Defect identification and detection system for anticorrosive coating of buried gas pipeline

Abstract

The invention discloses a buried gas pipeline anticorrosive coating defect identification and detection system, which relates to the technical field of pipeline anticorrosive coating identification and detection and comprises a pipeline acquisition module, a coating analysis module, an analysis report module and a coating detection robot. Existing detection means are single, results are not comprehensive, manual judgment is relied on, subjective errors exist, detection equipment is poor in adaptability, and complex environments cannot be dealt with. According to the invention, through integration of various detection devices and a multi-modal data analysis technology, efficient and accurate identification of buried gas pipeline anticorrosive coating defects is realized, analysis of multiple aspects of inner wall abnormity, flatness, circularity, anticorrosive coating integrity and the like is covered, and detection precision and comprehensiveness are significantly improved; through modular design and special sealing treatment, the coating detection robot has durability and stability; data external analysis reduces heating, and the endurance time is prolonged; the wheel drive and the telescopic rod structure enable the device to adapt to different pipeline specifications, and meet the detection requirements in a complex environment.

Description

Technical Field

[0001] The present invention relates to the technical field of pipeline anticorrosion layer identification and detection, and specifically to a buried gas pipeline anticorrosion layer defect identification and detection system. Background Technique

[0002] The anticorrosion layer of buried gas pipelines is an important barrier to protect the pipelines from external environmental corrosion, and its performance is directly related to the service life, operation safety of the pipelines, and the protection of the surrounding environment. As the first protection barrier between the pipeline and the soil, the anticorrosion layer can effectively isolate the erosion of moisture, oxygen, and corrosive substances, thereby delaying the corrosion rate of the pipeline. However, under the combined action of external factors (such as soil stress, groundwater level fluctuations, mechanical damage, etc.) and time factors, the anticorrosion layer may gradually develop defects such as aging, cracks, peeling, or even local damage;

[0003] In traditional detection methods (such as manual leak detection, potential detection, etc.), usually only one aspect of the defect can be concerned, and the overall state of the pipeline anticorrosion layer cannot be comprehensively reflected. The detection results in the prior art usually require manual analysis, which is easily limited by experience and judgment subjectivity, resulting in inaccurate detection results. Traditional detection equipment often cannot work properly due to insufficient adaptability when facing pipelines of different specifications or complex burial environments. Summary of the Invention

[0004] The purpose of the present invention is to propose a buried gas pipeline anticorrosion layer defect identification and detection system in order to solve the above-mentioned existing problems.

[0005] The purpose of the present invention can be achieved through the following technical solutions: A buried gas pipeline anticorrosion layer defect identification and detection system includes a coating detection robot and a coating analysis module;

[0006] The coating detection robot includes a coating detection robot body. A number of walking tires are installed on both the left and right sides of the coating detection robot body. The coating detection robot body is divided into two parts: the upper part X of the robot and the lower part S of the robot. The upper part X of the robot and the lower part S of the robot are connected by four electronic telescopic rods II in the middle, and both ends of the electronic telescopic rods are fixedly connected to the coating detection robot body, and the four electronic telescopic rods II extend and retract synchronously; the upper part X of the robot and the lower part S of the robot are further divided into left and right parts, and are connected by four electronic telescopic rods I in the middle, and the four electronic telescopic rods I extend and retract synchronously; A walking motor for driving the walking tires to rotate is provided inside the coating detection robot body to move the coating detection robot body; An infrared camera and a 3D laser scanner are installed in front of the upper part X of the robot, and an ultrasonic detector and a 3D laser scanner are installed in front of the lower part S of the robot; An anti-lost hook is installed behind the upper part X of the robot;

[0007] The coating analysis module is used to analyze the classified and packaged data. Specifically, it disassembles the classified and packaged data to obtain image data, scanning data, and acoustic wave data; analyzes the image data to obtain the pipeline inner wall graphic outlier TXYZ; analyzes the scanning data to obtain the pipeline inner wall flatness NPZ; analyzes the acoustic wave data to obtain the acoustic wave penetration outlier CSZ; combines the acoustic wave penetration outlier CSZ, the pipeline inner wall flatness NPZ, and the pipeline inner wall graphic outlier TXYZ to obtain the total outlier value JCFZ.

