Detection method, detection system and equipment for monitoring pipeline crack based on 3D scanning image

Abstract

The invention discloses a detection method, a detection system and equipment for monitoring a pipeline crack based on a 3D scanning image, and relates to the technical field of pipeline crack detection.The method comprises the steps that pipeline 3D scanning image data and pipeline design parameters are obtained, and the pipeline crack is detected according to the pipeline 3D scanning image data and the pipeline design parameters; judging a first detection result and crack characteristics of a potential crack area on the surface of the pipeline; generating a crack feature comparison table for comparing and adjusting a crack detection model according to the pipeline design parameters, the first detection result and the crack features; acquiring a crack detection reference range representing crack detection precision, and generating a crack detection model according to the crack detection reference range and the crack feature comparison table; acquiring pipeline high-resolution image data, inputting a pipeline high-resolution scanning image into the crack detection model to identify cracks on the surface of the pipeline, and generating a second detection result; the detection precision of pipeline crack detection is improved, and the false detection rate is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of pipeline crack detection, and in particular to a pipeline crack detection method, detection system and equipment based on 3D scanning image monitoring. Background Art

[0002] In the petrochemical or power sectors, pipeline cracks may lead to serious consequences. First, cracks can cause fluid leakage, resulting in resource waste and environmental pollution. In particular, chemical leakage in the petrochemical industry may pose a threat to the ecosystem and human health. Second, cracks may cause safety accidents, such as steam leakage in the power sector causing burns or equipment damage, and cracks in high-pressure pipelines may even cause explosions. Finally, cracks affect production continuity and efficiency, causing economic losses to enterprises. Therefore, it is crucial to detect and repair pipeline cracks in a timely manner.

[0003] Existing pipeline crack detection methods include manual visual inspection, ultrasonic testing, magnetic particle testing, and radiographic testing. These methods have problems such as low detection accuracy, high false detection rate, complex operation, and high cost. In recent years, pipeline crack detection methods based on 3D scanning images have gradually emerged, but existing methods still have problems such as poor detection accuracy and slightly high false detection rate, which limits their effectiveness in practical applications.

[0004] Therefore, a new pipeline crack detection method based on 3D scanning image monitoring is urgently needed to improve detection accuracy and reduce the false detection rate. Summary of the invention

[0005] In order to improve the detection accuracy of pipeline crack detection and reduce the false detection rate, the present application provides a pipeline crack detection method, detection system and equipment based on 3D scanning image monitoring.

[0006] In the first aspect, the invention objective of the present application is achieved by adopting the following technical solutions: The pipeline crack detection method based on 3D scanning image monitoring includes: Acquire pipeline 3D scanning image data and pipeline design parameters, and determine a first detection result and crack characteristics of a potential crack area on the pipeline surface according to the pipeline 3D scanning image data and the pipeline design parameters; Generating a crack feature comparison table for comparing and adjusting a crack detection model according to the pipeline design parameters, the first detection result and the crack feature; Acquire a crack detection reference range indicating crack detection accuracy, and generate a crack detection model according to the crack detection reference range and the crack feature comparison table; High-resolution image data of the pipeline is acquired, and the high-resolution scanning image of the pipeline is input into the crack detection model to identify cracks on the surface of the pipeline, thereby generating a second detection result.

[0007] By adopting the above technical solution, the pipeline design parameters include multiple design parameters such as pipeline material, pipeline diameter, pipeline wall thickness and pipeline service environment; the first detection result is to judge the preliminary position of the potential crack area on the pipeline surface based on the pipeline material, pipeline diameter and pipeline wall thickness; the first detection result is mainly used to preliminarily screen out the area where cracks may exist, providing a basis for further detailed crack detection, and the second detection result is to input the pipeline high-resolution image data into the crack detection model, identify the crack position, crack width, crack length, crack depth and crack shape on the pipeline surface, and generate detailed crack detection results; the application preliminarily screens the potential crack area through the first detection result, and then conducts detailed identification through the second detection result, thereby improving the accuracy of crack detection, effectively reducing the false detection rate through the crack feature comparison table and the crack detection model, and improving the accuracy and reliability of pipeline crack detection, and realizing efficient detection of pipeline cracks through multi-step image processing and model generation methods, while considering multiple design parameters such as pipeline material, pipeline diameter, pipeline wall thickness and pipeline service environment, so that the crack detection model is more comprehensive and accurate, and can be applied to pipeline crack monitoring operations of various types of pipelines and environments, thereby improving the scope of application of pipeline crack detection methods.

[0008] In a preferred example of the present application, the step of obtaining pipeline 3D scanning image data and pipeline design parameters, and determining the first detection result and crack characteristics of the potential crack area on the pipeline surface according to the pipeline 3D scanning image data and the pipeline design parameters, specifically includes: Acquire pipeline 3D scanning image data and pipeline design parameters, wherein the pipeline 3D scanning image data includes 3D point cloud data and texture images of the pipeline surface, and the pipeline design parameters include pipeline material, pipeline diameter, pipeline wall thickness and pipeline service environment; Determine a first detection result of a potential crack area on a pipeline surface according to the pipeline material, the pipeline diameter and the pipeline wall thickness; According to the pipeline service environment and the texture image, crack characteristics of potential crack areas on the pipeline surface are determined to obtain crack characteristic information.

