A visual detection method for surface crack defects of metal pipes based on image processing

Abstract

The present invention discloses a method for visual detection of crack defects on the surface of metal pipes based on image processing, which specifically relates to the field of defect detection technology; by acquiring an image of the surface of a metal pipe, combining a regional growth algorithm, and dividing the area into a high-incidence area and a low-incidence area of ​​crack defects based on the crack distribution law. The time dimension change trend analysis is performed on the high-incidence area of ​​crack defects to evaluate the risk of crack extension; the significance of the crack is evaluated by image texture feature analysis, and the crack severity level is determined by combining the extension risk and significance. The working environment of the high-incidence area of ​​crack defects is analyzed for its impact on the structural integrity of the metal pipe. Through a comprehensive analysis of the impact of crack extension risk, significance and structural integrity, the detection sensitivity of the regional growth algorithm is dynamically adjusted, and multi-dimensional and dynamic detection and evaluation of crack defects are realized, the accuracy and efficiency of crack detection are improved, and reliable protection is provided for the safety of metal pipes.

Description

Technical Field

[0001] The present invention relates to the technical field of defect detection, and more specifically, to a method for visually detecting surface crack defects of metal pipes based on image processing. Background Art

[0002] Traditional crack detection methods, including manual detection, ultrasonic detection or simple visual detection, are difficult to meet the needs of high-precision, automated and real-time detection. Traditional crack detection methods can often only perform static analysis of cracks at a single moment, ignoring the dynamic expansion characteristics of cracks in the time dimension. At the same time, there is also a lack of in-depth analysis of crack texture characteristics, and the impact of the working environment of the pipe on the integrity of the crack structure is not fully considered. Among the existing crack detection technologies, although the detection method based on image processing has improved the level of automation to a certain extent, it lacks a systematic analysis of the dynamic changes of cracks, significance evaluation, and the comprehensive impact of the working environment, and cannot provide a comprehensive and reliable evaluation basis for crack detection.

[0003] In order to solve the above problems, a technical solution is now provided. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a visual detection method for surface crack defects of metal pipes based on image processing to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A method for visually detecting surface crack defects of metal pipes based on image processing comprises the following steps:

[0007] Use a high-resolution industrial camera to obtain images of the metal pipe surface. Based on the crack distribution law of the metal pipe, use the regional growth algorithm to locate the crack area and divide the metal pipe surface area into a high-incidence crack defect area and a low-incidence crack defect area.

[0008] Analyze the changing trend of crack defect high-incidence areas in the time dimension to assess the expansion risk of crack defects on the surface of metal pipes;

[0009] Analyze the image texture features of the crack defect-prone areas to evaluate the significance of the crack defects on the surface of the metal pipe;

[0010] Based on the expansion risk of the crack defect on the metal pipe surface and the significance of the crack defect on the metal pipe surface, the severity level of the crack defect on the metal pipe surface is determined; the severity level includes a high severity level and a low severity level;

[0011] Analyze the working environment of metal pipes in areas with high incidence of crack defects and evaluate the impact of crack defects on the structural integrity of metal pipes;

[0012] By comprehensively analyzing the expansion risk of crack defects on the metal pipe surface, the significance of crack defects on the metal pipe surface, and the impact of crack defects on the structural integrity of the metal pipe, the detection sensitivity of the region growing algorithm to the metal pipe surface is adjusted.

[0013] In a preferred embodiment, a high-resolution industrial camera is used to obtain an image of the surface of the metal pipe. Based on the crack distribution law of the metal pipe, a regional growth algorithm is used to locate the crack area, and the surface area of ​​the metal pipe is divided into a high-incidence area of ​​crack defects and a low-incidence area of ​​crack defects, specifically:

[0014] Capture original image data of the pipe surface through high-resolution industrial cameras;

[0015] Extract crack candidate areas based on pipe crack distribution characteristics;

[0016] The region growing algorithm is used to determine the crack area in the image: the core of the region growing algorithm is to start from the selected seed point and find pixels that meet the grayscale similarity condition to add to the crack area until all pixels do not meet the expansion condition; the seed point is selected based on the high grayscale gradient area;

[0017] The surface of the metal pipe is divided according to the crack density: a sliding window of fixed size is defined, which slides across the entire image and the number of crack pixels in the window is counted; the crack density is defined as the ratio of crack pixels in the window to the total pixels;

[0018] By setting the demarcation threshold of crack density, the area with crack density higher than or equal to the demarcation threshold is divided into the area with high incidence of crack defects, and the area with crack density lower than the demarcation threshold is divided into the area with low incidence of crack defects.

