Fabricated bridge structure damage identification method and system

Abstract

The invention provides an assembly type bridge structure damage identification method and system, and relates to the technical field of bridge structures, and the method specifically comprises the steps: firstly obtaining an image of an inter-beam connection point of an assembly segment, zooming the image to 224 * 224 pixels, and carrying out the graying processing; calculating an image gradient by using a Sobel operator, carrying out threshold edge detection, and extracting contour lines of connection points; preliminarily identifying the shape of the contour according to the circularity, the length-width ratio and the vertex number of the contour, fitting a circle by using a least square method, and calculating the circularity and dispersion of the contour; and finally, performing data processing and correlation analysis on the parameter change of the circular contour, generating a comprehensive damage index, and judging the damage type and degree of the connection point. The method can effectively identify and quantify the damage of the inter-beam connection point of the fabricated bridge segment in real time, and has high efficiency and accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of bridge structure detection, and in particular to a method and system for identifying damage of an assembled bridge structure. Background Art

[0002] Due to the increasing traffic volume and environmental factors, many bridges with a long service life, such as bridges that have been used for more than 20 years, will have concrete cracks, spalling and other defects, especially the connection points of prefabricated bridge structures are prone to structural damage. Even though the mainstream bridge inspection can comprehensively identify the defects of various parts of the bridge structure and implement corresponding maintenance and reinforcement measures, the inspection frequency is low, the efficiency and economy are poor, and the identification of the overall status of the bridge structure is relatively delayed.

[0003] In the prior art, a bridge damage identification method with publication number CN117291072A includes the following steps: S1, establishing an initial finite element model of a target bridge to perform vehicle-bridge coupling analysis to obtain a simulated deflection response, optimizing the initial finite element model in combination with the measured deflection response to obtain a modified finite element model; S2, collecting traffic flow vehicle load data of the target bridge within a certain period of time, determining the physical parameter information of each vehicle type through mathematical and statistical analysis and establishing a standard vehicle physical model, performing random sampling using a sampling method, and generating a random traffic sample sequence; S3, designing different damage conditions of the target bridge, performing vehicle-bridge coupling analysis under random traffic according to different damage conditions and the modified finite element model, and obtaining bridge simulated deflection response data; S4, constructing a training data set with different damage conditions and corresponding bridge simulated deflection response data to establish a damage identification model to identify damage to the target bridge. This method can realize real-time online bridge damage location and quantification.

[0004] However, there are still some shortcomings: As can be seen from the above statements, the existing technology mainly relies on deflection response data for damage identification, which requires a large amount of measured data, and there is great uncertainty and complexity in the collection and analysis of vehicle load data; in addition, this method has certain limitations in real-time and accuracy, and it is difficult to quickly and accurately locate and quantify the damage of bridge structures. Especially for prefabricated bridge structures, due to the large number of connection points and complex nodes, traditional damage identification methods are difficult to efficiently and accurately identify the damage at the connection points, and cannot meet the needs of fast and real-time bridge health monitoring.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The purpose of the present invention is to provide a method and system for identifying damage of a prefabricated bridge structure to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions: A method for identifying damage to an assembled bridge structure, comprising the following specific steps: S1. Obtain an image of the connection point between the segment beams of the assembly segment, scale the image of the connection point of the assembly segment, adjust the image size to a uniform size of 224*224, grayscale the image of the connection point of the assembly segment, and obtain a recognition image; S2. Use the Sobel operator to calculate the gradient of the recognition image in the horizontal and vertical directions to obtain the gradient amplitude, perform threshold edge detection on the gradient amplitude, obtain edge pixels and non-edge pixels, connect all edge pixels to form an edge image, detect the edge image and extract all contour lines, analyze all extracted contour lines, and filter out the contours of the connection points; S3. Calculate the circularity, aspect ratio and number of vertices of the contour according to the contour of the connection points, and preliminarily identify the shape of the contour according to the numerical range of the circularity, aspect ratio and number of vertices of the contour; S4. Fitting a circle to the contour using the least square method, obtaining the center point and radius of the contour, and obtaining the area of ​​the fitted contour and the area of ​​the fitted circle based on the radius of the contour, obtaining the roundness of the contour based on the area of ​​the fitted contour and the area of ​​the fitted circle, calculating the deviation between the contour point and the fitted circle, obtaining the average deviation and the standard deviation based on the deviation between the contour point and the fitted circle, obtaining the discreteness of the contour based on the average deviation and the standard deviation, and determining that the shape of the contour is a circle when the roundness and discreteness of the contour fall within the numerical range of the roundness and discreteness of the circle; S5. Process the radius of the circular contour, the area of ​​the fitted circle, the average deviation, the standard deviation and the initial radius, the initial area of ​​the fitted circle, the initial average deviation and the initial standard deviation to generate the radius change, the fitted circle area change, the average deviation change and the standard deviation change; process the radius change, the fitted circle area change, the average deviation change and the standard deviation change and perform correlation analysis to generate a comprehensive damage index; judge the damage type of the connection point of the assembly segment beam according to the radius change, area change, average deviation change and standard deviation change; judge the degree of damage of the connection point between the assembly segment beams according to the interval range of the comprehensive damage index.