[0009] By adopting the above technical solution, the pipeline 3D scanning image data includes 3D point cloud data and texture images of the pipeline surface, as well as multi-dimensional data such as pipeline material, pipeline diameter, pipeline wall thickness and pipeline service environment, so as to more comprehensively reflect the state of the pipeline surface. The texture image provides surface detail information, which is conducive to improving the accuracy of crack detection. The first detection result of the potential crack area on the pipeline surface is judged according to the pipeline material, pipeline diameter and pipeline wall thickness, and the area where cracks may exist can be preliminarily screened out. Further, according to the pipeline service environment and texture image, the crack characteristics are judged to obtain crack feature information, thereby improving the accuracy of crack identification. Moreover, the present application comprehensively considers multiple parameters such as pipeline material, pipeline diameter, pipeline wall thickness and pipeline service environment, and can more accurately judge the potential crack area and reduce the false detection rate caused by a single parameter. The texture image extracts crack feature information, which can distinguish cracks from other surface defects (such as scratches, stains, etc.), further reducing the false detection rate. The high-resolution 3D point cloud data and texture image provide rich detail information, which helps to quickly and accurately identify cracks and improve the detection speed.

[0010] In a preferred example of the present application, the generation of a crack feature comparison table for comparing and adjusting the crack detection model according to the pipeline design parameters, the first detection result and the crack feature specifically includes: According to the pipe diameter and the pipe wall thickness, obtaining the theoretical crack width and length on the pipe surface; According to the pipeline material and the pipeline reconsideration environment, obtaining the theoretical crack depth and shape on the pipeline surface; A crack feature comparison table is generated according to the first detection result, the theoretical crack width, the theoretical crack length, the theoretical crack depth and the theoretical crack shape.

[0011] By adopting the above technical scheme, the theoretical crack width and length of the pipeline surface are obtained according to the pipeline diameter and pipeline wall thickness, and the theoretical crack depth and shape of the pipeline surface are obtained according to the pipeline material and pipeline service environment. A detailed theoretical crack parameter library is established. The theoretical crack parameters provide a scientific reference standard for crack detection and improve the accuracy of crack identification. The comprehensive judgment method of generating a crack feature comparison table by combining the first detection result with the theoretical crack parameter can more comprehensively evaluate the crack characteristics and ensure the reliability of the detection result. Multi-parameter comparison is realized based on the crack feature comparison table, and the actual detection results can be accurately matched with the theoretical crack parameters to ensure that only cracks that meet the standards are identified as real cracks, further reducing the possibility of false detection. The crack feature comparison table provides a standardized comparison standard, making the crack detection process more systematic and standardized. Through the use of the crack feature comparison table, the characteristics of potential crack areas can be quickly identified, unnecessary repeated detection can be reduced, and the detection speed can be improved.

[0012] In a preferred example of the present application, the obtaining of a crack detection reference range indicating crack detection accuracy and the generation of a crack detection model according to the crack detection reference range and the crack feature comparison table specifically include: Acquire a crack detection reference range that identifies crack detection accuracy, wherein the crack detection reference range includes a crack width threshold, a crack length threshold, a crack depth threshold, and a crack shape threshold; According to the crack width threshold, the crack length threshold, the crack depth threshold and the crack shape threshold, the crack features in the crack feature comparison table are screened to generate a crack detection model.

[0013] By adopting the above technical scheme, combined with the crack detection reference range, including crack width threshold, crack length threshold, crack depth threshold and crack shape threshold, the crack features in the crack feature comparison table are screened, so as to ensure that only crack features that meet the standards are included in the crack detection model, thereby improving the accuracy of crack identification. The crack detection model comprehensively considers multiple parameters such as crack width, length, depth and shape, and can more comprehensively evaluate crack characteristics to ensure the reliability of detection results.

[0014] In a preferred example of the present application, the step of obtaining high-resolution pipeline image data, inputting the high-resolution pipeline scan image into the crack detection model to identify cracks on the pipeline surface, and generating a second detection result specifically includes: obtaining high-resolution pipeline image data, wherein the high-resolution pipeline image data includes a high-resolution image of the pipeline surface; inputting the high-resolution pipeline image data into the crack detection model to identify the crack position, crack width, crack length, crack depth, and crack shape on the pipeline surface, and obtaining a crack detection result adjustment value; The parameters of the crack detection model are adjusted according to the crack detection result adjustment value, and the crack detection is performed again to generate a final second detection result.

[0015] By adopting the above technical solution, the high-resolution image of the pipeline surface provides rich detail information, which helps to more accurately identify the location, width, length, depth and shape of the cracks, that is, the high-resolution image can capture subtle crack characteristics; the crack detection model not only identifies the location of the crack, but also measures the width, length, depth and shape of the crack, providing comprehensive crack feature information; further, in the process of generating the second detection result, the parameters of the crack detection model are dynamically adjusted according to the crack detection result adjustment value, and the dynamic adjustment mechanism can ensure that the model is always in the best state and reduce false detections caused by fixed parameters; through high-resolution image data and multi-parameter recognition, crack characteristics can be matched more accurately.

[0016] In a preferred example of the present application: before generating a crack feature comparison table for comparing and adjusting a crack detection model according to the pipeline design parameters, the first detection result and the crack feature, the method further includes: Acquiring the light intensity and ambient temperature of the pipeline surface, and judging the image quality of the pipeline surface according to the light intensity and ambient temperature; According to the image quality, obtaining an image quality coefficient for adjusting the crack feature comparison table; The step of generating a crack feature comparison table for comparing and adjusting a crack detection model according to the pipeline design parameters, the first detection result and the crack feature specifically includes: A crack feature comparison table for comparing and adjusting a crack detection model is generated according to the image quality coefficient, the pipeline design parameter, the first detection result and the crack feature.