[0008] As a preferred embodiment of the present invention, it further includes a pipeline acquisition module and an analysis report module;

[0009] The pipeline acquisition module collects data through an infrared camera, a 3D laser scanner, and an ultrasonic detector, and classifies the data. The data includes: image data, scanning data, and acoustic wave data; packages the classified data, and sends the classified data to a processing device outside the buried gas pipeline through a data transmission unit;

[0010] The analysis report module is used to obtain the abnormal confirmation area for position marking. Specifically:

[0011] When it is marked as the abnormal confirmation area, the generated position acquisition signal is sent to the coating detection robot by the processing device and received by the data transmission unit; then the position acquisition unit of the coating detection robot obtains the position information of the abnormal confirmation area; the position information is sent to the processing device through the data transmission unit and displayed to generate a detection report corresponding to the text.

[0012] As a preferred embodiment of the present invention, the specific process of analyzing the image data to obtain the pipeline inner wall graphic outlier TXYZ is as follows:

[0013] Perform image preprocessing on the image data: Use Gaussian filtering to denoise the image and remove the noise points in the image through the Gaussian filtering formula: Output the Gaussian filter kernel G(x,y), where σ is the standard deviation; x and y are the spatial coordinates of the filter; then convert the image into a black-and-white binary image through the Otsu method; the Otsu method automatically selects a threshold to make the image segmentation effect optimal; then use histogram equalization or adaptive contrast enhancement technology to improve the contrast of the image and enhance the image details, especially the crack and corrosion areas;

[0014] Obtain the abnormal area to be detected from the data after image preprocessing, and analyze the abnormal area to be detected to obtain the shape factor Xz;

[0015] Perform texture feature analysis on the abnormal area to be inspected to obtain the contrast of the abnormal area to be inspected; then combine and calculate the shape factor Xz with the contrast value DB through the established formula: Output the abnormal value TXYZ of the inner wall pattern of the pipeline, where a1 and a2 are preset weight factors.

[0016] As a preferred embodiment of the present invention, the specific process of analyzing the abnormal area to be inspected to obtain the shape factor Xz is as follows:

[0017] Obtain the area, perimeter, and geometric features of the shape factor of the abnormal area to be inspected through the established formula: Output the shape factor Xz, where A is the area of the abnormal area to be inspected and P1 is the perimeter of the abnormal area to be inspected.

[0018] As a preferred embodiment of the present invention, the specific process of performing texture feature analysis on the abnormal area to be inspected to obtain the contrast of the abnormal area to be inspected is as follows:

[0019] Through the contrast calculation formula: Contrast = ∑i,j(i - j) 2 Output the contrast of the abnormal area to be inspected through P2(i,j); where P2(i,j) is the element P2(i,j) in the gray-level co-occurrence matrix, representing the joint probability of pixel pairs with gray values i and j in a specific direction and distance; i and j are the gray values of the rows and columns in the gray-level co-occurrence matrix respectively.

[0020] As a preferred embodiment of the present invention, the specific process of analyzing the scanned data to obtain the flatness NPZ of the inner wall of the pipeline is as follows:

[0021] The inner wall data of the buried gas pipeline obtained by 3D scanning technology contains the spatial coordinates (x, y, z) of each point; preprocess the 3D scanned data to identify and remove outliers that are far from most points and check and remove duplicate points at the same location; if the inner wall of the pipeline is close to a plane, use the plane equation for fitting: A1x + B1y + C1z + D1 = 0, where A1, B1, and C1 are the normal vectors of the plane and D1 is the offset term of the plane; (x, y, z) is the coordinate of a certain point in the point cloud data; calculate the sum of the squares of the distances from all points in the point cloud data to the plane to fit the plane; through the distance d i1 Calculate by the formula: Output the normal distance d from the i1-th point to the fitted plane i1 , (x i1 , y i1 , z i1 ) is the coordinate of the i1-th point; and solve the plane equation through the formula: Output the equation coefficients A1, B1, C1, D1 of the fitting plane; according to the obtained fitting plane equation, calculate the distance from each point to the plane to obtain the flatness of the inner wall of the pipeline.

[0022] For the inner wall of the pipeline close to circular, calculate the circularity of the inner wall of the pipeline. The process is as follows:

[0023] Use the least squares method to fit a circle. The circle equation is: (x - x c ) 2 +(y - y c ) 2 = r 2 , (x c , y c ) is the center coordinate of the circle, and r is the radius of the circle; during the fitting process, calculate the minimum distance from all points on the pipeline surface to the fitted circle; achieve it through the objective function: (x i2 , y i2 ) is the coordinate of the i2-th point in the point cloud; through the established formula: Output the circularity of the inner wall of the pipeline. A2 is the area of the fitted circular region; P2 is the perimeter of the fitted circular region.