[0008] Furthermore, the image of the connection point of the assembly segment is grayed out to obtain the recognition image as follows: The image of the connection point is grayed to obtain the recognition image, based on the following formula: ; in, is the gray value of the pixel in the recognition image, , , They are respectively the pixel red component value, green component value and blue component value of the image connecting the points after image scaling.

[0009] Furthermore, the Sobel operator is used to calculate the gradient of the recognition image in the horizontal and vertical directions, and the process of obtaining the gradient amplitude is as follows: The grayscale value of the pixel and its adjacent pixel points are multiplied with the horizontal gradient template of the Sobel operator, and all the product results are added to obtain the horizontal gradient value of the pixel. The grayscale value of the pixel and its adjacent pixel points are multiplied with the vertical gradient template of the Sobel operator, and all the product results are added to obtain the vertical gradient value of the pixel. The formula for calculating the horizontal gradient value and the vertical gradient value is: ; ; in, , Respectively Row, No. The horizontal and vertical gradient values ​​of the column pixels. For the Row, No. Gray value of the column pixel; The formula for generating the gradient amplitude of a pixel is: ; in, For the Row, No. The gradient magnitude of the pixel column.

[0010] Furthermore, the process of performing threshold edge detection on the gradient amplitude and obtaining edge pixels and non-edge pixels is as follows: Setting the Threshold , classify the pixels in the gradient magnitude map into edge pixels and non-edge pixels; when , then mark the pixel as an edge pixel; when , then mark the pixel as a non-edge pixel.

[0011] Furthermore, the process of detecting the edge image and extracting all contour lines, analyzing all extracted contour lines, and screening out the contours of the connection points is as follows: Use the contour detection algorithm to extract all contour lines from the edge image. Contour detection is regarded as a process of marking connected areas. The contours are initially screened according to their area. The area of ​​the contour is obtained by calculating the number of pixels it contains. The area formula is as follows: ; in, Represents a contour, Representing contours A pixel in Represents the area of ​​the contour. “1” actually means that for all the contours Count the pixels and set an area threshold , filter out contours whose area is larger than the threshold: ; in, is the first contour set after screening, including all contours whose areas are larger than the threshold; The shape features of the contours, i.e., aspect ratio and circularity, are analyzed to determine whether they contain the connection point. The circumscribed rectangle of the contour is used to calculate the aspect ratio. The aspect ratio formula of the circumscribed rectangle is as follows: ; in, For outline The aspect ratio, and Respectively represent contours The width and height of the bounding rectangle of the , setting the minimum aspect ratio and maximum value , filter out the contours that meet the conditions: ; in, is the second contour set after screening, including all contours whose aspect ratios are within the set range; For each contour, check its distance to other contours, if the minimum distance between two contour points is less than the threshold , they are considered to contain a connection point; Minimum distance between contours The formula is: ; in, , are two different contours in the second contour set, Representing contours A pixel in Representing contours A pixel in To point to the outline The index of a specific pixel in To point to the outline The index of a specific pixel in ; Filter out contour pairs that meet the conditions: ; in, is a set of contour pairs containing connection points, is the minimum distance threshold.

[0012] Furthermore, according to the contour of the connection point, the circularity, aspect ratio and number of vertices of the contour are calculated, and according to the numerical range of the circularity, aspect ratio and number of vertices of the contour, the shape of the contour is preliminarily identified. The specific steps are as follows: The formula for circularity is as follows: ; in, , , are the contours in the contour pair set Circularity, area, and perimeter; ; in, For outline The number of vertices, Represents the contour Perform polygon approximation and return the number of vertices of the approximated polygon. is the error parameter, which indicates the accuracy of the approximation. The smaller the value, the higher the accuracy of the approximation and the more vertices there are. The larger the value, the lower the accuracy of the approximation and the fewer vertices there are. when , , then the shape of the contour is a circle; when , , then the shape of the contour is a square; when , , , then the shape of the contour is a rectangle; when , or , , the shape of the contour is a triangle.

[0013] Furthermore, the least square method is used to fit the circle to the contour, the center point and radius of the contour are obtained, and the contour area and the fitted circle area are obtained according to the radius of the contour. The process of obtaining the roundness of the contour according to the contour area and the fitted circle area is as follows: The goal of least squares circle fitting is to find a circle that minimizes the sum of squared distances from all contour points. The equation of the circle is: ; Among them, (a, b) is the coordinate of the center of the circle, and r is the radius; Convert the equation of the circle into linear form so that we can use the least squares method: ; set up , then: ; make , , , then the equation becomes: ; For each contour point , then:

[0014] ; in, is the index of the contour point; Express the equations for all points in matrix form: ; in, is the number of contour points; Denoted as: ; in: , , ; The least squares solution is obtained by solving the following equation: ; ; in, is transposed; get Then, calculate the center and radius: , , ; The area of ​​the fitted contour Calculated by the polygon area formula of the contour points: ; Area of ​​the fitted circle Calculated based on the radius: ; The roundness of the contour is an indicator of how close it is to the fitted circle shape. The formula is as follows: .