[0019] In a preferred embodiment, the variation trend of the crack defect high-incidence area in the time dimension is analyzed to evaluate the expansion risk of the crack defect on the surface of the metal pipe, specifically:

[0020] Capture images of the crack area at consecutive time points;

[0021] Quantitative comparison of crack boundaries in multi-temporal images;

[0022] Calculate the crack propagation rate at different time intervals;

[0023] Crack propagation risk assessment based on rate change index: The risk of crack propagation depends not only on the current diffusion rate, but also on the rate change trend. By statistically analyzing the diffusion rates at multiple consecutive time points, a crack propagation trend curve is constructed to assess the crack propagation risk. The rate change index is expressed as: ;in, Indicates rate change index; is the number of time points; For at time point The crack propagation rate.

[0024] In a preferred embodiment, the image texture feature analysis of the crack defect high-incidence area is performed to evaluate the significance of the crack defect on the metal pipe surface, specifically:

[0025] Extracting texture feature vectors from areas with high incidence of crack defects;

[0026] Compare the differences in texture parameter distribution between the texture features of areas with high crack defect incidence and areas with low crack defect incidence;

[0027] Quantifying texture saliency using statistical models: Based on the differences in texture feature distribution, the saliency of crack texture is quantified using statistical models. The saliency score is expressed as ;in, is the significance score; it represents the Euclidean distance between the texture features of the crack defect high incidence area and the crack defect low incidence area; Weight parameters to adjust the sensitivity of the model; is the offset used to balance the significance score range; Represents the Euclidean distance between the texture features of the area with high crack defect incidence and the area with low crack defect incidence.

[0028] In a preferred embodiment, the severity level of the crack defect on the surface of the metal pipe is determined based on the expansion risk of the crack defect on the surface of the metal pipe and the significance of the crack defect on the surface of the metal pipe; the severity level includes a high severity level and a low severity level, specifically:

[0029] Preset the rate change index threshold and compare the rate change index with the rate change index threshold:

[0030] When the rate change index is greater than the rate change index threshold, the severity level of the metal pipe surface crack defect is high severity level;

[0031] When the rate change index is less than or equal to the rate change index threshold, the severity level of the metal pipe surface crack defect is low severity level;

[0032] Preset significance score threshold and compare the significance score with the significance score threshold:

[0033] When the significance score is greater than the significance score threshold, the severity level of the metal pipe surface crack defect is a high severity level;

[0034] When the significance score is less than or equal to the significance score threshold, the severity level of the metal pipe surface crack defect is low severity level;

[0035] When the rate change index is greater than the rate change index threshold and the significance score is greater than the significance score threshold, the severity level of the metal pipe surface crack defect is a high severity level; otherwise, the severity level of the metal pipe surface crack defect is a low severity level.

[0036] In a preferred embodiment, the working environment of the metal pipe in the crack defect prone area is analyzed to evaluate the influence of the crack defect on the structural integrity of the metal pipe, specifically:

[0037] Collect working environment parameters in areas with high crack incidence;

[0038] Analyze the influence of environmental parameters on the properties of metal materials and define the influence model of environmental parameters on the performance of metal pipe materials;

[0039] Evaluate the dynamic impact of environmental factors on structural integrity: Define the structural integrity coefficient to evaluate the impact of the environment on the structural integrity of metal pipes. The calculation formula is: ;in, is the structural integrity coefficient; is the total number of material performance parameters; is the index of material performance parameters; Indicates The absolute change in a material property; Indicates Initial value of a material property.

[0040] In a preferred embodiment, the detection sensitivity of the region growing algorithm to the metal pipe surface is adjusted by comprehensively analyzing the expansion risk of the crack defect on the metal pipe surface, the significance of the crack defect on the metal pipe surface, and the influence of the crack defect on the structural integrity of the metal pipe, specifically:

[0041] The rate change index corresponding to the expansion risk of crack defects on the metal pipe surface, the significance score corresponding to the significance of crack defects on the metal pipe surface, and the structural integrity coefficient corresponding to the degree of influence of crack defects on the structural integrity of the metal pipe are normalized, and the normalized rate change index, significance score and structural integrity coefficient are comprehensively analyzed to calculate the comprehensive risk coefficient. The calculation formula is: ;

[0042] in, represents the comprehensive risk factor; represent rate change index, significance score and structural integrity coefficient respectively;

[0043] Preset the comprehensive risk factor threshold and compare the comprehensive risk factor with the comprehensive risk factor threshold:

[0044] When the comprehensive risk factor is greater than or equal to the comprehensive risk factor threshold, the detection sensitivity of the region growing algorithm should be improved;

[0045] When the comprehensive risk coefficient is greater than or equal to the comprehensive risk coefficient threshold, the detection sensitivity of the region growing algorithm is reduced.