[0017] By adopting the above technical scheme, the image quality of the pipeline surface is judged in combination with the light intensity and ambient temperature of the pipeline surface; high-quality images can provide clearer and more detailed crack feature information. When generating the crack feature comparison table, not only the pipeline design parameters, the first detection results and the crack features are considered, but also the image quality coefficient is introduced. The method of comprehensively considering multiple parameters can more comprehensively reflect the actual situation of the pipeline surface and ensure the accuracy of the crack detection model; according to the image quality of the pipeline surface, the image quality coefficient for adjusting the crack feature comparison table is obtained, which can be used to correct the detection error caused by poor image quality and reduce the false detection rate; the present invention takes into account the influence of light intensity and ambient temperature on image quality, so that the crack detection method can adapt to different environmental conditions. By comprehensively considering the pipeline design parameters, the first detection results, the crack features and the image quality coefficient, the crack detection method can be applicable to different types of pipelines, thereby enhancing the scope of application of the method.

[0018] In a preferred example of the present application: the method further includes: Obtain pipeline operation status data, including pipeline pressure, temperature and vibration data; adjusting the sensitivity of the crack detection model according to the operating status data; The adjusted crack detection model is applied to the pipeline high-resolution scanning image data to generate a second detection result.

[0019] By adopting the above technical solution, the operating status data of the pipeline can provide a more comprehensive understanding of the real-time working status of the pipeline. According to the operating status data of the pipeline, the sensitivity of the crack detection model can be dynamically adjusted. By adopting dynamic adjustment, it can be ensured that the model can maintain high accuracy under different operating conditions, especially under extreme conditions, and cracks can be identified more accurately.

[0020] In the second aspect, the invention objective of the present application is achieved by adopting the following technical solutions: The pipeline crack detection system based on 3D scanning image monitoring is applied to the pipeline crack detection method based on 3D scanning image monitoring as described above, and the system includes: Data acquisition module, used to obtain pipeline 3D scanning image data and pipeline design parameters; A preliminary detection module, used to determine a first detection result and crack characteristics of a potential crack area on a pipeline surface according to the pipeline 3D scanning image data and the pipeline design parameters; A comparison table generating module, used for generating a crack feature comparison table for comparing and adjusting a crack detection model according to the pipeline design parameters, the first detection result and the crack feature; A model generation module, used to obtain a crack detection reference range representing crack detection accuracy, and generate a crack detection model according to the crack detection reference range and the crack feature comparison table; The crack detection module is used to obtain high-resolution image data of the pipeline, input the high-resolution scanning image of the pipeline into the crack detection model to identify cracks on the surface of the pipeline, and generate a second detection result.

[0021] In the third aspect, the invention objective of the present application is achieved by adopting the following technical solutions: A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned pipeline crack detection method based on 3D scanning image monitoring are implemented.

[0022] In a fourth aspect, the invention objective of the present application is achieved by adopting the following technical solutions: A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned pipeline crack detection method based on 3D scanning image monitoring are implemented.

[0023] In summary, the present application includes at least one of the following beneficial technical effects: 1. This application preliminarily screens potential crack areas through the first detection result, and then identifies them in detail through the second detection result, thereby improving the accuracy of crack detection. Through the crack feature comparison table and the crack detection model, the false detection rate is effectively reduced, and the accuracy and reliability of pipeline crack detection are improved. In addition, through multi-step image processing and model generation methods, efficient detection of pipeline cracks is achieved, while considering various design parameters such as pipeline material, pipeline diameter, pipeline wall thickness and pipeline service environment, making the crack detection model more comprehensive and accurate, and applicable to pipeline crack monitoring operations of various types of pipelines and environments, thereby improving the scope of application of pipeline crack detection methods; 2. Combine the light intensity and ambient temperature of the pipeline surface to judge the image quality of the pipeline surface; high-quality images can provide clearer and more detailed crack feature information. When generating the crack feature comparison table, not only the pipeline design parameters, the first detection results and the crack features are considered, but also the image quality coefficient is introduced. The method of comprehensively considering multiple parameters can more comprehensively reflect the actual situation of the pipeline surface and ensure the accuracy of the crack detection model; according to the image quality of the pipeline surface, the image quality coefficient used to adjust the crack feature comparison table is obtained, which can be used to correct the detection error caused by poor image quality and reduce the false detection rate; 3. The operating status data of the pipeline can provide a more comprehensive understanding of the real-time working status of the pipeline. According to the operating status data of the pipeline, the sensitivity of the crack detection model can be dynamically adjusted. By adopting dynamic adjustment, it can be ensured that the model can maintain high accuracy under different operating conditions, especially under extreme conditions, and cracks can be identified more accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 is a flow chart of a pipeline crack detection method based on 3D scanning image monitoring in one embodiment of the present application; Figure 2 This is a flowchart of step S1 in a pipeline crack detection method based on 3D scanning image monitoring in one embodiment of the present application; Figure 3 It is a schematic diagram of a device in an embodiment of the present application. DETAILED DESCRIPTION

[0025] The present application is further described in detail below in conjunction with the accompanying drawings.