[0015] Furthermore, the deviation between the contour point and the fitting circle is calculated to obtain the average deviation and standard deviation. Based on the average deviation and standard deviation, the process of obtaining the discreteness of the contour is as follows: The equation of the known fitting circle is: ; For each contour point , calculate its distance to the center of the circle The Euclidean distance : ; Calculate the distance and radius of each contour point to the fitted circle The deviation between : ; Calculate the average of all deviations to get the mean deviation : ; Calculate the standard deviation of all deviations : ; Calculate the dispersion of the contour : ; in, is the weight factor; When the roundness and discreteness of the contour fall within the numerical range of the roundness and discreteness of the circle, the specific process of determining that the shape of the contour is a circle is as follows: When the roundness of the contour is , Discreteness , the contour is considered to be circular.

[0016] Furthermore, the radius, area, average deviation, standard deviation of the circular contour and the initial radius, initial fitting circle area, initial average deviation, and initial standard deviation are processed to generate radius change, fitting circle area change, average deviation change, and standard deviation change. The radius change, fitting circle area change, average deviation change, and standard deviation change are processed and correlated to generate a comprehensive damage index, based on the following formula: Radius change : ; Fitted circle area change : ; Mean deviation change : ; Standard Deviation Change : ; , , , They are initial radius, initial fitting circle area, initial mean deviation, and initial standard deviation; ; in, is the comprehensive injury index, is the weight coefficient of radius change, is the weight coefficient of area change, is the weight coefficient of the average deviation change, is the weight coefficient of the standard deviation change, , ; According to the change in radius, the change in the area of ​​the fitted circle, the change in the average deviation and the change in the standard deviation, the damage type of the assembly segment connection point is determined, and according to the range of the comprehensive damage index, the damage degree of the assembly segment connection point is determined. The specific process is as follows: When the radius changes If it is not 0, it means that the connection point of the assembly segment has undergone overall deformation due to stress or fatigue; When the fitted circle area changes If it is not 0, it means that the connection point of the assembly segment has undergone overall deformation due to material expansion, contraction or local fracture; When the mean deviation changes If it is not 0, it means that the assembly segment connection point has a manufacturing defect or an assembly error that causes overall deformation; When the standard deviation changes If it is not 0, it means that the connection point of the assembly segment has an overall deformation caused by material inhomogeneity or local damage; According to the comprehensive injury index , define the damage degree interval: when , it means that there is slight damage at the connection point of the assembly section; when , it means that the connection point of the assembly segment has moderate damage; when , it means that the connection point of the assembly section is seriously damaged.

[0017] A prefabricated bridge structure damage identification system, the system is used to execute any of the prefabricated bridge structure damage identification methods described above, comprising: An image processing module is used to obtain images of the connection points of the assembly segments, scale the images of the connection points of the assembly segments, adjust the image size to a uniform size of 224*224, perform grayscale processing on the images of the connection points of the assembly segments, and obtain a recognition image; The contour extraction module is used to calculate the gradient of the recognition image in the horizontal and vertical directions using the Sobel operator to obtain the gradient amplitude, perform threshold edge detection on the gradient amplitude, obtain edge pixels and non-edge pixels, connect all edge pixels to form an edge image, detect the edge image and extract all contour lines, analyze all extracted contour lines, and filter out the contours of the connection points; A recognition module is used to calculate the circularity, aspect ratio and number of vertices of the contour according to the contour of the connection points, and preliminarily recognize the shape of the contour according to the numerical range of the circularity, aspect ratio and number of vertices of the contour; A data processing module is used to fit a circle to the contour using the least square method, obtain the center point and radius of the contour, and obtain the area of ​​the fitted contour and the area of ​​the fitted circle according to the radius of the contour, obtain the roundness of the contour according to the area of ​​the fitted contour and the area of ​​the fitted circle, calculate the deviation between the contour point and the fitted circle, obtain the average deviation and the standard deviation according to the deviation between the contour point and the fitted circle, obtain the discreteness of the contour according to the average deviation and the standard deviation, and determine that the shape of the contour is a circle when the roundness and discreteness of the contour fall within the numerical range of the roundness and discreteness of the circle; The judgment module is used to process the radius, fitted circle area, average deviation, standard deviation of the circular contour and the initial radius, initial fitted circle area, initial average deviation, and initial standard deviation to generate radius change, fitted circle area change, average deviation change, and standard deviation change; perform data processing and correlation analysis on the radius change, fitted circle area change, average deviation change, and standard deviation change to generate a comprehensive damage index; judge the damage type of the assembly segment connection point according to the radius change, area change, average deviation change, and standard deviation change; and judge the degree of damage of the assembly segment connection point according to the interval range of the comprehensive damage index.

[0018] Compared with the prior art, the present invention has the following beneficial effects: The present invention processes and analyzes the image of the connection point, utilizes steps such as image scaling, graying, edge detection and contour extraction, accurately identifies the shape of the connection point, and then accurately determines the damage type and degree of the connection point by calculating the change in parameters such as circularity, discreteness, radius and area, and generates a comprehensive damage index to achieve real-time online monitoring of damage to prefabricated bridge structures. The present invention can solve the problems of relying on a large amount of measured data, poor real-time performance and difficulty in accurately identifying damage to assembly section connection points in the prior art, significantly improve the real-time performance and accuracy of damage identification, and can effectively identify and quantify damage to connection points of prefabricated bridge structures. The present invention is particularly suitable for rapid detection and analysis of complex nodes, and improves the efficiency and accuracy of bridge health monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a schematic diagram of the overall method flow of the present invention; Figure 2 This is a block diagram of the module composition of the present invention. DETAILED DESCRIPTION

