention relates to the technical field of pipeline defect recognition, in particular to an intelligent recognition system and method for oil pipeline defects, and the method comprises the steps: obtaining a plurality of images of an oil pipeline, and determining a feature extraction position and a potential stripping region; determining whether the potential stripping area is a bump or not according to the offset distance; obtaining a front view of the potential stripping area based on the potential stripping area determined as the bump, and determining a plane range of the bump, so as to determine the overlap ratio of the plane range and the potential stripping area; determining the adjustment of the illumination angle based on the overlap ratio so as to determine the height of the bump, and determining the predicted stripping duration according to the height of the bump; the system comprises a pipeline detection robot and a control center, the pipeline detection robot is used for acquiring image information, and the control center is used for analyzing the image information acquired by the pipeline robot to determine the bump and the predicted stripping time corresponding to the bump. According to the method, the bump identification precision is improved, and the defect detection precision is further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of pipeline defect detection, and particularly to an intelligent recognition system and method for oil pipeline defects. Background Art

[0002] As the core infrastructure for energy transportation, oil pipelines are susceptible to internal and external corrosion, mechanical stress, and geological activities over a long period, easily resulting in defects such as bulges and cracks. Among them, bulges are difficult to detect because of their diverse shapes and frequent confusion with attachments on the pipeline surface (such as rust spots, weld protrusions, and anticorrosion layer patches). Traditional manual inspections rely on experience for judgment, with low efficiency and a missed inspection rate as high as 30%; although conventional non-destructive testing techniques (such as ultrasonic thickness measurement and eddy current testing) can locate abnormalities, they are difficult to achieve large-area and rapid screening, especially lacking the ability to quantitatively analyze surface topography features.

[0003] In recent years, automated detection techniques based on machine vision have developed rapidly, but still face multiple challenges in practical applications: interference from morphological similarity: bulges, weld crowns, and accumulations of anticorrosion materials all exhibit local elevation features in two-dimensional images, and traditional edge detection algorithms (such as the Canny operator) are prone to misjudgment due to texture noise; interference from environmental complexity: artifacts formed by oil stains and rust on the pipeline surface highly overlap with real bulges in terms of color and gray-scale distribution, and threshold segmentation methods (such as the Otsu algorithm) are difficult to effectively distinguish; loss of three-dimensional features: monocular cameras cannot capture the three-dimensional height information of bulges, resulting in similar contours of concave corrosion and convex bulges in two-dimensional projections.

[0004] Chinese Patent Publication No.: CN111695482A discloses a pipeline defect recognition method. While a pipeline robot transmits the video inside the pipeline in real time, the video is sampled into key-frame images, and the pipeline defects in the images are effectively recognized and captured. The extracted defect images are saved with location markings. This invention solves the target defect detection as a regression problem based on the basic idea of DefectNet. First, feature extraction is performed through a convolutional neural network to obtain a feature map of a certain size, and then multi-scale prediction divides feature maps of different scales into several grids. Whichever grid the center of the defect target falls into is responsible for predicting that defect target. Finally, target classification and bounding box regression are carried out. Each grid determines the category to which the defect target belongs and adjusts the position of the bounding box. Compared with existing technologies, it improves the detection accuracy and efficiency, has high innovation and practical value, and is suitable for promotion.

[0005] It can be seen that the pipeline defect identification method has the following problems: The invention saves the defect image positioning marks obtained by extraction to obtain a feature map, divides the feature map into several grids, and the grids are responsible for confirming the defect targets in the area, thereby improving the detection efficiency. However, the invention does not show how to identify defects and still does not solve the problem of inaccurate identification of bulge defects. Summary of the Invention

[0006] To this end, the present invention provides an intelligent identification system and method for oil pipeline defects to overcome the problem of low defect detection accuracy caused by inaccurate identification of bulge defects in oil pipelines in the prior art.