[0026] In one embodiment, if Figure 1 As shown, the present application discloses a pipeline crack detection method based on 3D scanning image monitoring, which specifically includes the following steps: S1: Obtain pipeline 3D scanning image data and pipeline design parameters, and determine a first detection result and crack characteristics of a potential crack area on the pipeline surface according to the pipeline 3D scanning image data and pipeline design parameters.

[0027] In this embodiment, the pipeline 3D scanning image data includes 3D point cloud data and texture images of the pipeline surface, providing the geometric shape and texture details of the pipeline surface; the pipeline design parameters include pipeline material, pipeline diameter, pipeline wall thickness and pipeline service environment, etc., which are used to reflect the basic properties and usage conditions of the pipeline; the first detection result is to judge the preliminary location of the potential crack area on the pipeline surface based on the pipeline material, pipeline diameter and pipeline wall thickness; the first detection result is mainly used to preliminarily screen out areas where cracks may exist, providing a basis for further detailed crack detection; crack characteristics include crack width, length, depth and shape, etc., which are used to describe the specific form of the crack.

[0028] Specifically, a 3D scanner is used to scan the pipeline surface to obtain 3D point cloud data and texture images; parameters such as pipeline material, diameter, wall thickness and service environment are obtained from the pipeline design documents or the sensing data transmitted by the intelligent sensor preset on the pipeline; the position and range of the potential crack area are identified through image processing algorithm and edge detection algorithm to obtain the first detection result; in the potential crack area, the contour of the crack is obtained by using the contour extraction algorithm, and the depth of the crack is obtained by morphological analysis to obtain the crack characteristics.

[0029] S2: generating a crack feature comparison table for comparing and adjusting the crack detection model according to the pipeline design parameters, the first detection result and the crack feature.

[0030] In this embodiment, the crack feature comparison table includes parameters such as theoretical crack width, length, depth and shape, which are used to compare with actual detection results and adjust the parameters of the crack detection model; Specifically, firstly, the width and length of the theoretical crack are calculated according to the pipeline material, diameter and wall thickness to obtain the theoretical crack parameters, and then the depth and shape of the theoretical crack are estimated according to the reconsideration environment; then, the theoretical crack parameters are compared with the crack characteristics in the first detection result to generate a crack characteristic comparison table; the comparison table contains theoretical values ​​and actual values ​​of different crack characteristics, which are used to adjust the parameters of the crack detection model.

[0031] S3: Obtain a crack detection reference range representing crack detection accuracy, and generate a crack detection model according to the crack detection reference range and a crack feature comparison table.

[0032] In this embodiment, the crack detection reference range includes a crack width threshold, a crack length threshold, a crack depth threshold and a crack shape threshold, which are used to define the accuracy standard of crack detection; the crack detection model is a neural network intelligent model for identifying and evaluating cracks on the pipeline surface.

[0033] Specifically, a crack detection model is trained using a machine learning algorithm (such as support vector machine, deep learning, etc.). The training data includes theoretical values ​​and actual values ​​in the crack feature comparison table. The goal of the crack detection model is to accurately identify cracks within a given crack detection reference range.

[0034] S4: Acquire high-resolution image data of the pipeline, input the high-resolution scanning image of the pipeline into the crack detection model to identify cracks on the surface of the pipeline, and generate a second detection result.

[0035] In this embodiment, the high-resolution image data of the pipeline is obtained, including a high-resolution image of the pipeline surface, providing detailed surface information; the second detection result is to input the high-resolution image data of the pipeline into a crack detection model, identify the crack position, crack width, crack length, crack depth and crack shape on the pipeline surface, and generate a detailed crack detection result.

[0036] Specifically, a high-resolution camera is used to scan the pipeline surface to obtain a high-resolution image. The high-resolution image data is input into a trained crack detection model. The model outputs information such as the location, width, length, depth and shape of the cracks. Based on the output of the model, a final crack detection report is generated, including the specific location, size and shape of the cracks.

[0037] For example, petrochemical pipelines operate under high temperature and high pressure for a long time, which is prone to cracks. Regular inspections are required to ensure safety: pipeline design parameters are collected by obtaining parameters such as pipeline material (such as carbon steel), diameter (such as 1 meter), wall thickness (such as 10 mm) and service environment (such as high temperature and high pressure) from the design documents of petrochemical pipelines. The actual parameters of the service environment can also be detected by preset pressure sensors and temperature sensors; in the potential crack area, the width, length, depth and shape of the crack are extracted; according to the standards of the petrochemical industry, the accuracy standards for crack detection are defined, including crack width threshold (such as 0.5 mm), crack length threshold (such as 10 mm), crack depth threshold (such as 1 mm) and crack shape threshold, and high-resolution image data is input into the trained crack detection model. The model outputs information such as the location, width, length, depth and shape of the crack, and then generates a final crack detection report.

[0038] In one embodiment, if Figure 2 As shown, in step S1, the pipeline 3D scanning image data and pipeline design parameters are obtained, and the first detection result and crack characteristics of the potential crack area on the pipeline surface are determined according to the pipeline 3D scanning image data and pipeline design parameters, which specifically includes: S11: Acquire pipeline 3D scanning image data and pipeline design parameters. The pipeline 3D scanning image data includes 3D point cloud data and texture images of the pipeline surface. The pipeline design parameters include pipeline material, pipeline diameter, pipeline wall thickness and pipeline service environment.