[0024] Analyze the calculated flatness and circularity. Through the established formula: NPZ = a3 × flatness index value + a4 × circularity value, obtain the flatness NPZ of the inner wall of the pipeline. Both a3 and a4 are preset weight parameters.

[0025] As a preferred implementation manner of the present invention, the specific process of calculating the flatness of the inner wall of the pipeline by calculating the distance from each point to the plane is as follows:

[0026] Calculate the average distance from all points to the fitting plane through the formula: Output the average deviation, d i1 is the distance from the i1-th point to the fitting plane, and n1 is the total number of points in the point cloud data; calculate the standard deviation of the distance from the points to the plane through the formula: Output the standard deviation σ1 of the distance from the points to the plane; calculate the maximum distance from the points to the plane; Obtain the maximum deviation; finally, comprehensively calculate the average deviation, standard deviation, and maximum deviation to obtain the flatness index of the pipeline: Output the flatness index of the pipeline; where d max is the maximum deviation in this area.

[0027] As a preferred implementation manner of the present invention, the specific process of analyzing the acoustic wave data to obtain the acoustic wave penetration outlier CSZ is as follows:

[0028] Analyze the acoustic wave propagation time and signal intensity of the preprocessed acoustic wave data:

[0029] Calculate the acoustic wave propagation time through the formula: Output the acoustic wave propagation time T2, where: D2 is the distance between the detection point and the receiving point; V2 is the propagation speed of the acoustic wave in the pipeline anticorrosion layer;

[0030] Calculate the signal intensity through the formula: Ij = Ic × e -αd Output the received echo signal intensity Ij, d is the distance of acoustic wave propagation, Ic is the initial intensity of the acoustic wave, and α is the attenuation coefficient; the attenuation coefficient α is obtained through Calculation, and e is the natural constant;

[0031] Combining the two indicators of propagation time and signal intensity: If the signal intensity belongs to the corresponding preset interval, but the propagation time belongs to the corresponding preset interval, then comprehensively calculate the acoustic wave propagation time T2 and the received echo signal intensity Ij through the established formula: CSZ = T2 × b1 + Ij × b2 to obtain the acoustic wave penetration anomaly value CSZ; where b1 and b2 are the corresponding preset weight factors.

[0032] As a preferred embodiment of the present invention, the specific process of obtaining the total anomaly value JCFZ is:

[0033] Through the established formula: Output the total anomaly value JCFZ, CSZ z Is the median of the corresponding preset interval of the acoustic wave penetration anomaly value CSZ, and c1, c2, and c3 are all the corresponding preset weight factors.

[0034] Compared with the prior art, the beneficial effects of the present invention are:

[0035] 1. The present invention realizes the efficient identification of defects in the anticorrosion layer of buried gas pipelines by integrating advanced detection devices such as infrared cameras, 3D laser scanners, and ultrasonic detectors, and combining multi-modal data analysis technology. By analyzing the inner wall anomalies through image data, the inner wall flatness and roundness through scan data, and the integrity of the anticorrosion layer through acoustic wave data, the accuracy and comprehensiveness of the detection results are effectively improved. In addition, using the algorithm design of preset weights and comprehensive index evaluation can quickly and intuitively output the specific location of the abnormal area, avoiding the subjective errors of human judgment in traditional detection methods.

[0036] 2. The coating detection robot of the present invention adopts a modular design and protects the internal electronic components through special sealing treatment, with high stability and the ability to withstand harsh environments. At the same time, the classified data is sent to the processing equipment outside the pipeline for analysis, greatly reducing the heat generation inside the robot and improving the battery life and working stability of the equipment. The design of multi-wheel synchronous drive and telescopic rod adjustment structure enables the robot to adapt to pipelines of different specifications, ensuring the continuity and flexibility of the detection work, so as to meet the detection requirements in complex environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] For the convenience of those skilled in the art to understand, the present invention will be further described below with reference to the accompanying drawings.

[0038] Figure 1 is the principle block diagram of the present invention;

[0039] Figure 2 is the schematic diagram of the coating detection robot of the present invention Figure 1 ;

[0040] Figure 3 is the schematic diagram of the coating detection robot of the present invention Figure 2 ;

[0041] Figure 4 is the working schematic diagram of the coating detection robot of the present invention Figure 1 ;

[0042] Figure 5 is the working schematic diagram of the coating detection robot of the present invention Figure 2 .