[0046] The technical effects and advantages of the visual detection method for metal pipe surface crack defects based on image processing of the present invention are as follows:

[0047] The surface image of the metal pipe is acquired by a high-resolution industrial camera, and the crack area is located and divided in combination with the regional growing algorithm, which improves the sensitivity and accuracy of crack detection. The changing trend of the crack defect high-incidence area in the time dimension is further analyzed to evaluate the risk of crack extension; the significance of the crack is quantified through image texture feature analysis to ensure a comprehensive evaluation of different crack characteristics. The severity level of the crack defect is determined by combining the risk and significance of crack extension. By analyzing the working environment of the crack defect high-incidence area, the impact of the crack on the structural integrity of the metal pipe is accurately evaluated, which improves the practicality of the detection scheme. Comprehensively analyzing the crack extension risk, significance and structural integrity impact, dynamically adjusting the detection sensitivity of the regional growing algorithm, achieving accurate detection and efficient processing of crack defects, improving the reliability and safety of metal pipe detection, and having important industrial application value. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a schematic diagram of a method for visually detecting surface crack defects of metal pipes based on image processing according to the present invention. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Example

[0050] Figure 1 The present invention provides a method for visually detecting surface crack defects of metal pipes based on image processing, which comprises the following steps:

[0051] Use a high-resolution industrial camera to obtain images of the metal pipe surface. Based on the crack distribution law of the metal pipe, use the regional growth algorithm to locate the crack area and divide the metal pipe surface area into a high-incidence crack defect area and a low-incidence crack defect area.

[0052] Analyze the changing trend of crack defect high-incidence areas in the time dimension to assess the expansion risk of crack defects on the surface of metal pipes;

[0053] Analyze the image texture features of the crack defect-prone areas to evaluate the significance of the crack defects on the surface of the metal pipe;

[0054] Based on the expansion risk of the crack defect on the metal pipe surface and the significance of the crack defect on the metal pipe surface, the severity level of the crack defect on the metal pipe surface is determined; the severity level includes a high severity level and a low severity level;

[0055] Analyze the working environment of metal pipes in areas with high incidence of crack defects and evaluate the impact of crack defects on the structural integrity of metal pipes;

[0056] By comprehensively analyzing the expansion risk of crack defects on the metal pipe surface, the significance of crack defects on the metal pipe surface, and the impact of crack defects on the structural integrity of the metal pipe, the detection sensitivity of the region growing algorithm to the metal pipe surface is adjusted.

[0057] Specifically, a high-resolution industrial camera is used to obtain images of the metal pipe surface. Based on the crack distribution law of the metal pipe, a regional growth algorithm is used to locate the crack area, and the surface area of ​​the metal pipe is divided into a high-incidence area of ​​crack defects and a low-incidence area of ​​crack defects, including:

[0058] Capture the original image data of the pipe surface through a high-resolution industrial camera: Real-time image acquisition of the metal pipe surface is performed through a high-resolution industrial camera to ensure that the details of small defects such as cracks can be fully captured. In order to avoid image blur caused by the movement of the metal pipe during the acquisition process, the synchronous trigger technology is used to control the camera's shooting timing to make the image acquisition process stable and reliable. The resolution of the industrial camera is optimized during acquisition to meet the needs of accurate observation of the crack area. The acquired original image data is represented in the form of a two-dimensional matrix, in which each pixel corresponds to the grayscale value of a specific position.

[0059] Extract crack candidate areas based on pipe crack distribution characteristics: Normalize the grayscale of the collected image to eliminate the deviation caused by uneven illumination intensity. In the normalized image, cracks usually appear as high grayscale gradient areas. The gradient operator is used to calculate the grayscale change of each pixel in the image, and mark the area where the grayscale change exceeds the threshold as a crack candidate area.