[0007] To achieve the above object, on the one hand, the present invention provides an intelligent identification method for oil pipeline defects, including:

[0008] Obtain a plurality of images of the oil pipeline, preprocess the images to determine a plurality of feature extraction positions, and determine potential peeling areas according to the feature extraction positions;

[0009] Increase the fluid flow rate in the potential peeling area to determine whether the potential peeling area is a bulge according to the offset distance of the shadow boundary;

[0010] Based on the result that the potential peeling area is determined to be a bulge, obtain the front view of the potential peeling area, preprocess the front view to determine the planar range of the bulge, and determine the coincidence degree between the planar range and the potential peeling area;

[0011] Based on the coincidence degree, adjust the illumination angle, determine the bulge height according to the feature extraction position, and determine the predicted peeling duration of the bulge according to the bulge height and the edge gradient of the bulge.

[0012] Further, the determination process of the feature extraction position includes:

[0013] Determine a plurality of pixel points smaller than the first gray value, and connect adjacent positions in each of the pixel points to form a plurality of pixel regions;

[0014] Match the pixel regions with the standard region set to determine each similarity, and determine the maximum similarity based on each similarity;

[0015] Compare the maximum similarity with a preset similarity;

[0016] Based on the comparison result that the maximum similarity is greater than or equal to the preset similarity, determine the pixel region as the feature extraction position.

[0017] Further, the determination process of the potential peeling area includes:

[0018] Determine the line on the side of the feature extraction position closer to the light source as the shadow boundary, and determine the center point of the shadow boundary, so as to determine a plane passing through the center point and perpendicular to the center line of the oil pipeline based on the center point;

[0019] Taking the plane as a reference, perform a mirror operation on the feature extraction position to form a mirror area;

[0020] Connect the feature extraction position and the outer edge of the mirror area, and the formed area is the potential peeling area.

[0021] Further, the process of determining the offset distance of the shadow boundary includes:

[0022] After increasing the fluid flow rate, re-determine the shadow boundary and record it as the secondary boundary;

[0023] Determine the distance between the shadow boundary and the secondary boundary as the offset distance.

[0024] Further, the process of determining the nature of the potential peeling area based on the offset distance includes:

[0025] Compare the offset distance with a preset offset distance;

[0026] Based on the comparison result that the offset distance is greater than the preset distance, determine that the potential peeling area is a bulge.

[0027] Further, the process of determining whether to adjust the illumination angle includes:

[0028] Obtain the front view of the bulge, and determine the plane range of the bulge after preprocessing the front view;

[0029] Determine the ratio of the plane range to the area of the feature extraction position as the coincidence degree;

[0030] Compare the coincidence degree with a first preset coincidence degree and a second preset coincidence degree respectively;

[0031] Based on the comparison result that the coincidence degree is less than the first preset coincidence degree, determine to decrease the illumination angle;

[0032] Based on the comparison result that the coincidence degree is greater than the second preset coincidence degree, determine to increase the illumination angle.

[0033] Further, the adjustment process of decreasing the illumination angle includes:

[0034] Subtract the coincidence degree from the first preset coincidence degree to obtain a first difference,

[0035] Determine a first angle adjustment coefficient according to the first difference, and reduce the illumination angle with the first angle adjustment coefficient;

[0036] Wherein, the illumination angle is the included angle between the light ray and the inner wall of the oil pipeline.

[0037] Further, the process of increasing the illumination angle includes:

[0038] Subtract the degree of coincidence from the second preset degree of coincidence to obtain a second difference;

[0039] Determine a second angle adjustment coefficient according to the second difference, and increase the illumination angle with the second angle adjustment coefficient.

[0040] Further, the process of determining the predicted peeling duration according to the bulge height and the edge gradient includes:

[0041] Based on the adjusted illumination angle, determine the maximum spacing of the feature extraction positions in the direction parallel to the fluid flow direction, and input the maximum spacing and the illumination angle into the calculation model to output the bulge height;

[0042] Determine the edge gradient based on the planar range of the bulge;

[0043] Combine the bulge height and the edge gradient to determine the predicted peeling duration of the bulge.