[0043] BRIEF DESCRIPTION OF THE DRAWINGS: 1. Coating detection robot body, 2. Infrared camera, 3. First electronic telescopic rod, 4. 3D laser scanner, 5. Walking tire, 6. Second electronic telescopic rod, 7. Anti-loss hook, 8. Ultrasonic detector, A. Pipeline model 1, B. Pipeline model 2, S. Upper part of the robot, X. Lower part of the robot. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0044] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0045] It should be understood that the terms "comprising" and "including" as used in the specification and claims of this disclosure indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0046] It should also be understood that the terms used in this disclosure specification are for the purpose of describing particular embodiments only and are not intended to limit this disclosure. As used in this disclosure specification and claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms. It should further be understood that the term "and / or" as used in this disclosure specification and claims refers to any combination and all possible combinations of one or more of the associated listed items and includes such combinations.

[0047] Please refer to Figure 1 As shown, an anti-corrosion layer defect identification and detection system for buried gas pipelines includes: a pipeline acquisition module, a coating analysis module, and an analysis report module;

[0048] Please refer to Figures 2 - 3 As shown, an anti-corrosion layer defect identification and detection system for buried gas pipelines operates in a coating detection robot; a number of walking tires 5 are installed on both the left and right sides of the coating detection robot body 1, and the coating detection robot body 1 is divided into an upper part X of the robot and a lower part S of the robot. The upper part X of the robot and the lower part S of the robot are connected by four electronic telescopic rods two 6 in the middle, and both ends of the electronic telescopic rods are fixedly connected to the coating detection robot body 1, and the four electronic telescopic rods two 6 extend and contract synchronously; the upper part X of the robot and the lower part S of the robot are further divided into left and right parts and are connected by four electronic telescopic rods one 3 in the middle, and the four electronic telescopic rods one 3 extend and contract synchronously; a walking motor for driving the walking tires 5 to rotate is provided inside the coating detection robot body 1 to move the coating detection robot body 1; an infrared camera 2 and a 3D laser scanner 4 are installed in front of the upper part X of the robot, and an ultrasonic detector 8 and a 3D laser scanner 4 are installed in front of the lower part S of the robot; an anti-loss hook 7 is installed behind the upper part X of the robot; it should be noted that: the coating detection robot is applied inside the buried gas pipeline, and all the internal electronic components of the coating detection robot are specially sealed.

[0049] The pipeline acquisition module collects data through the infrared cameras 2, 3D laser scanners 4, and ultrasonic detectors 8 carried by the coating detection robot, and classifies the data, including: image data, scanning data, and acoustic data; packs the classified data and sends the classified data to the processing device outside the buried gas pipeline through the data transmission unit for analysis; it should be noted that: packing the classified data for analysis by the processing device outside the buried gas pipeline can reduce the heat generation of the coating detection robot inside the pipeline, and increase the battery life and working stability of the coating detection robot;

[0050] The coating analysis module exists in the processing device and analyzes the classified and packed data, specifically:

[0051] First, disassemble the classified and packed data to obtain image data, scanning data, and acoustic data, and then perform successive analysis:

[0052] Analyze the image data (inner wall data of the buried gas pipeline) to obtain the abnormal value of the inner wall graph of the pipeline. The process is as follows:

[0053] Perform image preprocessing on the image data: use Gaussian filtering or median filtering to denoise the image, remove the noise points in the image, and retain the main structural information of the inner wall of the pipeline; Gaussian filtering formula: Output the Gaussian filter kernel G(x, y), which represents the weighting coefficient of each pixel; where σ is the standard deviation, which controls the smoothness of the Gaussian distribution; x and y are the spatial coordinates of the filter, which determine the filtering range; then convert the image into a black-and-white binary image through the Otsu method or other thresholding methods; in the Otsu method, an optimal threshold is automatically selected to make the image segmentation effect the best; secondly, use histogram equalization or adaptive contrast enhancement technology to improve the contrast of the image and enhance the details of the image, especially the crack and corrosion areas;