[0039] In this embodiment, the parameters of pipeline material (such as carbon steel, stainless steel, etc.), pipeline diameter (such as 1 meter), pipeline wall thickness (such as 10 mm) and pipeline service environment (such as high temperature and high pressure, corrosive environment, etc.) reflect the basic properties and usage conditions of the pipeline.

[0040] Specifically, a 3D scanner is used to scan the pipeline surface to obtain 3D point cloud data, and a high-resolution camera is used to photograph the pipeline surface to obtain a texture image to obtain the pipeline 3D scanning image data, and the design parameters such as pipeline material, diameter, wall thickness and service environment are obtained from the pipeline design document.

[0041] S12: Determine a first detection result of a potential crack area on the pipeline surface according to the pipeline material, pipeline diameter and pipeline wall thickness.

[0042] In this embodiment, the crack edge is identified by edge detection algorithm, and the potential crack area is extracted by region segmentation algorithm, so as to complete the preliminary analysis of 3D point cloud data; the crack tendency of the material under specific conditions is evaluated in combination with the characteristics of the pipeline material (such as hardness, elastic modulus, etc.), for example, carbon steel is more likely to crack under high temperature environment, so as to realize the analysis of pipeline material characteristics; and the structural stability of the pipeline is evaluated according to the pipeline diameter and wall thickness. Pipes with larger diameters are more likely to crack when subjected to external pressure, and pipes with thinner wall thickness are more likely to crack under internal pressure, so as to realize the analysis of pipeline geometric dimensions.

[0043] S13: judging crack characteristics of potential crack areas on the pipeline surface according to the pipeline service environment and the texture image, and obtaining crack characteristic information.

[0044] In this embodiment, the impact of the environment on the pipeline material is evaluated according to the service environment of the pipeline (such as high temperature and high pressure, corrosive environment, etc.). For example, creep and fatigue of materials in a high temperature environment are more likely to cause cracks, so as to realize the analysis of the impact of the pipeline environment; then, in the potential crack area, an image processing algorithm is used to extract crack width, length, depth, shape and other features. For example, the contour of the crack is obtained by combining a contour extraction algorithm, and the depth of the crack is obtained by morphological analysis; the extracted crack feature information is summarized to generate a first detection result.

[0045] In one embodiment, in step S2, a crack feature comparison table for comparing and adjusting the crack detection model is generated according to the pipeline design parameters, the first detection result and the crack feature, which specifically includes: S21: Obtain theoretical crack width and length on the pipeline surface based on the pipeline diameter and pipeline wall thickness.

[0046] Specifically, the pipe diameter refers to the inner diameter or outer diameter of the pipe; the theoretical crack width and length refer to the theoretical width and length of cracks that may appear on the pipe surface calculated based on the pipe diameter and wall thickness through mechanical analysis and empirical formulas.

[0047] Specifically, use finite element analysis software (such as ANSYS, ABAQUS) to perform mechanical analysis on the pipeline, simulate the stress distribution of pipelines with different diameters and wall thicknesses under stress, find out the areas where cracks may occur, and use empirical formulas to calculate the theoretical crack width and length based on existing research and engineering practice. For example, for carbon steel pipes, the crack width and length can be calculated according to the formula in the API standard. The results of mechanical analysis and empirical formula calculations are summarized to generate a database of theoretical crack widths and lengths.

[0048] S22: Obtain theoretical crack depth and shape on the pipeline surface based on pipeline material and pipeline reconsideration environment.

[0049] In this embodiment, pipeline material refers to the type of material used for the pipeline, such as carbon steel, stainless steel, etc., and pipeline service environment refers to the environmental conditions in which the pipeline is located, such as temperature, pressure, corrosive media, etc., which affect the aging and damage of the material; theoretical crack depth and shape refers to the theoretical depth and shape of cracks that may appear on the pipeline surface obtained through simulation and experimental data based on the mechanical properties of the pipeline material and the service environment.

[0050] Specifically, when analyzing material properties, the crack tendency of the material under specific conditions is evaluated based on the mechanical properties of the pipeline material (such as yield strength, fracture toughness, etc.). For example, carbon steel is more susceptible to intergranular corrosion in high-temperature environments, leading to cracks. When analyzing environmental impacts, the impact of the environment on the material is evaluated based on the pipeline service environment (such as high temperature and high pressure, corrosive media, etc.). For example, creep and fatigue of the material are more likely to cause cracks in high-temperature and high-pressure environments. The theoretical depth and shape of cracks that may appear on the pipeline surface are obtained through numerical simulation and experimental testing. For example, finite element software is used to simulate material damage in different environments, or actual fatigue tests are conducted.

[0051] S23: Generate a crack feature comparison table according to the first detection result, the theoretical crack width, the theoretical crack length, the theoretical crack depth and the theoretical crack shape.

[0052] In this embodiment, the crack feature comparison table refers to comparing the first detection result with the theoretical crack parameters to generate a comparison table containing crack features for adjusting the parameters of the crack detection model.

[0053] Specifically, data processing software (such as Python, MATLAB, etc.) is used to compare the first detection result with the theoretical crack parameters to generate a crack feature comparison table, and the parameters of the crack detection model are adjusted according to the data in the comparison table to ensure the accuracy and reliability of the model in practical applications.