[0060] Use the region growing algorithm to determine the crack block in the image: Based on the extracted crack candidate region, the region growing algorithm is used to further segment the crack region. The core of the region growing algorithm is to start from the selected seed point and find pixels that meet the grayscale similarity condition to add to the crack region until all pixels do not meet the expansion condition. The selection of seed points is based on high grayscale gradient areas, and ensure that there is enough spacing between seed points to avoid overfitting of regions caused by excessive density.

[0061] The growth condition of the crack region is set according to the similarity of the pixel grayscale value, that is, the grayscale difference between the adjacent pixels and the boundary pixels of the current region needs to be less than the set threshold. The binary image matrix of the marked crack region is generated by the region growing algorithm. The crack region is assigned a marking value, and the background region is marked as zero.

[0062] Divide the surface of the metal pipe according to the crack density: After the crack area segmentation is completed, the surface of the metal pipe is further divided by counting the crack pixel density in each area. Define a sliding window of fixed size, slide it across the entire image, and count the number of crack pixels in the window. The crack density is defined as the ratio of crack pixels in the window to the total pixels.

[0063] By setting the demarcation threshold of crack density, the area with crack density higher than or equal to the demarcation threshold is divided into the area with high incidence of crack defects, and the area with crack density lower than the demarcation threshold is divided into the area with low incidence of crack defects.

[0064] Specifically, the changing trend of crack defect high-incidence areas in the time dimension is analyzed to evaluate the expansion risk of crack defects on the surface of metal pipes, including:

[0065] Capture images of crack areas at continuous time points: Use a high-resolution industrial camera to capture images of crack areas in metal pipes at multiple time points. Indicates that Indicates the acquisition time point. The image matrix of the metal pipe crack area acquired each time is expressed as , is the pixel coordinate, and the matrix value represents the grayscale value of the point. The image acquisition process maintains the same lighting conditions and camera parameter settings to ensure data consistency.

[0066] Quantitative comparison of crack boundaries in multi-temporal images: The crack boundaries in the image at each time point are extracted using a boundary detection algorithm, and the extracted boundary data is represented as a set , where each point The pixel coordinates representing the crack boundary.

[0067] In order to achieve the comparison in time dimension, the crack boundaries of two consecutive time points are superimposed and analyzed, the boundary change area is calculated, and the boundary change matrix is ​​defined as , the calculation formula is: ;in, is a sign function. If the change point is the extension area, then ; If the change point is a contraction area, then .

[0068] Through the boundary change matrix, the dynamic change of the crack boundary in the time dimension can be obtained.

[0069] Calculate the crack diffusion rate at different time intervals: After obtaining the crack boundary change data, it is necessary to quantify the crack diffusion rate. Define the crack diffusion area as , the calculation formula is: ;in, Indicates at a point in time The corresponding total crack propagation area; Respectively represent the number of pixels in the horizontal and vertical directions of the image matrix of the crack area of ​​the metal pipe; Indicates the actual physical area corresponding to the pixel; is the pixel coordinate; is the boundary change matrix.

[0070] By calculating the increment of the diffusion area, the crack diffusion rate can be obtained. , the calculation formula is: ,in, For at time point The crack diffusion rate reflects the crack expansion trend per unit time; For the time interval.

[0071] Crack propagation risk assessment based on rate change index: The risk of crack propagation depends not only on the current diffusion rate, but also on the rate change trend. By statistically analyzing the diffusion rates at multiple consecutive time points, a crack propagation trend curve is constructed to assess the crack propagation risk. The rate change index is expressed as: ;in, Indicates rate change index; is the number of time points; For at time point The crack propagation rate.

[0072] The larger the rate change index, the greater the risk of crack propagation on the surface of the metal pipe, the faster the crack propagation speed, and the crack area is in a rapid expansion process. A larger rate change index usually indicates that the crack may be developing outward at a faster rate, and the potential harm increases. A larger rate change index reflects the instability and unpredictability of crack propagation, which may be affected by external stress. The larger the rate change index, the shorter the time window for crack propagation, and the higher the failure risk of the metal pipe.

[0073] Specifically, the image texture feature analysis of the crack defect-prone areas is used to evaluate the significance of the crack defects on the metal pipe surface, including:

[0074] Extract texture feature vectors from crack defect prone areas: In the image matrix of crack defect prone areas, extract the texture features of the crack area to analyze the significance of the crack defect. Texture feature extraction is based on the gray level co-occurrence matrix to generate a set of feature vectors describing the texture characteristics. , where each Is a texture feature parameter, which is defined as follows:

[0075] Energy feature, used to describe the distribution uniformity of gray values ​​in texture images, is calculated as: ;in, Indicates energy characteristics; is the gray level index of the gray level co-occurrence matrix; is the gray level in the gray level co-occurrence matrix The joint probability value of is the total number of gray levels, defining the dimension of the gray-level co-occurrence matrix;

[0076] Contrast feature is used to indicate the significant degree of grayscale change in an image. The calculation formula is: ;in, Represents contrast characteristics;

[0077] Entropy feature is used to describe the complexity of image texture. The calculation formula is: ;in, Represents entropy characteristics.