[0054] Obtain the abnormal area to be detected from the preprocessed image data, and calculate the geometric features such as the area, perimeter, and shape factor of the abnormal area to be detected through the established formula: Output the shape factor Xz, where A is the area of the abnormal area to be detected, and P1 is the perimeter of the abnormal area to be detected; then analyze the texture features of the abnormal area to be detected through the contrast (contrast feature, used to measure the roughness or degree of change of the image texture) calculation formula: contrast = ∑ i,j (i - j) 2P2(i,j) outputs the contrast of the abnormal area to be detected; among them, the element P2(i,j) in the gray-level co-occurrence matrix P2(i,j) represents the joint probability of pixel pairs with gray values i and j in a specific direction and distance; i and j are the gray values of the row and column in the gray-level co-occurrence matrix respectively; it is the degree of difference between different gray levels in the image; the greater the difference, the higher the contrast value, indicating that there are more texture changes in the image; on the contrary, the smaller the difference, the lower the contrast value, and the texture is relatively smooth; it should be noted that: the gray-level co-occurrence matrix calculates the co-occurrence probability between the gray values of each pair of pixels in the image by selecting a suitable direction (such as 0°, 45°, 90° or 135°) and distance (such as 1 pixel); usually, the gray-level co-occurrence matrix is constructed by scanning the image and counting the frequency of gray value pairs; then, the shape factor Xz is combined with the contrast value for calculation through the established formula: Output the abnormal value TXYZ of the inner wall graph of the pipeline. Among them, a1 and a2 are preset weight factors, and a1 + a2 = 1, and DB is the contrast value; then obtain the preset graph abnormality preset threshold and compare it with the abnormal value TXYZ of the inner wall graph of the pipeline. If the abnormal value TXYZ of the inner wall graph of the pipeline is greater than the preset graph abnormality preset threshold, mark the abnormal area to be detected as an abnormal confirmation area and analyze the scanning data; otherwise, directly analyze the scanning data;

[0055] Analyze the scanning data (3D scanning data of the inner wall of the buried gas pipeline) to obtain the flatness of the inner wall of the pipeline. The process is as follows:

[0056] The data of the inner wall of the buried gas pipeline obtained by 3D scanning technology contains the spatial coordinates (x, y, z) of each point; preprocess the 3D scanning data to identify and remove the outlier points that are far away from most points and check and remove the duplicate points at the same position; if the inner wall of the pipeline is close to a plane, use the plane equation for fitting: A1x + B1y + C1z + D1 = 0, where A1, B1, C1 are the normal vectors of the plane, and D1 is the offset term of the plane; (x, y, z) is the coordinate of a certain point in the point cloud data; then calculate the sum of the squares of the distances from all points in the point cloud data to the plane to fit the plane; through the distance d from each point to the plane i1 Calculate by the formula: Output the normal distance d from the i1th point to the fitted plane i1 , where (x i1 , y i1 , z i1 ) is the coordinate of the i1th point; and solve the plane equation through the formula: Output the equation coefficients A1, B1, C1, D1 of the fitted plane;

[0057] According to the obtained fitting plane equation, calculate the distance from each point to the plane to evaluate the flatness of the inner wall of the pipeline, specifically as follows:

[0058] Calculate the average distance from all points to the fitting plane through the formula: Output the average deviation, d i1 is the distance from the i1-th point to the fitting plane, and n1 is the total number of points in the point cloud data; then calculate the standard deviation of the distance from the points to the plane through the formula: Output the standard deviation σ1 of the distance from the points to the plane; calculate the maximum distance from the points to the plane; Obtain the maximum deviation; finally, comprehensively calculate the average deviation, standard deviation, and maximum deviation to obtain the flatness index of the pipeline: Output the flatness index of the pipeline; where, d max is the maximum deviation within this area;

[0059] For the inner wall of a pipeline close to a circle, calculate the circularity of the inner wall of the pipeline, and the process is as follows:

[0060] Use the least squares method to fit a circle, and the circle equation is: (x - x c ) 2 +(y - y c ) 2 =r 2 , where, (x c , y c ) is the center coordinate of the circle, and r is the radius of the circle; in the fitting process, the optimal values of the center and radius are solved to minimize the distance from all points on the pipeline surface to the fitted circle; it is achieved through the objective function: (x i2 , y i2 ) is the coordinate of the i2-th point in the point cloud; after the fitting is completed, through the established formula: Output the circularity of the inner wall of the pipeline, A2 is the area of the fitted circular region; P2 is the perimeter of the fitted circular region;

[0061] Analyze the calculated flatness and circularity through the established formula: NPZ = a3 × flatness index value + a4 × circularity value to obtain the flatness NPZ of the inner wall of the pipeline, where, a3 and a4 are both preset weight parameters and are adjusted according to actual application requirements; compare the flatness of the inner wall of the pipeline with the preset flatness anomaly threshold. If the flatness of the inner wall of the pipeline is greater than the preset flatness anomaly threshold, mark the area corresponding to the scanned data as the anomaly confirmation area and analyze the acoustic wave data; otherwise, directly analyze the acoustic wave data;

[0062] Analyze the acoustic wave data (the data detected by the ultrasonic detector) to obtain the acoustic wave penetration anomaly value, and the process is as follows:

[0063] First, preprocess the acoustic wave data collected by the ultrasonic detector to ensure the accuracy and effectiveness of the analyzed data;

[0064] Analyze the acoustic wave propagation time and signal intensity of the preprocessed acoustic wave data:

[0065] It should be noted that: the acoustic wave propagation time is one of the key parameters for analyzing the integrity of the pipeline anti-corrosion coating; the longer the propagation time, usually the greater the resistance to the propagation of acoustic waves in the material, and there may be greater damage or defects;

[0066] Calculate the acoustic wave propagation time through the formula: Output the acoustic wave propagation time T2, where: D2 is the distance between the detection point and the receiving point, and it is a fixed quantity, usually determined by the distance between the detection point and the receiving point; V2 is the propagation speed of acoustic waves in the pipeline anti-corrosion coating, usually obtained through existing data or experiments; (for a pipeline anti-corrosion coating without defects, the propagation time of acoustic waves should be maintained within a specific range; if the propagation time deviates significantly from the normal value, it may indicate the existence of defects (such as peeling, pores, etc.));

[0067] Calculate the signal intensity (the signal intensity usually refers to the amplitude or intensity of the received echo signal, indicating the energy size of the acoustic wave reflected from the detected object (pipeline anti-corrosion coating); under normal circumstances, the acoustic wave will generate a strong echo signal when encountering a dense medium, while when encountering defects (such as corrosion, cracks or pores), the echo signal will be attenuated, resulting in a lower received signal intensity) through the formula: Ij = Ic × e-αd to output the received echo signal intensity Ij, d is the distance of acoustic wave propagation, usually referring to the distance from the sound source to the defect, Ic is the initial intensity of the acoustic wave (i.e., the signal intensity without any attenuation), and α is the attenuation coefficient, indicating the attenuation degree of the acoustic wave during propagation in the anti-corrosion coating; the attenuation coefficient α is calculated through the empirical formula: Obtain, where e is the natural constant;

[0068] Then, combine the two indicators of propagation time and signal intensity: when the signal intensity is less than the minimum value within the corresponding preset interval and the propagation time is greater than the maximum value within the corresponding preset interval, it indicates that there are relatively large defects at this position, and mark the detected defect area as an abnormal confirmation area; if the signal intensity belongs to the corresponding preset interval, but the propagation time does not belong to the corresponding preset interval, there is a problem with the thickness change, indicating that the anti-corrosion coating does not have a certain integrity, and mark the detected thickness change area as an abnormal confirmation area; if the signal intensity belongs to the corresponding preset interval and the propagation time belongs to the corresponding preset interval, then comprehensively calculate the acoustic wave propagation time T2 and the received echo signal intensity Ij through the established formula: CSZ = T2 × b1 + Ij × b2 to obtain the acoustic wave penetration anomaly value CSZ; where b1 and b2 are the corresponding preset weight factors;

[0069] The acoustic wave penetration outlier CSZ, the pipe inner wall flatness NPZ, and the pipe inner wall graphic outlier TXYZ are combined to obtain the total outlier value. Through the established formula: Output the total outlier value JCFZ, where CSZ z is the median of the preset interval corresponding to the acoustic wave penetration outlier CSZ, and c1, c2, and c3 are all preset weight factors corresponding to each; compare the obtained total outlier value JCFZ with the preset corresponding threshold. If the total outlier value JCFZ is less than the preset corresponding threshold, mark the detection area as an abnormal confirmation area.

[0070] The analysis report module is used to obtain the abnormal confirmation area for position marking. Specifically:

[0071] When marked as an abnormal confirmation area, the generated position acquisition signal is sent to the coating detection robot by the processing device and received by the data transmission unit; then the position acquisition unit of the coating detection robot obtains the position information of the abnormal confirmation area; the position information is sent to the processing device through the data transmission unit and displayed to generate a detection report for the corresponding text.