[0044] On the other hand, the present invention also provides an intelligent identification system for oil pipeline defects applying the intelligent identification method for oil pipeline defects, including:

[0045] A pipeline inspection robot for acquiring a plurality of images of the inner wall of the oil pipeline;

[0046] A control center connected to the pipeline inspection robot, including,

[0047] A region determination module for determining a plurality of feature extraction positions based on the images, and determining a potential peeling region according to the feature extraction positions through mirroring;

[0048] A defect determination module for determining whether the potential peeling region is a bulge based on the offset distance of the shadow boundary, and determining the planar range of the front view of the bulge to determine the adjustment of the illumination angle based on the degree of coincidence;

[0049] A defect development prediction module for determining the bulge height based on the adjusted illumination angle to determine the predicted peeling duration of the bulge.

[0050] Compared with the prior art, the beneficial effects of the present invention are as follows. The present invention determines the feature extraction range by identifying the area formed by connecting the pixel points that meet the requirements. A shadow will be generated on the backlight side of the bulge under light. Since the light direction in the oil pipeline is fixed, the shadow shape formed by the bulge has a specific shape. The feature extraction position, that is, the shadow area, can be divided according to the shape characteristics of the pixel area. On the basis of determining the shadow area, mirroring is performed to determine the potential peeling area, so as to initially determine the bottom range of the potential peeling area. Further increase the fluid flow rate and record the offset distance of the shadow boundary. If the offset distance is greater than the preset distance, it means that the potential peeling area is a bulge. The bulge is caused by the gas generated by corrosion, resulting in a cavity on the metal surface. Under the action of external force, the gas will flow to resist the external pressure, resulting in the movement of the highest point of the convex point. And the shadow boundary passes through the highest point of the convex point. Therefore, it is determined whether the potential peeling area is a bulge by judging the offset of the shadow boundary. After determining that it is a bulge, obtain the front view and determine the coincidence degree between the plane range of the bulge and the range of the potential peeling area. A large range of the potential peeling area means that the light angle is too small, resulting in too large a shadow part. A small range of the potential peeling area means that the light angle is too large, resulting in too small a shadow part. By adjusting the light angle, the area of the shadow part can be exactly half of the plane range. For a single bulge, under the premise that the area of the shadow part is exactly half of the plane range, there is a one-to-one correspondence between the bulge height and the light angle. The bulge height can be determined by the model to solve the problem that a monocular camera cannot capture the three-dimensional height information of the bulge. The higher the bulge height, the shorter the time from the bulge to rupture. Therefore, the expected peeling duration of the bulge can be predicted according to the bulge height, so as to achieve the accurate identification of the bulge and improve the detection accuracy of defects.

[0051] Furthermore, the present invention determines a number of pixel points through the gray value, and determines the pixel area based on the pixel points, so as to initially screen the feature extraction position according to the objective fact of the shadow of the bulge under the light condition, and then further determine the potential peeling area within the initial position range, and determine the nature of the potential peeling area according to the objective fact that the bulge will deform under the action of external force. Further detection and analysis are carried out for the position determined to be a bulge, thereby further improving the identification accuracy of the bulge.

[0052] Furthermore, according to the condition that the shadow area can reach half of the plane range only at a specific light angle for the bulge height, the light angle and the maximum distance between the feature extraction positions are input into the model to determine the bulge height. Under the condition of determining the bulge height, further determine the expected peeling duration according to the bulge height, so as to predict the development trend of the bulge while improving the detection accuracy, and further improve the detection accuracy of defects. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 Flow chart of the intelligent recognition method for defects in the oil pipeline in the embodiment of the present invention;

[0054] Figure 2 Flow chart of determining the nature of the potential peeling area in the embodiment of the present invention;

[0055] Figure 3 Flow chart of determining whether to adjust the illumination angle in the embodiment of the present invention;

[0056] Figure 4 Block diagram of the structure of the intelligent recognition system for defects in the oil pipeline in the embodiment of the present invention. Detailed implementation manners

[0057] In order to make the objectives and advantages of the present invention more clear and understandable, the present invention will be further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0058] The preferred implementation manners of the present invention will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these implementation manners are only used to explain the technical principle of the present invention and do not limit the protection scope of the present invention.

[0059] It should be noted that in the description of the present invention, the terms indicating directions or positional relationships such as "upper", "lower", "left", "right", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings. This is only for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention.