[0054] In one embodiment, in step S3, a crack detection reference range indicating crack detection accuracy is obtained, and a crack detection model is generated according to the crack detection reference range and a crack feature comparison table, specifically including: S31: Obtaining a crack detection reference range for identifying crack detection accuracy, where the crack detection reference range includes a crack width threshold, a crack length threshold, a crack depth threshold, and a crack shape threshold.

[0055] In this embodiment, the crack width threshold is used to define the minimum and maximum values ​​of the crack width, which is used to screen the crack characteristics; the crack length threshold is used to define the minimum and maximum values ​​of the crack length, which is used to screen the crack characteristics; the crack depth threshold is used to define the minimum and maximum values ​​of the crack depth, which is used to screen the crack characteristics; the crack shape threshold is used to define the characteristics of the crack shape, such as straight type, curved type, etc., which is used to screen the crack characteristics.

[0056] S32: According to the crack width threshold, the crack length threshold, the crack depth threshold and the crack shape threshold, the crack features in the crack feature comparison table are screened to generate a crack detection model.

[0057] In this embodiment, screening crack features refers to screening crack features that meet the standards from a crack feature comparison table according to a threshold value in a crack detection reference range.

[0058] Specifically, a screening algorithm can be written in a programming language (such as Python, MATLAB), and crack features that meet the standards can be screened out from a crack feature comparison table based on the threshold in the crack detection reference range; then a machine learning algorithm (such as support vector machine, deep learning, etc.) is used to train the crack detection model. The training data includes the screened crack features. The goal of the model is to accurately identify cracks within a given crack detection reference range.

[0059] In one embodiment, in step S4, high-resolution pipeline image data is obtained, and the high-resolution pipeline scan image is input into a crack detection model to identify cracks on the pipeline surface, and a second detection result is generated, which specifically includes: S41: Acquire pipeline high-resolution image data, where the pipeline high-resolution image data includes a high-resolution image of the pipeline surface.

[0060] In this embodiment, high-resolution image data refers to photographing the pipeline surface with a high-resolution camera to obtain a detailed surface image; and preprocessing the obtained high-resolution image data, such as denoising, contrast enhancement, etc., to improve image quality.

[0061] S42: Inputting the high-resolution pipeline image data into the crack detection model, identifying the crack position, crack width, crack length, crack depth and crack shape on the pipeline surface, and obtaining the crack detection result adjustment value.

[0062] Specifically, the preprocessed high-resolution image data is input into the trained crack detection model, and the crack detection model outputs information such as the location, width, length, depth and shape of the crack. According to the output results of the crack detection model, the crack detection result adjustment value is obtained for subsequent model parameter adjustment.

[0063] S43: adjusting the parameters of the crack detection model according to the crack detection result adjustment value, re-performing crack detection, and generating a final second detection result.

[0064] Specifically, according to the adjustment value of the crack detection result, the parameters of the crack detection model are dynamically adjusted to optimize the performance of the model. For example, the threshold, weight and other parameters of the model are adjusted, and the adjusted model is used again to re-perform crack detection to generate a final second detection result, thereby ensuring the accuracy and reliability of the detection.

[0065] In one embodiment, before step S2, the pipeline crack detection method based on 3D scanning image monitoring further includes: S201: obtaining the light intensity and ambient temperature of the pipeline surface, and judging the image quality of the pipeline surface according to the light intensity and ambient temperature.

[0066] In this embodiment, light intensity refers to the light intensity on the pipe surface, which affects the brightness and contrast of the image; ambient temperature refers to the temperature on the pipe surface, which affects the physical properties of the material and the performance of the image sensor; image quality evaluates the quality of the acquired image, including clarity, contrast, and noise level, based on light intensity and ambient temperature.

[0067] Specifically, a light intensity meter is used to measure the light intensity on the pipeline surface to ensure that the light is uniform and sufficient. A temperature sensor is used to measure the temperature of the pipeline surface to ensure that the temperature is within a reasonable range. Image processing software is used to evaluate the quality of the acquired image, including clarity, contrast, and noise level, such as by calculating the signal-to-noise ratio (SNR) and contrast of the image.

[0068] S202: Obtaining an image quality coefficient for adjusting the crack feature comparison table according to the image quality.

[0069] In this embodiment, the image quality coefficient is a coefficient generated according to the image quality evaluation result, and is used to adjust the parameters in the crack feature comparison table.

[0070] Specifically, an image quality coefficient is generated based on the image quality assessment results. For example, if the image quality is good, the coefficient is close to 1; if the image quality is poor, the coefficient is less than 1. This application will apply the image quality coefficient to the subsequent crack feature comparison table generation process to adjust the weights and thresholds of the crack features.

[0071] For example, suppose that in the inspection of a section of a city water supply pipeline, the image quality assessment result shows that the image quality is average, and the image quality coefficient is set to 0.8; after crack feature extraction, the following information is recorded: Crack position: (x1, y1); Crack width: 10 mm; Crack length: 50 mm; Crack depth: 2 mm; Crack shape: linear; According to the image quality factor of 0.8, adjust the weight and threshold of the crack feature: Crack width weight adjustment: the original weight is 1.0, and after adjustment it is 1.0*0.8=0.8.

[0072] Crack length weight adjustment: the original weight is 1.0, and after adjustment it is 1.0*0.8=0.8.

[0073] Crack detection threshold adjustment: the original threshold is 0.5, and after adjustment it is 0.5*0.8=0.4.

[0074] By applying the image quality coefficient to the generation process of the crack feature comparison table and adjusting the weights and thresholds of the crack features, the accuracy and robustness of crack detection can be significantly improved.