[0020] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0021] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0022] Example: See also Figure 1 , the present invention provides a technical solution: A method for identifying damage to an assembled bridge structure, comprising the following specific steps: S1. Obtain an image of the connection point of the assembly segment, scale the image of the connection point of the assembly segment, adjust the image size to 224*224, grayscale the image of the connection point of the assembly segment, and obtain a recognition image; S2. Use the Sobel operator to calculate the gradient of the recognition image in the horizontal and vertical directions to obtain the gradient amplitude, perform threshold edge detection on the gradient amplitude, obtain edge pixels and non-edge pixels, connect all edge pixels to form an edge image, detect the edge image and extract all contour lines, analyze all extracted contour lines, and filter out the contours of the connection points; S3. Calculate the circularity, aspect ratio and number of vertices of the contour according to the contour of the connection points, and preliminarily identify the shape of the contour according to the numerical range of the circularity, aspect ratio and number of vertices of the contour; S4. Fitting a circle to the contour using the least square method, obtaining the center point and radius of the contour, and obtaining the area of ​​the fitted contour and the area of ​​the fitted circle based on the radius of the contour, obtaining the roundness of the contour based on the area of ​​the fitted contour and the area of ​​the fitted circle, calculating the deviation between the contour point and the fitted circle, obtaining the average deviation and the standard deviation based on the deviation between the contour point and the fitted circle, obtaining the discreteness of the contour based on the average deviation and the standard deviation, and determining that the shape of the contour is a circle when the roundness and discreteness of the contour fall within the numerical range of the roundness and discreteness of the circle; S5. Process the radius, fitted circle area, average deviation, standard deviation of the circular contour and the initial radius, initial fitted circle area, initial average deviation and initial standard deviation to generate radius change, fitted circle area change, average deviation change and standard deviation change; process the radius change, fitted circle area change, average deviation change and standard deviation change and perform correlation analysis to generate a comprehensive damage index; judge the damage type of the assembly segment connection point based on the radius change, area change, average deviation change and standard deviation change; judge the degree of damage of the assembly segment connection point based on the interval range of the comprehensive damage index.

[0023] On the basis of the above embodiment, the image of the connection point of the assembly segment is grayed to obtain the recognition image in the following process: The image of the connection point is grayed to obtain the recognition image, based on the following formula: ; in, is the gray value of the pixel in the recognition image, , , They are respectively the pixel red component value, green component value and blue component value of the image connecting the points after image scaling.

[0024] On the basis of the above embodiment, the Sobel operator is used to calculate the gradient of the recognition image in the horizontal and vertical directions, and the process of obtaining the gradient amplitude is as follows: The grayscale value of the pixel and its adjacent pixel points are multiplied with the horizontal gradient template of the Sobel operator, and all the product results are added to obtain the horizontal gradient value of the pixel. The grayscale value of the pixel and its adjacent pixel points are multiplied with the vertical gradient template of the Sobel operator, and all the product results are added to obtain the vertical gradient value of the pixel. The formula for calculating the horizontal gradient value and the vertical gradient value is: ; ; in, , Respectively Row, No. The horizontal and vertical gradient values ​​of the column pixels. For the Row, No. Gray value of the column pixel; The formula for generating the gradient amplitude of a pixel is: ; in, For the Row, No. The gradient magnitude of the pixel column.

[0025] On the basis of the above embodiment, the process of performing threshold edge detection on the gradient amplitude and obtaining edge pixels and non-edge pixels is as follows: Setting the Threshold , classify the pixels in the gradient magnitude map into edge pixels and non-edge pixels; when , then mark the pixel as an edge pixel; when , then mark the pixel as a non-edge pixel.

[0026] On the basis of the above embodiment, the process of detecting the edge image and extracting all contour lines, analyzing all extracted contour lines, and screening out the contours of the connection points is as follows: Use the contour detection algorithm to extract all contour lines from the edge image. Contour detection can be regarded as a process of marking connected areas. The contours are initially screened according to their area. The area of ​​the contour is obtained by calculating the number of pixels it contains. The area formula is as follows: ; in, Represents a contour, Representing contours A pixel in Represents the area of ​​the contour. “1” actually means that for all the contours Count the pixels and set an area threshold , filter out contours whose area is larger than the threshold: ; in, is the first contour set after screening, including all contours whose areas are larger than the threshold; The shape features of the contours, i.e., aspect ratio and circularity, are analyzed to determine whether they contain the connection point. The circumscribed rectangle of the contour is used to calculate the aspect ratio. The aspect ratio formula of the circumscribed rectangle is as follows: ; in, For outline The aspect ratio, and Respectively represent contours The width and height of the bounding rectangle of the , setting the minimum aspect ratio and maximum value , filter out the contours that meet the conditions: ; in, is the second contour set after screening, including all contours whose aspect ratios are within the set range; For each contour, check its distance to other contours, if the minimum distance between two contour points is less than the threshold , they are considered to contain a connection point; Minimum distance between contours The formula is: ; in, , are two different contours in the second contour set, Representing contours A pixel in Representing contours A pixel in To point to the outline The index of a specific pixel in To point to the outline The index of a specific pixel in ; Filter out contour pairs that meet the conditions: ; in, is a set of contour pairs containing connection points, is the minimum distance threshold.