[0072] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only the specific implementation manners. Obviously, according to the content of this specification, many modifications and changes can be made. This specification selects and specifically describes these embodiments to better explain the principle and practical application of the present invention, so that those skilled in the art in the relevant technical field can well understand and utilize the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. A buried gas pipeline anti-corrosion layer defect recognition and detection system, comprising a coating detection robot and a coating analysis module; characterized in that: The coating inspection robot comprises a coating inspection robot body (1), a plurality of running tires (5) are installed on both sides of the coating inspection robot body (1), and the coating inspection robot body (1) is divided into two parts, namely, a robot upper part X and a robot lower part S. The robot upper part X and the robot lower part S are connected by four electronic telescopic rods (6) in the middle, and two sections of the electronic telescopic rods are fixedly connected to the coating inspection robot body (1), and the four electronic telescopic rods (6) are synchronously extended and retracted; the robot upper part X and the robot lower part S are further divided into two left and right parts, which are connected by four electronic telescopic rods (3) in the middle, and the four electronic telescopic rods (3) are synchronously extended and retracted; a running motor for driving the running tires (5) to rotate is provided in the coating inspection robot body (1), so that the coating inspection robot body (1) moves; an infrared camera (2) and a 3D laser scanner (4) are installed in front of the robot upper part X, and an ultrasonic detector (8) and a 3D laser scanner (4) are installed in front of the robot lower part S; an anti-lost hook (7) is installed at the rear of the robot upper part X; The coating analysis module is used to analyze the classified and packaged data, specifically: disassembling the classified and packaged data to obtain image data, scanning data and acoustic wave data; analyzing the image data to obtain the pipeline inner wall graphic abnormal value TXYZ; analyzing the scanning data to obtain the pipeline inner wall flatness NPZ; analyzing the acoustic wave data to obtain the acoustic wave penetration abnormal value CSZ; combining the acoustic wave penetration abnormal value CSZ, the pipeline inner wall flatness NPZ and the pipeline inner wall graphic abnormal value TXYZ to obtain the total abnormal value JCFZ.

2. According to claim 1, a buried gas pipeline anti-corrosion layer defect identification and detection system is characterized in that: It also includes pipeline acquisition module and analysis report module; The pipeline acquisition module collects data through an infrared camera (2), a 3D laser scanner (4) and an ultrasonic detector (8), and classifies the data, the data including: image data, scanning data and sound wave data; packages the classified data, and sends the classified data to a processing device outside the buried gas pipeline through a data transmission unit; The analysis report module is used to obtain the abnormal confirmation area for location marking, specifically: When it is marked as an abnormal confirmation area, the generated position acquisition signal is sent to the coating inspection robot through the processing device and received by the data transmission unit; the coating inspection robot position acquisition unit then acquires the position information of the abnormal confirmation area; the position information is sent to the processing device through the data transmission unit and displayed to generate a corresponding text inspection report.

3. The system for identifying and detecting defects in the anti-corrosion layer of underground gas pipelines according to claim 1 is characterized in that: The specific process of analyzing the image data to obtain the pipeline inner wall graphic abnormal value TXYZ is as follows: Perform image preprocessing on the image data: Use Gaussian filtering to denoise the image and remove the noise in the image. The Gaussian filtering formula is as follows: Output the Gaussian filter kernel G(x,y), where σ is the standard deviation; x and y are the spatial coordinates of the filter; then use the Otsu method to convert the image into a black and white binary image; automatically select a threshold in the Otsu method to achieve the best image segmentation effect; then use histogram equalization or adaptive contrast enhancement technology to improve the image contrast and enhance image details, especially cracks and corrosion areas; Characterize the data after image preprocessing to obtain the abnormal area to be detected, and analyze the abnormal area to be detected to obtain the shape factor Xz; The texture feature analysis of the abnormal area to be detected is performed to obtain the contrast of the abnormal area to be detected; then the shape factor Xz is combined with the contrast value DB for calculation, and the established formula is: Output the abnormal value TXYZ of the pipeline inner wall graphic, where a1 and a2 are preset weight factors.

4. A buried gas pipeline anti-corrosion layer defect identification and detection system according to claim 3, characterized in that: The specific process of analyzing the abnormal area to be inspected to obtain the shape factor Xz is: Get the area, perimeter, shape factor and geometric characteristics of the abnormal inspection area through the established formula: Output shape factor Xz, where A is the area of ​​the abnormality to be detected and P1 is the perimeter of the abnormality to be detected.

5. A buried gas pipeline anti-corrosion layer defect identification and detection system according to claim 4, characterized in that: The specific process of performing texture feature analysis on the abnormal area to be detected to obtain the comparison of the abnormal area to be detected is: Calculate the contrast using the contrast formula: Contrast = ∑i,j(ij) 2 P2(i,j) outputs the contrast of the abnormal area to be inspected; among them, the element P2(i,j) in the gray level co-occurrence matrix P2(i,j) represents the joint probability of the pixel pair with gray level values ​​i and j in a specific direction and distance; i and j are the gray level values ​​of the row and column in the gray level co-occurrence matrix respectively.