[0078] Compare the texture parameter distribution differences between the texture features of the crack defect high-incidence area and the crack defect low-incidence area: After extracting the texture feature vector of the crack defect high-incidence area, compare its distribution difference with the texture feature of the crack defect low-incidence area. The texture feature vector of the crack defect low-incidence area is recorded as . The comparison is based on the Euclidean distance, and the calculation formula is: ;in, The Euclidean distance between the texture features of the crack defect high-incidence area and the crack defect low-incidence area is used to quantify the difference between the two. is the total number of texture feature dimensions in the crack defect high incidence area and the crack defect low incidence area; The first area where crack defects are most likely to occur Texture feature values; The first Texture feature values.

[0079] The larger the Euclidean distance is, the greater the difference in texture features between the crack defect high-incidence area and the crack defect low-incidence area is, that is, the crack texture in the crack defect high-incidence area is more significant; conversely, it means that the texture features of the crack defect high-incidence area and the crack defect low-incidence area are closer, that is, the more similar they are.

[0080] Quantifying texture saliency using statistical models: Based on the differences in texture feature distribution, the saliency of crack texture is quantified using statistical models. The saliency score is expressed as ;in, is the significance score; it represents the Euclidean distance between the texture features of the crack defect high incidence area and the crack defect low incidence area; The weight parameters to adjust the model sensitivity are determined by experiments; is the offset used to balance the significance score range; Represents the Euclidean distance between the texture features of the area with high crack defect incidence and the area with low crack defect incidence.

[0081] The larger the significance score, the more significant the crack defect on the surface of the metal pipe. A larger significance score usually means that the texture features of the crack area are more prominent in the overall image, the grayscale changes are more significant, and the structure of the crack is more complex or clear. This means that the crack is easier to identify visually and has more significant regional characteristics.

[0082] Specifically, based on the expansion risk of the metal pipe surface crack defect and the significance of the metal pipe surface crack defect, the severity level of the metal pipe surface crack defect is determined; the severity level includes a high severity level and a low severity level, including:

[0083] Preset the rate change index threshold and compare the rate change index with the rate change index threshold:

[0084] When the rate change index is greater than the rate change index threshold, it indicates that the crack propagation speed has reached or exceeded the set risk threshold, and the crack may be rapidly expanding, posing a greater threat to the safety of the metal pipe. The severity level of the crack defect on the surface of the metal pipe is high. At this time, early warning measures need to be taken immediately to strengthen real-time monitoring of the crack area and evaluate the impact of the crack on the overall performance of the pipe. At the same time, reinforcement repairs, material replacement or other intervention plans need to be implemented to reduce the risk of deterioration caused by crack expansion;

[0085] When the rate change index is less than or equal to the rate change index threshold, it means that the crack propagation speed is within an acceptable range, the crack propagation risk is low, and the severity level of the crack defect on the metal pipe surface is low. Regular inspections of the crack area can be carried out using conventional monitoring frequencies and detection methods.

[0086] The setting of the rate change index threshold requires comprehensive consideration of multiple factors such as the material of the pipe, bearing stress, and historical crack data. Usually, the threshold is determined based on experimental tests and historical experience values ​​to ensure that it can accurately reflect the actual impact of crack propagation on pipe performance. The threshold needs to be sensitive enough to detect early signs of crack propagation in a timely manner, and it also needs to have a certain tolerance to avoid false alarms due to minor fluctuations. In addition, different types of pipes or different usage scenarios may correspond to different rate change index thresholds, which need to be set according to the specific situation.