[0027] On the basis of the above embodiment, according to the contour of the connection points, the circularity, aspect ratio and number of vertices of the contour are calculated, and according to the numerical range of the circularity, aspect ratio and number of vertices of the contour, the shape of the contour is preliminarily identified. The specific steps are as follows: The formula for circularity is as follows: ; in, , , are the contours in the contour pair set Circularity, area, and perimeter; ; in, For outline The number of vertices, Represents the contour Perform polygon approximation and return the number of vertices of the approximated polygon. is the error parameter, which indicates the accuracy of the approximation. The smaller the value, the higher the accuracy of the approximation and the more vertices there are. The larger the value, the lower the accuracy of the approximation and the fewer vertices there are. when , , then the shape of the contour is a circle; when , , then the shape of the contour is a square; when , , , then the shape of the contour is a rectangle; when , or , , the shape of the contour is a triangle.

[0028] On the basis of the above embodiment, the least square method is used to fit a circle to the contour, the center point and radius of the contour are obtained, and the contour area and the fitted circle area are obtained according to the radius of the contour. The process of obtaining the roundness of the contour according to the contour area and the fitted circle area is as follows: The goal of least squares circle fitting is to find a circle that minimizes the sum of squared distances from all contour points. The equation of the circle is: ; Among them, (a, b) is the coordinate of the center of the circle, and r is the radius; Convert the equation of the circle into linear form so that we can use the least squares method: ; set up , then: ; make , , , then the equation becomes: ; For each contour point , then:

[0029] ; in, is the index of the contour point; the equations of all points are expressed in matrix form: ; Denoted as: ; in: , , ; in, is the number of contour points; the least squares solution is obtained by solving the following equation: ; ; in, is transposed; get Then, calculate the center and radius: , , ; The area of ​​the fitted contour Calculated by the polygon area formula of the contour points: ; Area of ​​the fitted circle Calculated based on the radius: ; The roundness of the contour is an indicator of how close it is to the fitted circle shape. The formula is as follows: .

[0030] On the basis of the above embodiment, the deviation between the contour point and the fitting circle is calculated, and the average deviation and the standard deviation are obtained. According to the average deviation and the standard deviation, the process of obtaining the discreteness of the contour is as follows: The equation of the known fitting circle is: ; For each contour point , calculate its distance to the center of the circle The Euclidean distance : ; Calculate the distance and radius of each contour point to the fitted circle The deviation between : ; Calculate the average of all deviations : ; Calculate the standard deviation of all deviations : ; Calculate the dispersion of the contour : ; in, is the weight factor; When the roundness of the contour is , Discreteness , the contour is considered to be circular.

[0031] On the basis of the above embodiment, the radius, fitted circle area, average deviation, standard deviation and initial radius, initial fitted circle area, initial average deviation and initial standard deviation of the circular contour are processed to generate radius change, fitted circle area change, average deviation change and standard deviation change. The radius change, fitted circle area change, average deviation change and standard deviation change are processed and correlated to generate a comprehensive damage index, and the formula is as follows: Radius change : ; Fitted circle area change : ; Mean deviation change : ; Standard Deviation Change : ; , , , They are initial radius, initial fitting circle area, initial mean deviation, and initial standard deviation; ; in, is the comprehensive injury index, is the weight coefficient of radius change, is the weight coefficient of area change, is the weight coefficient of the average deviation change, is the weight coefficient of the standard deviation change.

[0032] Generally, the change in radius directly affects the size and proportion of the entire geometric shape. The radius change is an important parameter when evaluating the overall change of a geometric shape or contour. The area change reflects the overall size change of the shape. The change in area has a significant impact on material properties or structural stability. The area change is often given a higher weight. Although the mean deviation change is an important quality indicator, in some cases it is not as important as the overall size change. The standard deviation change measures the degree of discreteness of the data. In geometric and shape analysis, the change in standard deviation is not as critical as other parameters. Therefore, set , in the case of only the above parameters, set .

[0033] On the basis of the above embodiment, the damage type of the assembly segment connection point is determined according to the radius change, the fitted circle area change, the average deviation change and the standard deviation change, and the damage degree of the assembly segment connection point is determined according to the interval range of the comprehensive damage index. The specific process is as follows: When the radius changes If it is not 0, it means that the connection point of the assembly segment has an overall deformation caused by excessive stress or fatigue; When the fitted circle area changes If it is not 0, it means that the connection point of the assembly segment has undergone overall deformation due to material expansion, contraction or local fracture; When the mean deviation changes If it is not 0, it means that the assembly segment connection point has a manufacturing defect or an assembly error that causes overall deformation; When the standard deviation changes If it is not 0, it means that the connection point of the assembly segment has an overall deformation caused by material inhomogeneity or local damage; According to the comprehensive injury index , define the damage degree interval: when , it means that there is slight damage at the connection point of the assembly section; when , it means that the connection point of the assembly segment has moderate damage; when , it means that the connection point of the assembly section is seriously damaged.