6. The system for identifying and detecting defects in the anti-corrosion layer of underground gas pipelines according to claim 1 is characterized in that: The specific process of analyzing the scanned data to obtain the pipeline inner wall flatness NPZ is as follows: The inner wall data of buried gas pipelines obtained by 3D scanning technology includes the spatial coordinates (x, y, z) of each point; pre-processing the 3D scanning data to identify and remove outliers that are far away from the majority of points and to check and remove duplicate points at the same location; If the inner wall of the pipe is close to a plane, use the plane equation for fitting: A1x+B1y+C1z+D1=0, A1, B1, C1 are the normal vectors of the plane, and D1 is the offset term of the plane; (x, y, z) is the coordinate of a point in the point cloud data; calculate the sum of the squares of the distances from all points in the point cloud data to the plane to fit the plane; pass the distance d from each point to the plane i1 Calculated by the formula: Output the normal distance d from the i1th point to the fitting plane i1 ,(x i1 ,y i1 ,z i1 ) is the coordinate of the i1th point; and solve the plane equation, through the formula: Output the equation coefficients A1, B1, C1, D1 of the fitting plane; according to the obtained fitting plane equation, calculate the distance from each point to the plane to calculate the flatness of the inner wall of the pipeline; For a pipe inner wall that is close to a circle, and to calculate the circularity of the pipe inner wall, the process is: Use the least squares method to fit the circle, and the circle equation is: (xx c ) 2 +(yy c ) 2 =r 2 ,(x c ,y c ) is the coordinate of the center of the circle, and r is the radius of the circle; in the fitting process, the distance from all points on the pipe surface to the fitting circle is calculated to be the minimum; this is achieved through the objective function: (x i2 ,y i2 ) is the coordinate of the i2th point in the point cloud; through the established formula: The circularity of the inner wall of the output pipe, A2 is the area of ​​the fitted circular area; P2 is the circumference of the fitted circular area; The calculated flatness and circularity are analyzed, and the flatness NPZ of the inner wall of the pipe is obtained through the established formula: NPZ = a3 × flatness index value + a4 × circularity value, where a3 and a4 are both preset weight parameters.

7. A system for identifying and detecting defects in anti-corrosion layers of underground gas pipelines according to claim 6, characterized in that: The specific process of calculating the distance from each point to the plane to obtain the flatness of the inner wall of the pipeline is as follows: Calculate the average distance of all points to the fitted plane using the formula: Output mean deviation, d i1 is the distance from the i1th point to the fitting plane, n1 is the total number of points in the point cloud data; calculate the standard deviation of the distance from the point to the plane, through the formula: Output the standard deviation σ1 of the distance from the point to the plane; calculate the maximum distance from the point to the plane; Get the maximum deviation; finally, comprehensively calculate the average deviation, standard deviation and maximum deviation to get the pipeline flatness index: The smoothness index of the output pipeline; where d max is the maximum deviation in this area.

8. The system for identifying and detecting defects in the anti-corrosion layer of a buried gas pipeline according to claim 1 is characterized in that: The specific process of analyzing the acoustic wave data to obtain the acoustic wave penetration abnormal value CSZ is as follows: Analyze the sound wave propagation time and signal strength of the preprocessed sound wave data: The sound wave propagation time is calculated using the formula: Output sound wave propagation time T2, where: D2 is the distance between the detection point and the receiving point; V2 is the propagation speed of the sound wave in the pipeline anti-corrosion layer; Calculate the signal strength using the formula: Ij = Ic × e -αd The received echo signal strength Ij is output, where d is the distance the sound wave propagates, Ic is the initial strength of the sound wave, and α is the attenuation coefficient; the attenuation coefficient α is calculated by It is calculated that e is a natural constant; Combine the two indicators of propagation time and signal strength: if the signal strength is within the corresponding preset interval, but the propagation time is within the corresponding preset interval, then the sound wave propagation time T2 and the received echo signal strength Ij are comprehensively calculated, and the sound wave penetration anomaly value CSZ is obtained through the established formula: CSZ=T2×b1+Ij×b2; where b1 and b2 are the corresponding preset weight factors respectively.

9. The system for identifying and detecting defects in the anti-corrosion layer of underground gas pipelines according to claim 1 is characterized in that: The specific process of obtaining the abnormal total value JCFZ is as follows: By establishing the formula: Output abnormal total value JCFZ, CSZ z is the median of the preset interval corresponding to the sound wave penetration abnormal value CSZ, and c1, c2 and c3 are their corresponding preset weight factors.

Images