[0087] Preset significance score threshold and compare the significance score with the significance score threshold:

[0088] When the significance score is greater than the significance score threshold, the significance of the texture feature of the crack area has reached or exceeded the preset threshold, indicating that the regional features of the crack are more prominent in the overall image, and the severity level of the crack defect on the surface of the metal pipe is high. At this time, the crack may pose a greater safety threat and requires priority monitoring and treatment. It is necessary to increase the frequency of real-time detection and take further detailed detection and repair measures to prevent the crack from causing greater impact on the pipe;

[0089] When the significance score is less than or equal to the significance score threshold, the significance of the texture feature of the crack area does not meet the preset standard, indicating that the crack area is relatively inconspicuous, and the severity level of the crack defect on the metal pipe surface is low. At this time, the conventional monitoring strategy can be maintained without additional intervention, and periodic detection is maintained to ensure that the crack significance does not change rapidly.

[0090] The significance score threshold is set based on the application scenarios of metal pipes and statistical data of texture features, and is determined through experimental analysis and historical data verification. The threshold usually reflects the critical impact range of crack significance on pipe performance. It is a key benchmark set in combination with engineering safety standards, crack characteristic distribution laws, and detection accuracy requirements, and is used to guide the hierarchical management of crack defects and resource allocation strategies.

[0091] When the rate change index is greater than the rate change index threshold and the significance score is greater than the significance score threshold, the severity level of the metal pipe surface crack defect is a high severity level; otherwise, the severity level of the metal pipe surface crack defect is a low severity level.

[0092] Specifically, the working environment of metal pipes in areas with high incidence of crack defects is analyzed to evaluate the impact of crack defects on the structural integrity of metal pipes, including:

[0093] Collect working environment parameters in areas with high incidence of cracks: In areas with high incidence of crack defects, multi-dimensional parameters related to the working environment, including temperature, humidity, pressure, and chemical corrosion concentration, are collected through sensor networks and monitoring equipment.

[0094] Among them, temperature, in degrees Celsius, is obtained through a temperature sensor and reflects the thermal state of the environment in which the metal pipe is located; humidity, in percentage, is obtained through a humidity sensor and is used to evaluate the effect of water vapor on the surface of the pipe; pressure, in megapascals, is obtained through a pressure sensor and is used to reflect the load intensity of the pipe under working conditions; chemical corrosion concentration, in milligrams per liter, is obtained through a chemical analyzer and is used to evaluate the chemical corrosion effect of the environment on the material surface.

[0095] Analyze the influence of environmental parameters on the properties of metal materials: According to the material properties of metal pipes, analyze the influence of environmental parameters on material properties. The mechanical properties of metal materials are described by a set of parameters, including: yield strength, in megapascals, which indicates the maximum stress value of the material before deformation under stress; ductility, which indicates the plastic deformation ability of the material after stress; fatigue resistance, in megapascals, which indicates the damage resistance of the material under cyclic load.

[0096] The model that defines the influence of environmental parameters on the material properties of metal pipes is: ;in, For the environmental parameters The impact of changes in material properties; are the influence weight coefficients of environmental parameters, respectively, obtained by fitting the experimental data; Represent temperature, humidity, pressure and chemical corrosion concentration respectively.

[0097] Through the impact model, the weakening effect of environmental parameters on the material properties of metal pipes can be quantitatively evaluated.

[0098] Evaluate the dynamic impact of environmental factors on structural integrity: Based on the changes in material properties, define the structural integrity coefficient to evaluate the impact of the environment on the structural integrity of metal pipes. The calculation formula is: ;in, is the structural integrity coefficient; is the total number of material performance parameters; is the index of material performance parameters; Indicates The absolute change in a material property; Indicates The initial value of a material property.

[0099] The larger the structural integrity coefficient, the more serious the performance of the metal pipe is weakened by the working environment. A larger structural integrity coefficient indicates that environmental factors may significantly reduce the mechanical properties of the material and increase the risk of pipe failure. When the structural integrity coefficient increases, the metal pipe may lose its bearing capacity or structural stability more quickly, and immediate measures such as repair, replacement or enhanced monitoring are required. Through dynamic monitoring of the structural integrity coefficient, the long-term impact of the environment on the metal pipe structure can be more scientifically evaluated, providing a reliable basis for formulating precise risk management and maintenance strategies.

[0100] Specifically, by comprehensively analyzing the expansion risk of crack defects on the metal pipe surface, the significance of crack defects on the metal pipe surface, and the impact of crack defects on the structural integrity of the metal pipe, the detection sensitivity of the regional growing algorithm to the metal pipe surface is adjusted, including:

[0101] The rate change index corresponding to the expansion risk of crack defects on the metal pipe surface, the significance score corresponding to the significance of crack defects on the metal pipe surface, and the structural integrity coefficient corresponding to the degree of influence of crack defects on the structural integrity of the metal pipe are normalized, and the normalized rate change index, significance score and structural integrity coefficient are comprehensively analyzed to calculate the comprehensive risk coefficient. According to the comprehensive risk coefficient, the detection sensitivity of the regional growing algorithm to the metal pipe surface is adjusted.