[0034] In the formula , , , and The specific value of is generally determined by those skilled in the art according to actual conditions. The essence of this formula is a comprehensive analysis by weighted summation. The technicians in this field collect multiple groups of sample data, and set corresponding weight factors or weight coefficients for each group of sample data. The set weight factors or weight coefficients and the collected sample data are substituted into the formula. Through repeated experiments and parameter adjustments, the accuracy of the model output and the rationality of the results are observed, and these weight factors or weight coefficients are gradually adjusted. The performance and effect of the model under different parameter settings are compared to find the optimal coefficient combination. The calculated proportional factors or weight coefficients are screened and averaged to obtain , , , and The value of .

[0035] In addition, the size of the weight factor or weight coefficient is a specific numerical value obtained by quantifying each parameter. In order to facilitate subsequent comparison, the size of the weight factor or weight coefficient depends on the amount of sample data and the technical personnel in this field initially setting the corresponding weight factor or weight coefficient for each set of sample data. It is not unique, as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0036] See also Figure 2 , the present invention provides a technical solution: A prefabricated bridge structure damage identification system, the system is used to execute any of the prefabricated bridge structure damage identification methods described above, comprising: A prefabricated bridge structure damage identification system, the system is used to execute any of the prefabricated bridge structure damage identification methods described above, comprising: An image processing module is used to obtain images of the connection points of the assembly segments, scale the images of the connection points of the assembly segments, adjust the image size to a uniform size of 224*224, perform grayscale processing on the images of the connection points of the assembly segments, and obtain a recognition image; The contour extraction module is used to calculate the gradient of the recognition image in the horizontal and vertical directions using the Sobel operator to obtain the gradient amplitude, perform threshold edge detection on the gradient amplitude, obtain edge pixels and non-edge pixels, connect all edge pixels to form an edge image, detect the edge image and extract all contour lines, analyze all extracted contour lines, and filter out the contours of the connection points; A recognition module is used to calculate the circularity, aspect ratio and number of vertices of the contour according to the contour of the connection points, and preliminarily recognize the shape of the contour according to the numerical range of the circularity, aspect ratio and number of vertices of the contour; A data processing module is used to fit a circle to the contour using the least square method, obtain the center point and radius of the contour, and obtain the area of ​​the fitted contour and the area of ​​the fitted circle according to the radius of the contour, obtain the roundness of the contour according to the area of ​​the fitted contour and the area of ​​the fitted circle, calculate the deviation between the contour point and the fitted circle, obtain the average deviation and the standard deviation according to the deviation between the contour point and the fitted circle, obtain the discreteness of the contour according to the average deviation and the standard deviation, and determine that the shape of the contour is a circle when the roundness and discreteness of the contour fall within the numerical range of the roundness and discreteness of the circle; The judgment module is used to process the radius, fitted circle area, average deviation, standard deviation of the circular contour and the initial radius, initial fitted circle area, initial average deviation, and initial standard deviation to generate radius change, fitted circle area change, average deviation change, and standard deviation change; perform data processing and correlation analysis on the radius change, fitted circle area change, average deviation change, and standard deviation change to generate a comprehensive damage index; judge the damage type of the assembly segment connection point according to the radius change, area change, average deviation change, and standard deviation change; and judge the degree of damage of the assembly segment connection point according to the interval range of the comprehensive damage index.

[0037] 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 in the formula are set by technicians in this field according to actual conditions.

[0038] 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. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0039] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0040] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the 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.

Claims

1. A method for identifying damage to an assembled bridge structure, characterized in that: The specific steps include: S1. Obtain an image of the connection point between the segment beams of the assembly segment, scale the image of the connection point of the assembly segment, adjust the image size to a uniform size of 224*224, grayscale the image of the connection point of the assembly segment, and obtain a recognition image; S2. Use the Sobel operator to calculate the gradient of the recognition image in the horizontal and vertical directions to obtain the gradient amplitude, perform threshold edge detection on the gradient amplitude, obtain edge pixels and non-edge pixels, connect all edge pixels to form an edge image, detect the edge image and extract all contour lines, analyze all extracted contour lines, and filter out the contours of the connection points; S3. Calculate the circularity, aspect ratio and number of vertices of the contour according to the contour of the connection points, and preliminarily identify the shape of the contour according to the numerical range of the circularity, aspect ratio and number of vertices of the contour; S4. Fitting a circle to the contour using the least square method, obtaining the center point and radius of the contour, and obtaining the area of ​​the fitted contour and the area of ​​the fitted circle based on the radius of the contour, obtaining the roundness of the contour based on the area of ​​the fitted contour and the area of ​​the fitted circle, calculating the deviation between the contour point and the fitted circle, obtaining the average deviation and the standard deviation based on the deviation between the contour point and the fitted circle, obtaining the discreteness of the contour based on the average deviation and the standard deviation, and determining that the shape of the contour is a circle when the roundness and discreteness of the contour fall within the numerical range of the roundness and discreteness of the circle; S5. Process the radius of the circular contour, the area of ​​the fitted circle, the average deviation, the standard deviation and the initial radius, the initial area of ​​the fitted circle, the initial average deviation and the initial standard deviation to generate the radius change, the fitted circle area change, the average deviation change and the standard deviation change; process the radius change, the fitted circle area change, the average deviation change and the standard deviation change and perform correlation analysis to generate a comprehensive damage index; judge the damage type of the connection point of the assembly segment beam according to the radius change, area change, average deviation change and standard deviation change; judge the degree of damage of the connection point between the assembly segment beams according to the interval range of the comprehensive damage index.