[0060] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and defined, the terms "installation", "connection", "connection" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, an electrical connection; it can be directly connected, or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0061] Please refer to Figures 1-3 as shown in Figure 1 Flow chart of the intelligent recognition method for defects in the oil pipeline in the embodiment of the present invention; Figure 2 Flow chart of determining the nature of the potential peeling area in the embodiment of the present invention; Figure 3 Flow chart of determining whether to adjust the illumination angle in the embodiment of the present invention.

[0062] An embodiment of the present invention provides an intelligent recognition method for defects in an oil pipeline, including:

[0063] Step S1, obtaining a plurality of images of the oil pipeline, preprocessing the images to determine a plurality of feature extraction positions, and determining potential peeling areas according to the feature extraction positions;

[0064] Step S2, increasing the fluid flow rate in the potential peeling areas to determine whether the potential peeling areas are bulges according to the offset distance of the shadow boundary;

[0065] Step S3, based on the result that the potential peeling area is determined to be a bulge, obtaining a front view of the potential peeling area, preprocessing the front view to determine the planar range of the bulge, and determining the coincidence degree between the planar range and the potential peeling area;

[0066] Step S4, adjusting the illumination angle based on the coincidence degree, determining the bulge height according to the feature extraction position, and determining the predicted peeling duration of the bulge according to the bulge height and the edge gradient of the bulge.

[0067] Specifically, all images in the embodiments of the present invention need to be preprocessed before analysis, and the preprocessing process includes but is not limited to grayscale conversion, geometric transformation, denoising, filtering, and image enhancement.

[0068] Specifically, the determination process of the feature extraction position includes:

[0069] Determining a first grayscale value of a defect-free position of the oil pipeline;

[0070] Determining a plurality of pixel points smaller than the first grayscale value, and connecting adjacent positions of each pixel point to form a plurality of pixel regions;

[0071] Matching the pixel regions with a standard region set to determine respective similarity degrees, and determining the maximum similarity degree based on the respective similarity degrees;

[0072] Comparing the maximum similarity degree with a preset similarity degree;

[0073] Based on the comparison result that the maximum similarity degree is greater than or equal to the preset similarity degree, determining the pixel region as the feature extraction position;

[0074] Wherein, the first grayscale value is the grayscale value of an area without defects on the simulated oil pipeline under the detection conditions.

[0075] Specifically, both bulges and solder joints have protrusions. Under the illumination of light, shadows will be generated on the backlight side of the protrusions, and the grayscale values of the shadows are small. Connecting the pixel points with small grayscale values into a region, and then overlapping according to the shape characteristics of the region to determine the feature extraction position.

[0076] Specifically, the set of standard regions is a set of pixel regions that simulate the shadows formed on the backlight side under the illumination of bumps of different sizes, and the illumination direction of the light is the same as the direction of the light emitted by the pipeline inspection robot inside the pipeline.

[0077] Specifically, the first gray value is the average of the gray values of each pixel at the defect-free position, determined by experimental simulation. The value range of the preset similarity is set to [70%, 95%], and 85% is preferably selected in the embodiments of the present invention.

[0078] It can be understood that the feature extraction position is the shadow area, which represents the position where a bump may exist. During the long-term use of the oil pipeline, the material inside the pipeline will be corroded under continuous erosion, gradually forming tiny rust spots or rust patches. As the corrosion progresses, the rust spots or rust patches gradually expand, and cavities or bubbles are formed inside the metal. The gas generated by corrosion (such as hydrogen) accumulates in the internal cavities or bubbles of the metal, resulting in an increase in internal pressure. Under the action of the internal pressure, the metal surface begins to bulge, forming a bump. As the corrosion continues, the gas inside the bump continuously accumulates, and the bump gradually enlarges. The metal layer on the surface of the bump may become thinner due to corrosion, or even cracks may appear. When the pressure inside the bump reaches a certain level, the metal surface can no longer withstand this pressure, and the bump ruptures. After rupture, obvious cracks or holes are formed on the metal surface, exposing the internal corrosion products. The corrosion products are accelerated by the scouring of the fluid and finally carried away by the fluid and peeled off from the metal surface.