[0075] Further, in step S2, a crack feature comparison table for comparing and adjusting the crack detection model is generated according to the pipeline design parameters, the first detection result and the crack feature, which specifically includes: S211: generating a crack feature comparison table for comparing and adjusting a crack detection model according to the image quality coefficient, the pipeline design parameter, the first detection result and the crack feature.

[0076] In this embodiment, the image quality coefficient, pipeline design parameters, the first detection result and the crack characteristics are integrated, for example, using data processing software (such as Python, MATLAB), and a crack characteristic comparison table is generated according to the integrated data.

[0077] In one embodiment, the pipeline crack detection method based on 3D scanning image monitoring further includes: S10: Obtaining pipeline operation status data, including pipeline pressure, temperature and vibration data.

[0078] In this embodiment, the operating status data refers to the real-time data collected during the operation of the pipeline, mainly including parameters such as pressure, temperature and vibration, which reflects the physical state of the pipeline under actual working conditions and helps to understand the environment in which the pipeline is located and the stress conditions it may face.

[0079] S20: Adjust the sensitivity of the crack detection model according to the operating status data.

[0080] In this embodiment, sensitivity refers to the ability of the model to detect crack features. By adjusting the sensitivity, the model can more accurately identify cracks under different working conditions to avoid over-detection or missed detection.

[0081] Specifically, vibration sensors are used to monitor the vibration of pipelines caused by external factors (such as traffic and construction).

[0082] S30: Applying the adjusted crack detection model to the pipeline high-resolution scanning image data to generate a second detection result.

[0083] Specifically, the second detection result includes a crack with a length of 50 mm and a width of 2 mm found in a certain section of the pipeline, and the crack is distributed linearly.

[0084] It should be understood that the serial numbers of the steps in the above embodiments do not imply a sequence of execution. The execution sequence 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 application.

[0085] In one embodiment, a pipeline crack detection system based on 3D scanning image monitoring is provided. The pipeline crack detection system based on 3D scanning image monitoring corresponds to the pipeline crack detection method based on 3D scanning image monitoring in the above embodiment.

[0086] The pipeline crack detection system based on 3D scanning image monitoring includes a data acquisition module, a preliminary detection module, a comparison table generation module, a model generation module and a crack detection module. The detailed description of each functional module is as follows: Data acquisition module, used to obtain pipeline 3D scanning image data and pipeline design parameters; A preliminary detection module, used to determine a first detection result and crack characteristics of a potential crack area on a pipeline surface according to the pipeline 3D scanning image data and the pipeline design parameters; A comparison table generating module, used for generating a crack feature comparison table for comparing and adjusting a crack detection model according to the pipeline design parameters, the first detection result and the crack feature; A model generation module, used to obtain a crack detection reference range representing crack detection accuracy, and generate a crack detection model according to the crack detection reference range and the crack feature comparison table; The crack detection module is used to obtain high-resolution image data of the pipeline, input the high-resolution scanning image of the pipeline into the crack detection model to identify cracks on the surface of the pipeline, and generate a second detection result.

[0087] For the specific limitations of the pipeline crack detection system based on 3D scanning image monitoring, please refer to the limitations of the pipeline crack detection method based on 3D scanning image monitoring above, which will not be repeated here; each module in the above-mentioned pipeline crack detection system based on 3D scanning image monitoring can be implemented in whole or in part through software, hardware and a combination thereof; each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0088] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store pipeline 3D scanning image data, a first detection result and a second detection result. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a pipeline crack detection method based on 3D scanning image monitoring is implemented.

[0089] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: S1: Acquire pipeline 3D scanning image data and pipeline design parameters, and determine a first detection result and crack characteristics of a potential crack area on the pipeline surface according to the pipeline 3D scanning image data and the pipeline design parameters; S2: generating a crack feature comparison table for comparing and adjusting a crack detection model according to the pipeline design parameters, the first detection result and the crack feature; S3: obtaining a crack detection reference range indicating crack detection accuracy, and generating a crack detection model according to the crack detection reference range and the crack feature comparison table; S4: Acquire high-resolution image data of the pipeline, input the high-resolution scanned image of the pipeline into the crack detection model to identify cracks on the surface of the pipeline, and generate a second detection result.

[0090] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: S1: Acquire pipeline 3D scanning image data and pipeline design parameters, and determine a first detection result and crack characteristics of a potential crack area on the pipeline surface according to the pipeline 3D scanning image data and the pipeline design parameters; S2: generating a crack feature comparison table for comparing and adjusting a crack detection model according to the pipeline design parameters, the first detection result and the crack feature; S3: obtaining a crack detection reference range indicating crack detection accuracy, and generating a crack detection model according to the crack detection reference range and the crack feature comparison table; S4: Acquire high-resolution image data of the pipeline, input the high-resolution scanned image of the pipeline into the crack detection model to identify cracks on the surface of the pipeline, and generate a second detection result.

[0091] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0092] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0093] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments may still be modified, or some of the features thereof may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A pipeline crack detection method based on 3D scanning image monitoring, characterized in that: include: Acquire pipeline 3D scanning image data and pipeline design parameters, and determine a first detection result and crack characteristics of a potential crack area on the pipeline surface according to the pipeline 3D scanning image data and the pipeline design parameters; Generating a crack feature comparison table for comparing and adjusting a crack detection model according to the pipeline design parameters, the first detection result and the crack feature; Acquire a crack detection reference range indicating crack detection accuracy, and generate a crack detection model according to the crack detection reference range and the crack feature comparison table; High-resolution image data of the pipeline is acquired, and the high-resolution scanning image of the pipeline is input into the crack detection model to identify cracks on the surface of the pipeline, thereby generating a second detection result.