2. The damage identification method for a prefabricated bridge structure according to claim 1 is characterized in that: The process of graying the image of the assembly segment connection point and obtaining the recognition image is as follows: The image of the connection point is grayed to obtain the recognition image, based on the following formula: ； in, is the gray value of the pixel in the recognition image, , , They are respectively the pixel red component value, green component value and blue component value of the image connecting the points after image scaling.

3. The damage identification method for a prefabricated bridge structure according to claim 2 is characterized in that: The Sobel operator is used to calculate the gradient of the recognition image in the horizontal and vertical directions. The process of obtaining the gradient amplitude is as follows: The grayscale value of the pixel and its adjacent pixel points are multiplied with the horizontal gradient template of the Sobel operator, and all the product results are added to obtain the horizontal gradient value of the pixel. The grayscale value of the pixel and its adjacent pixel points are multiplied with the vertical gradient template of the Sobel operator, and all the product results are added to obtain the vertical gradient value of the pixel. The formula for calculating the horizontal gradient value and the vertical gradient value is: ； ； in, , Respectively Row, No. The horizontal and vertical gradient values ​​of the column pixels. For the Row, No. Gray value of the column pixel; The formula for generating the gradient amplitude of a pixel is: ； in, For the Row, No. The gradient magnitude of the pixel column.

4. The damage identification method for a prefabricated bridge structure according to claim 3 is characterized in that: The process of performing threshold edge detection on the gradient amplitude and obtaining edge pixels and non-edge pixels is as follows: Setting the Threshold , classify the pixels in the gradient magnitude map into edge pixels and non-edge pixels; when , then mark the pixel as an edge pixel; when , then mark the pixel as a non-edge pixel.

5. The damage identification method for a prefabricated bridge structure according to claim 4 is characterized in that: The process of detecting the edge image and extracting all contour lines, analyzing all extracted contour lines, and screening out the contours of the connection points is as follows: Use the contour detection algorithm to extract all contour lines from the edge image. Contour detection is regarded as a process of marking connected areas. The contours are initially screened according to their area. The area of ​​the contour is obtained by calculating the number of pixels it contains. The area formula is as follows: ； in, Represents a contour, Representing contours A pixel in Represents the area of ​​the contour. "1" actually means that for all the contours Count the pixels and set an area threshold , filter out contours whose area is larger than the threshold: ； in, is the first contour set after screening, including all contours whose areas are larger than the threshold; The shape features of the contours, i.e., aspect ratio and circularity, are analyzed to determine whether they contain the connection point. The circumscribed rectangle of the contour is used to calculate the aspect ratio. The aspect ratio formula of the circumscribed rectangle is as follows: ； in, For outline The aspect ratio, and Respectively represent contours The width and height of the bounding rectangle of the , setting the minimum aspect ratio and maximum value , filter out the contours that meet the conditions: ； in, is the second contour set after screening, including all contours whose aspect ratios are within the set range; For each contour, check its distance to other contours, if the minimum distance between two contour points is less than the threshold , they are considered to contain a connection point; Minimum distance between contours The formula is: ； in, , are two different contours in the second contour set, Representing contours A pixel in Representing contours A pixel in To point to the outline The index of a specific pixel in To point to the outline The index of a specific pixel in ; Filter out contour pairs that meet the conditions: ； in, is a set of contour pairs containing connection points, is the minimum distance threshold.

6. The damage identification method for a prefabricated bridge structure according to claim 5 is characterized in that: According to the contour of the connection points, the circularity, aspect ratio and number of vertices of the contour are calculated. According to the numerical range of the circularity, aspect ratio and number of vertices of the contour, the shape of the contour is preliminarily identified. The specific steps are as follows: The formula for circularity is as follows: ； in, , , are the contours in the contour pair set Circularity, area, and perimeter; ； in, For outline The number of vertices, Represents the contour Perform polygon approximation and return the number of vertices of the approximated polygon. is the error parameter, which indicates the accuracy of the approximation. The smaller the value, the higher the accuracy of the approximation and the more vertices there are. The larger the value, the lower the accuracy of the approximation and the fewer vertices there are. when , , then the shape of the contour is a circle; when , , then the shape of the contour is a square; when , , , then the shape of the contour is a rectangle; when , or , , the shape of the contour is a triangle.