[0079] Specifically, the determination process of the potential peeling region includes:

[0080] Determine the line on the side of the feature extraction position close to the light source as the shadow boundary line, determine the center point of the shadow boundary line, and determine a plane passing through the center point and perpendicular to the center line of the oil pipeline based on the center point;

[0081] Mirror the feature extraction position with the plane as the reference to form a mirror image region;

[0082] The region formed by connecting the outer edge of the feature extraction position and the mirror image region is the potential peeling region.

[0083] Specifically, the potential peeling region is a preliminary region obtained by mirroring the shadow part. The mirrored region and the original potential peeling region often cannot form a closed figure. Therefore, it is necessary to connect the outer edges of the two parts after mirroring to form a closed figure.

[0084] Specifically, the determination process of the offset distance of the shadow boundary line includes:

[0085] After increasing the fluid flow rate, re-determine the shadow boundary and record it as the secondary boundary;

[0086] Determine the distance between the shadow boundary and the secondary boundary as the offset distance.

[0087] It can be understood that the bulge contains gas, and the gas will transfer under the impact of different flow rates. The highest point of the bulge will shift away from the light source side, resulting in the shadow boundary also shifting away from the light source side.

[0088] Specifically, the process of determining the nature of the potential peeling area based on the offset distance includes:

[0089] Compare the offset distance with a preset offset distance;

[0090] Based on the comparison result that the offset distance is greater than the preset distance, determine that the potential peeling area is a bulge;

[0091] Based on the comparison result that the offset distance is equal to the preset distance, determine that the potential peeling area is non-bulge.

[0092] Specifically, the preset distance is the offset distance of light propagation in the same fluid at different flow rates. It can be understood that as the flow rate of the fluid increases, the propagation of light under the same conditions in the fluid will shift, and the specific offset distance is determined by experiments.

[0093] Specifically, the process of determining whether to adjust the illumination angle includes:

[0094] Obtain the front view of the bulge, and determine the planar range of the bulge after preprocessing the front view;

[0095] Determine the ratio of the planar range to the area of the feature extraction position as the coincidence degree;

[0096] Compare the coincidence degree with a first preset coincidence degree and a second preset coincidence degree respectively;

[0097] Based on the comparison result that the coincidence degree is less than the first preset coincidence degree, determine to reduce the illumination angle;

[0098] Based on the comparison result that the coincidence degree is greater than the second preset coincidence degree, determine to increase the illumination angle;

[0099] Based on the comparison result that the coincidence degree is greater than or equal to the first preset coincidence degree and less than or equal to the second preset coincidence degree, determine not to adjust the illumination angle.

[0100] Specifically, the value range of the first preset coincidence degree is set to [95%, 100%], and 98% is preferred in the embodiments of the present invention; the value range of the second preset coincidence degree is set to [100.1%, 103%], and 102% is preferred in the embodiments of the present invention.

[0101] It can be understood that when the coincidence degree is less than the first preset coincidence degree, it means that the area of the potential peeling region is smaller than the planar area of the bulge, indicating that the illumination angle is too large, and the illumination angle should be appropriately reduced to increase the area of the potential peeling region. When the coincidence degree is greater than the second preset coincidence degree, it means that the area of the potential peeling region is larger than the planar area of the bulge, indicating that the illumination angle is too small, and the illumination angle should be appropriately increased to reduce the area of the potential peeling region.

[0102] Specifically, the adjustment process of reducing the illumination angle includes:

[0103] Subtracting the first preset coincidence degree from the coincidence degree to obtain a first difference value.

[0104] Determining a first angle adjustment coefficient according to the first difference value, and reducing the illumination angle by the first angle adjustment coefficient.

[0105] Wherein, the illumination angle is the included angle between the light ray and the inner wall of the oil pipeline.

[0106] Specifically, the calculation formula of the first angle adjustment coefficient is:

[0107]

[0108] Wherein, X1 represents the first angle adjustment coefficient, and ΔC1 represents the first difference value.

[0109] Specifically, the adjustment process of increasing the illumination angle includes:

[0110] Subtracting the second preset coincidence degree from the coincidence degree to obtain a second difference value.

[0111] Determining a second angle adjustment coefficient according to the second difference value, and increasing the illumination angle by the second angle adjustment coefficient.