[0102] The calculation formula of the comprehensive risk factor is: ;

[0103] in, represents the comprehensive risk factor; represent rate change index, significance score and structural integrity coefficient respectively.

[0104] Preset the comprehensive risk factor threshold and compare the comprehensive risk factor with the comprehensive risk factor threshold:

[0105] When the comprehensive risk factor is greater than or equal to the comprehensive risk factor threshold, the risk of crack defects on the surface of the metal pipe reaches or exceeds the warning level. At this time, the detection sensitivity of the regional growth algorithm should be improved, and more stringent parameter settings should be used to capture subtle crack boundaries and potential expansion areas to ensure full coverage of the metal pipe surface;

[0106] When the comprehensive risk factor is greater than or equal to the comprehensive risk factor threshold, the crack risk on the metal pipe surface is low and within a controllable range. At this time, the detection sensitivity of the regional growing algorithm is reduced, the computational burden of the algorithm operation is reduced, and resource utilization efficiency is optimized while meeting basic detection requirements.

[0107] The comprehensive risk threshold is to set a reasonable safety tolerance value by experimentally analyzing the correlation between different comprehensive risk factors and the possibility of pipe failure. At the same time, the engineering requirements and safety standards of specific application scenarios are considered to ensure that cracks can be identified and countermeasures can be taken in time before they threaten the performance and structural integrity of the pipe.

[0108] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0109] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or may be transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0110] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0111] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0112] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0113] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0114] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0115] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0116] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0117] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for visually detecting surface crack defects of metal pipes based on image processing, characterized in that: The steps include: Use a high-resolution industrial camera to obtain images of the metal pipe surface. Based on the crack distribution law of the metal pipe, use the regional growth algorithm to locate the crack area and divide the metal pipe surface area into a high-incidence crack defect area and a low-incidence crack defect area. Analyze the changing trend of crack defect high-incidence areas in the time dimension to assess the expansion risk of crack defects on the surface of metal pipes; Capture images of the crack area at consecutive time points; Quantitative comparison of crack boundaries in multi-temporal images; Calculate the crack propagation rate at different time intervals; Evaluation of crack propagation risk based on rate change index: The risk of crack propagation depends not only on the current diffusion rate, but also on the rate change trend. By statistically analyzing the diffusion rates at multiple consecutive time points, a crack diffusion trend curve is constructed to evaluate the crack propagation risk. The rate change index is expressed as: Where RC represents the rate change index; n is the number of time points; R i At time point t i Crack propagation rate; Analyze the image texture features of the crack defect-prone areas to evaluate the significance of the crack defects on the surface of the metal pipe; Based on the expansion risk of the crack defect on the metal pipe surface and the significance of the crack defect on the metal pipe surface, the severity level of the crack defect on the metal pipe surface is determined; the severity level includes a high severity level and a low severity level; Analyze the working environment of metal pipes in areas with high incidence of crack defects and evaluate the impact of crack defects on the structural integrity of metal pipes; By comprehensively analyzing the expansion risk of crack defects on the metal pipe surface, the significance of crack defects on the metal pipe surface, and the impact of crack defects on the structural integrity of the metal pipe, the detection sensitivity of the region growing algorithm to the metal pipe surface is adjusted.

2. According to claim 1, a method for visual detection of surface crack defects of metal pipes based on image processing is characterized in that: A high-resolution industrial camera is used to obtain images of the metal pipe surface. Based on the crack distribution law of the metal pipe, a regional growth algorithm is used to locate the crack area, and the surface area of ​​the metal pipe is divided into a high-incidence area of ​​crack defects and a low-incidence area of ​​crack defects. Specifically: Capture original image data of the pipe surface through high-resolution industrial cameras; Extract crack candidate areas based on pipe crack distribution characteristics; The region growing algorithm is used to determine the crack area in the image: the core of the region growing algorithm is to start from the selected seed point and find pixels that meet the grayscale similarity condition to add to the crack area until all pixels do not meet the expansion condition; the seed point is selected based on the high grayscale gradient area; Divide the surface of the metal pipe according to the crack density: define a sliding window of fixed size, slide it across the entire image, and count the number of crack pixels in the window; The crack density is defined as the ratio of crack pixels to total pixels within the window; By setting the demarcation threshold of crack density, the area with crack density higher than or equal to the demarcation threshold is divided into the area with high incidence of crack defects, and the area with crack density lower than the demarcation threshold is divided into the area with low incidence of crack defects.