7. The damage identification method for a prefabricated bridge structure according to claim 6 is characterized in that: The least square method is used to fit a circle to the contours in the contour pair set, the center point and radius of the contour are obtained, and the fitted contour area and the fitted circle area are obtained according to the radius of the contour. The process of obtaining the roundness of the contour according to the fitted contour area and the fitted circle area is as follows: The goal of least squares circle fitting is to find a circle that minimizes the sum of squared distances from all contour points. The equation of the circle is: ； Among them, (a, b) is the coordinate of the center of the circle, and r is the radius; Convert the equation of the circle into linear form so that we can use the least squares method: ； set up , then: ； make , , , then the equation becomes: ； For each contour point , then: ; in, is the index of the contour point; the equations of all points are expressed in matrix form: ； in, is the number of contour points; recorded as: ； in: ， ， ； The least squares solution is obtained by solving the following equation: ； ； in, is transposed; get Then, calculate the center and radius: ， ， ； The area of ​​the fitted contour Calculated by the polygon area formula of the contour points: ； Area of ​​the fitted circle Calculated based on the radius: ； The roundness of the contour is an indicator of how close it is to the fitted circle shape. The formula is as follows: 。 8. The damage identification method for a prefabricated bridge structure according to claim 7 is characterized in that: Calculate the deviation between the contour point and the fitting circle, obtain the average deviation and standard deviation, and obtain the discreteness of the contour based on the average deviation and standard deviation as follows: The equation of the known fitting circle is: ； For each contour point , calculate its distance to the center of the circle The Euclidean distance : ； Calculate the distance and radius of each contour point to the fitted circle The deviation between : ； Calculate the average of all deviations to get the mean deviation : ； Calculate the standard deviation of all deviations : ； Calculate the dispersion of the contour : ； in, is the weight factor; When the roundness and discreteness of the contour fall within the numerical range of the roundness and discreteness of the circle, the specific process of determining that the shape of the contour is a circle is as follows: When the roundness of the contour is , Discreteness , the contour is considered to be circular.

9. The damage identification method for a prefabricated bridge structure according to claim 8 is characterized in that: The radius, fitted circle area, average deviation, standard deviation of the circular contour and the initial radius, initial fitted circle area, initial average deviation, and initial standard deviation are processed to generate the radius change, fitted circle area change, average deviation change, and standard deviation change. The radius change, fitted circle area change, average deviation change, and standard deviation change are processed and correlated to generate a comprehensive damage index based on the following formula: Radius change : ； Fitted circle area change : ； Mean deviation change : ； Standard Deviation Change : ； , , , They are initial radius, initial fitting circle area, initial mean deviation, and initial standard deviation; ； in, is the comprehensive injury index, is the weight coefficient of radius change, is the weight coefficient of area change, is the weight coefficient of the average deviation change, is the weight coefficient of the standard deviation change, , ; According to the change in radius, the change in the area of ​​the fitted circle, the change in the average deviation and the change in the standard deviation, the damage type of the assembly segment connection point is determined, and according to the range of the comprehensive damage index, the damage degree of the assembly segment connection point is determined. The specific process is as follows: When the radius changes If it is not 0, it means that the connection point of the assembly segment has undergone overall deformation due to stress or fatigue; When the fitted circle area changes If it is not 0, it means that the connection point of the assembly segment has undergone overall deformation due to material expansion, contraction or local fracture; When the mean deviation changes If it is not 0, it means that the assembly segment connection point has a manufacturing defect or an assembly error that causes overall deformation; When the standard deviation changes If it is not 0, it means that the connection point of the assembly segment has an overall deformation caused by material inhomogeneity or local damage; According to the comprehensive injury index , define the damage degree interval: when , it means that there is slight damage at the connection point of the assembly section; when , it means that the connection point of the assembly segment has moderate damage; when , it means that the connection point of the assembly section is seriously damaged.

10. A system for identifying damage to an assembled bridge structure, the system being used to execute the method for identifying damage to an assembled bridge structure according to any one of claims 1 to 9, characterized in that: include: An image processing module is used to obtain images of the connection points of the assembly segments, scale the images of the connection points of the assembly segments, adjust the image size to a uniform size of 224*224, perform grayscale processing on the images of the connection points of the assembly segments, and obtain a recognition image; The contour extraction module is used to calculate the gradient of the recognition image in the horizontal and vertical directions using the Sobel operator to obtain the gradient amplitude, perform threshold edge detection on the gradient amplitude, obtain edge pixels and non-edge pixels, connect all edge pixels to form an edge image, detect the edge image and extract all contour lines, analyze all extracted contour lines, and filter out the contours of the connection points; A recognition module is used to calculate the circularity, aspect ratio and number of vertices of the contour according to the contour of the connection points, and preliminarily recognize the shape of the contour according to the numerical range of the circularity, aspect ratio and number of vertices of the contour; A data processing module is used to fit a circle to the contour using the least square method, obtain the center point and radius of the contour, and obtain the area of ​​the fitted contour and the area of ​​the fitted circle according to the radius of the contour, obtain the roundness of the contour according to the area of ​​the fitted contour and the area of ​​the fitted circle, calculate the deviation between the contour point and the fitted circle, obtain the average deviation and the standard deviation according to the deviation between the contour point and the fitted circle, obtain the discreteness of the contour according to the average deviation and the standard deviation, and determine that the shape of the contour is a circle when the roundness and discreteness of the contour fall within the numerical range of the roundness and discreteness of the circle; The judgment module is used to process the radius, fitted circle area, average deviation, standard deviation of the circular contour and the initial radius, initial fitted circle area, initial average deviation, and initial standard deviation to generate radius change, fitted circle area change, average deviation change, and standard deviation change; perform data processing and correlation analysis on the radius change, fitted circle area change, average deviation change, and standard deviation change to generate a comprehensive damage index; judge the damage type of the assembly segment connection point according to the radius change, area change, average deviation change, and standard deviation change; and judge the degree of damage of the assembly segment connection point according to the interval range of the comprehensive damage index.

Images