2. The pipeline crack detection method based on 3D scanning image monitoring according to claim 1 is characterized in that: The step of acquiring pipeline 3D scanning image data and pipeline design parameters, and determining a first detection result and crack characteristics of a potential crack area on the pipeline surface according to the pipeline 3D scanning image data and the pipeline design parameters, specifically includes: Acquire pipeline 3D scanning image data and pipeline design parameters, wherein the pipeline 3D scanning image data includes 3D point cloud data and texture images of the pipeline surface, and the pipeline design parameters include pipeline material, pipeline diameter, pipeline wall thickness and pipeline service environment; Determine a first detection result of a potential crack area on a pipeline surface according to the pipeline material, the pipeline diameter and the pipeline wall thickness; According to the pipeline service environment and the texture image, crack characteristics of potential crack areas on the pipeline surface are determined to obtain crack characteristic information.

3. The pipeline crack detection method based on 3D scanning image monitoring according to claim 1 is characterized in that: The step of generating a crack feature comparison table for comparing and adjusting a crack detection model according to the pipeline design parameters, the first detection result and the crack feature specifically includes: According to the pipe diameter and the pipe wall thickness, obtaining the theoretical crack width and length on the pipe surface; According to the pipeline material and the pipeline reconsideration environment, obtaining the theoretical crack depth and shape on the pipeline surface; A crack feature comparison table is generated according to the first detection result, the theoretical crack width, the theoretical crack length, the theoretical crack depth and the theoretical crack shape.

4. The pipeline crack detection method based on 3D scanning image monitoring according to claim 1 is characterized in that: The obtaining of a crack detection reference range indicating crack detection accuracy and generating a crack detection model according to the crack detection reference range and the crack feature comparison table specifically includes: Acquire a crack detection reference range that identifies crack detection accuracy, wherein the crack detection reference range includes a crack width threshold, a crack length threshold, a crack depth threshold, and a crack shape threshold; According to the crack width threshold, the crack length threshold, the crack depth threshold and the crack shape threshold, the crack features in the crack feature comparison table are screened to generate a crack detection model.

5. The pipeline crack detection method based on 3D scanning image monitoring according to claim 1 is characterized in that: The step of acquiring high-resolution pipeline image data, inputting the high-resolution pipeline scan image into the crack detection model to identify cracks on the pipeline surface, and generating a second detection result specifically includes: Acquiring high-resolution pipeline image data, wherein the high-resolution pipeline image data includes a high-resolution image of the pipeline surface; Inputting the pipeline high-resolution image data into a crack detection model, identifying the crack position, crack width, crack length, crack depth and crack shape on the pipeline surface, and obtaining a crack detection result adjustment value; The parameters of the crack detection model are adjusted according to the crack detection result adjustment value, and the crack detection is performed again to generate a final second detection result.

6. The pipeline crack detection method based on 3D scanning image monitoring according to claim 1 or 3 is characterized in that: Before generating a crack feature comparison table for comparing and adjusting a crack detection model according to the pipeline design parameters, the first detection result and the crack feature, the method further includes: Acquiring the light intensity and ambient temperature of the pipeline surface, and judging the image quality of the pipeline surface according to the light intensity and ambient temperature; According to the image quality, obtaining an image quality coefficient for adjusting the crack feature comparison table; The step of generating a crack feature comparison table for comparing and adjusting a crack detection model according to the pipeline design parameters, the first detection result and the crack feature specifically includes: A crack feature comparison table for comparing and adjusting a crack detection model is generated according to the image quality coefficient, the pipeline design parameter, the first detection result and the crack feature.

7. The pipeline crack detection method based on 3D scanning image monitoring according to claim 1 or 6 is characterized in that: The method further comprises: Obtain pipeline operation status data, including pipeline pressure, temperature and vibration data; adjusting the sensitivity of the crack detection model according to the operating status data; The adjusted crack detection model is applied to the pipeline high-resolution scanning image data to generate a second detection result.

8. The pipeline crack detection system based on 3D scanning image monitoring is characterized by: Applied to the pipeline crack detection method based on 3D scanning image monitoring as described in any one of claims 1 to 7, the system comprises: Data acquisition module, used to obtain pipeline 3D scanning image data and pipeline design parameters; A preliminary detection module, used to determine a first detection result and crack characteristics of a potential crack area on a pipeline surface according to the pipeline 3D scanning image data and the pipeline design parameters; A comparison table generating module, used for generating a crack feature comparison table for comparing and adjusting a crack detection model according to the pipeline design parameters, the first detection result and the crack feature; A model generation module, used to obtain a crack detection reference range representing crack detection accuracy, and generate a crack detection model according to the crack detection reference range and the crack feature comparison table; The crack detection module is used to obtain high-resolution image data of the pipeline, input the high-resolution scanning image of the pipeline into the crack detection model to identify cracks on the surface of the pipeline, and generate a second detection result.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the pipeline crack detection method based on 3D scanning image monitoring as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the pipeline crack detection method based on 3D scanning image monitoring as claimed in any one of claims 1 to 7 are implemented.

Images