3. The method for visually detecting surface crack defects of metal pipes based on image processing according to claim 2 is characterized in that: The image texture feature analysis of the crack defect prone area evaluates the significance of the crack defect on the metal pipe surface, specifically: Extracting texture feature vectors from areas with high incidence of crack defects; Compare the differences in texture parameter distribution between the texture features of areas with high crack defect incidence and areas with low crack defect incidence; Quantify texture saliency using statistical models: Based on the differences in texture feature distribution, the saliency of crack texture is quantified using statistical models; the saliency score is expressed as Among them, SFS is the significance score; it represents the Euclidean distance between the texture features of the crack defect high incidence area and the crack defect low incidence area; is the weight parameter for adjusting the sensitivity of the model; γ is the offset used to balance the significance score range; d represents the Euclidean distance between the texture features of the crack defect high incidence area and the crack defect low incidence area.

4. The method for visually detecting surface crack defects of metal pipes based on image processing according to claim 3 is characterized in that: Based on the expansion risk of the crack defect on the metal pipe surface and the significance of the crack defect on the metal pipe surface, the severity level of the crack defect on the metal pipe surface is determined; the severity level includes a high severity level and a low severity level, specifically: Preset the rate change index threshold and compare the rate change index with the rate change index threshold: When the rate change index is greater than the rate change index threshold, the severity level of the metal pipe surface crack defect is high severity level; When the rate change index is less than or equal to the rate change index threshold, the severity level of the metal pipe surface crack defect is low severity level; Preset significance score threshold and compare the significance score with the significance score threshold: When the significance score is greater than the significance score threshold, the severity level of the metal pipe surface crack defect is a high severity level; When the significance score is less than or equal to the significance score threshold, the severity level of the metal pipe surface crack defect is low severity level; When the rate change index is greater than the rate change index threshold and the significance score is greater than the significance score threshold, the severity level of the metal pipe surface crack defect is a high severity level; otherwise, the severity level of the metal pipe surface crack defect is a low severity level.

5. The method for visually detecting surface crack defects of metal pipes based on image processing according to claim 4 is characterized in that: The working environment of metal pipes in areas with high incidence of crack defects is analyzed to evaluate the impact of crack defects on the structural integrity of metal pipes, specifically: Collect working environment parameters in areas with high crack incidence; Analyze the influence of environmental parameters on the properties of metal materials and define the influence model of environmental parameters on the performance of metal pipe materials; Evaluate the dynamic impact of environmental factors on structural integrity: Define the structural integrity coefficient to evaluate the impact of the environment on the structural integrity of metal pipes. The calculation formula is: Where SIF is the structural integrity factor; T is the total number of material performance parameters; g is the index of the material performance parameter; |ΔZ g | represents the absolute change value of the g-th material property; ΔZ g Represents the initial value of the g-th material property.

6. The method for visually detecting surface crack defects of metal pipes based on image processing according to claim 5 is characterized in that: By comprehensively analyzing the expansion risk of crack defects on the metal pipe surface, the significance of crack defects on the metal pipe surface, and the impact of crack defects on the structural integrity of the metal pipe, the detection sensitivity of the regional growing algorithm to the metal pipe surface is adjusted, specifically: The rate change index corresponding to the expansion risk of crack defects on the metal pipe surface, the significance score corresponding to the significance of crack defects on the metal pipe surface, and the structural integrity coefficient corresponding to the degree of influence of crack defects on the structural integrity of the metal pipe are normalized, and the normalized rate change index, significance score and structural integrity coefficient are comprehensively analyzed to calculate the comprehensive risk coefficient. The calculation formula is: Among them, CRF represents the comprehensive risk factor; RC, SFS, and SIF represent the rate change index, significance score, and structural integrity coefficient, respectively; Preset the comprehensive risk factor threshold and compare the comprehensive risk factor with the comprehensive risk factor threshold: When the comprehensive risk factor is greater than or equal to the comprehensive risk factor threshold, the detection sensitivity of the region growing algorithm should be improved; When the comprehensive risk coefficient is less than the comprehensive risk coefficient threshold, the detection sensitivity of the region growing algorithm is reduced.

Images