[0112] Specifically, the calculation formula of the second angle adjustment coefficient is:

[0113]

[0114] Wherein, X2 represents the second angle adjustment coefficient, and ΔC2 represents the second difference value.

[0115] Specifically, the process of determining the expected peeling duration according to the bulge height and the edge gradient includes:

[0116] Based on the adjusted illumination angle, determine the maximum spacing of the feature extraction positions in the direction parallel to the fluid flow direction, and input the maximum spacing and the illumination angle into a calculation model to output the bulge height;

[0117] Determine the edge gradient based on the planar range of the bulge;

[0118] Combine the bulge height and the edge gradient to determine the predicted peeling duration of the bulge.

[0119] Specifically, the maximum spacing is actually half of the distance of the bulge planar range in the direction parallel to the fluid flow direction.

[0120] Specifically, the calculation model is trained according to the data of the recognition processes of a large number of accurate bulges. The calculation model can be, for example, a neural network model or a support vector machine, and is not specifically limited.

[0121] It can be understood that the edge gradient represents the clarity of the edge, which is determined according to the gray difference value of the bulge edge. The higher the height of the bulge, the greater the clarity of the bulge edge, that is, the greater the edge gradient, and the shorter the duration until rupture and peeling.

[0122] Specifically, the formula for determining the predicted peeling duration of the bulge according to the bulge height and the edge gradient is as follows:

[0123]

[0124] Wherein, S represents the predicted peeling duration, K represents the material constant, E represents the edge gradient, H represents the bulge height, ΔC represents the difference in thermal expansion coefficients between the inner surface of the oil pipeline and the pipeline matrix, T represents the fluid temperature in the oil pipeline, and ε represents the critical strain at the interface between the inner surface of the oil pipeline and the pipeline matrix.

[0125] It can be understood that there is often a coating on the inner surface of the oil pipeline, and the difference in expansion coefficients refers to the difference in expansion coefficients between the coating and the matrix.

[0126] Please refer to Figure 4 as shown, which is the structural block diagram of the intelligent recognition system for oil pipeline defects in an embodiment of the present invention.

[0127] Specifically, an embodiment of the present invention further provides an intelligent recognition system for oil pipeline defects applying the intelligent recognition method for oil pipeline defects, including:

[0128] A pipeline inspection robot for acquiring a plurality of images of the inner wall of the oil pipeline;

[0129] A control center connected to the pipeline inspection robot, including,

[0130] An area determination module, which is used to determine a number of feature extraction positions based on the image, so as to determine a potential peeling area after mirroring according to the feature extraction positions;

[0131] A defect determination module, which is used to determine whether the potential peeling area is a bulge based on the offset distance of the shadow boundary line, and determine the plane range of the front view of the bulge to determine the adjustment of the illumination angle based on the coincidence degree;

[0132] A defect development prediction module, which is used to determine the bulge height based on the adjusted illumination angle to determine the expected peeling duration of the bulge.

[0133] Specifically, the pipeline inspection robot moves passively according to the pressure difference of the fluid under normal inspection conditions. After determining to increase the fluid flow rate, the power facilities it has start to increase the speed of the pipeline inspection robot to increase the fluid flow rate, and increase the pressure of the fluid on the bulge to cause changes in the bulge.

[0134] So far, the technical solution of the present invention has been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the protection scope of the present invention.

Claims

1. An intelligent identification method for defects in oil pipelines, characterized in that, Including: Obtain a number of images of the oil pipeline, preprocess the images to determine a number of feature extraction positions, and determine potential peeling areas based on the feature extraction positions; Increase the fluid flow rate in the potential peeling area to determine whether the potential peeling area is a bulge according to the offset distance of the shadow boundary; Based on the result that the potential peeling area is determined to be a bulge, obtain a front view of the potential peeling area, preprocess the front view to determine the planar range of the bulge, and determine the coincidence degree between the planar range and the potential peeling area; Based on the coincidence degree, determine the adjustment of the illumination angle, determine the bulge height according to the feature extraction position, and determine the estimated peeling duration of the bulge according to the bulge height and the edge gradient of the bulge.

2. The intelligent identification method for defects in an oil pipeline according to claim 1, characterized in that The determination process of the feature extraction position includes: Determine a number of pixel points smaller than the first gray value, and connect adjacent positions in each of the pixel points to form a number of pixel regions; Match the pixel regions with a set of standard regions to determine respective similarity degrees, and determine the maximum similarity degree based on the respective similarity degrees; Compare the maximum similarity degree with a preset similarity degree; Based on the comparison result that the maximum similarity degree is greater than or equal to the preset similarity degree, determine the pixel region as the feature extraction position.

3. The intelligent recognition method for defects in an oil pipeline according to claim 2, characterized in that, The determination process of the potential peeling area includes: Determine the line on the side of the feature extraction position close to the light source as the shadow boundary, determine the center point of the shadow boundary, and based on the center point, determine a plane perpendicular to the center line of the oil pipeline passing through the center point; Taking the plane as a reference, perform a mirror operation on the feature extraction position to form a mirror image area; Connect the outer edges of the feature extraction position and the mirror image area, and the formed area is the potential peeling area.

4. The intelligent identification method for defects in an oil pipeline according to claim 3, characterized in that The determination process of the offset distance of the shadow boundary includes: After increasing the fluid flow rate, re-determine the shadow boundary and record it as the secondary boundary; Determine the distance between the shadow boundary and the secondary boundary as the offset distance.

5. The intelligent identification method for defects in an oil pipeline according to claim 4, wherein The process of determining the nature of the potential peeling area based on the offset distance includes: Compare the offset distance with a preset offset distance; Based on the comparison result that the offset distance is greater than the preset distance, determine that the potential peeling area is a bulge.

6. The intelligent identification method for defects in an oil pipeline according to claim 5, characterized in that, The process of determining whether to adjust the illumination angle includes: Obtain a front view of the bulge, preprocess the front view to determine the planar range of the bulge; Determine the ratio of the planar range to the area of the feature extraction position as the coincidence degree; Compare the coincidence degree with a first preset coincidence degree and a second preset coincidence degree respectively; Based on the comparison result that the coincidence degree is less than the first preset coincidence degree, determine to reduce the illumination angle; Based on the comparison result that the coincidence degree is greater than the second preset coincidence degree, determine to increase the illumination angle.

7. The intelligent identification method for defects in an oil pipeline according to claim 6, characterized in that The adjustment process of reducing the illumination angle includes: Subtract the coincidence degree from the first preset coincidence degree to obtain a first difference value, Determine a first angle adjustment coefficient according to the first difference value, and reduce the illumination angle with the first angle adjustment coefficient; Wherein, the illumination angle is the included angle between the light ray and the inner wall of the oil pipeline.

8. The intelligent recognition method for defects in an oil pipeline according to claim 6, characterized in that, The process of increasing the illumination angle includes: Subtracting the degree of coincidence from the second preset degree of coincidence to obtain a second difference; Determining a second angle adjustment coefficient according to the second difference, and increasing the illumination angle with the second angle adjustment coefficient.

9. The intelligent recognition method for defects in an oil pipeline according to claim 8, characterized in that The process of determining the predicted peeling duration according to the bulge height and the edge gradient includes: Based on the adjusted illumination angle, determining the maximum spacing of the feature extraction positions in the direction parallel to the fluid flow direction, and inputting the maximum spacing and the illumination angle into a calculation model to output the bulge height; Determining the edge gradient based on the planar range of the bulge; Combining the bulge height and the edge gradient to determine the predicted peeling duration of the bulge.

10. An intelligent identification system for defects in an oil pipeline applying the intelligent identification method for defects in an oil pipeline according to any one of claims 1-9, characterized in that, Includes: A pipeline inspection robot for obtaining a plurality of images of the inner wall of an oil pipeline; A control center connected to the pipeline inspection robot, including, A region determination module for determining a plurality of feature extraction positions based on the images, and determining a potential peeling region according to the feature extraction positions through mirroring; A defect determination module for determining whether the potential peeling region is a bulge based on the offset distance of the shadow boundary, and determining the planar range of the front view of the bulge to determine the adjustment of the illumination angle based on the degree of coincidence; A defect development prediction module for determining the bulge height based on the adjusted illumination angle to determine the predicted peeling duration of the bulge.

Images