Concrete crack detection method for bridge engineering

Abstract

The invention relates to the technical field of image processing, in particular to a concrete crack detection method for bridge engineering, which comprises the following steps: acquiring a crack area and a main tensile stress direction; dividing the crack region into a plurality of crack sub-regions; dividing the crack sub-region into a plurality of local crack sub-regions; according to the extension direction of the local crack sub-region and the main tensile stress direction, the harmful degree of the crack sub-region is obtained; according to the extension direction and the harmful degree of the adjacent crack sub-regions, the splicing degree between the adjacent crack sub-regions is obtained, and a plurality of harmful cracks are obtained; and evaluating the quality of the bridge according to the distribution positions, the harmful degrees and the areas of all the harmful cracks in the bridge. According to the method, the formation reason of the harmful crack in the bridge is analyzed, the characteristics of the harmful crack are extracted, the harmful crack is obtained according to the characteristics of the harmful crack, and the accuracy of evaluating the bridge quality is further improved according to the distribution of the harmful crack and the size of the harmful crack.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and particularly relates to a method for detecting concrete cracks for bridge engineering. Background Art

[0002] To ensure the safety of the overall structure of the beam and extend the service life of the bridge, it is necessary to detect the cracks in the concrete of the bridge to evaluate the quality of the bridge. When the cast concrete has not yet solidified, as the moisture on the concrete surface gradually evaporates, fine cracks will inevitably form on the concrete surface due to surface shrinkage. However, such cracks are normal phenomena generated during the casting of concrete and will not endanger the structural safety of the bridge. Traditional concrete crack detection methods will identify all cracks. However, harmless cracks always occur during the solidification of concrete, and harmless cracks do not harm the structure of the bridge. Therefore, the quality of the bridge cannot be accurately evaluated only by the size of the cracks on the bridge surface. Summary of the Invention

[0003] The present invention provides a method for detecting concrete cracks for bridge engineering to solve the existing problem that the quality of the bridge cannot be accurately evaluated only by the size of the cracks on the bridge surface.

[0004] A method for detecting concrete cracks for bridge engineering of the present invention adopts the following technical solutions: Including the following steps: Obtain a plurality of crack regions in the bridge and the principal tensile stress directions at each position; Divide the crack regions into a plurality of crack sub-regions; divide the crack sub-regions into a plurality of local crack sub-regions; according to the extension direction of the local crack sub-regions and the principal tensile stress direction at the corresponding position, obtain the harmful factors of the local crack sub-regions, where the harmful factors characterize the perpendicular situation between the extension direction and the principal tensile stress direction; according to the differences between the harmful factors of each local crack sub-region and adjacent local crack sub-regions in the crack sub-region, obtain the harmful degree of the crack sub-region; Determine the extension consistency of adjacent crack sub-regions according to the difference in the inclination angles of adjacent crack sub-regions; determine the parameter consistency of adjacent crack sub-regions according to the relative deviation of the harmful degrees of adjacent crack sub-regions; combine the extension consistency and the parameter consistency to determine the fitting degree between adjacent crack sub-regions, where both the extension consistency and the parameter consistency are positively correlated with the fitting degree; according to the fitting degree between adjacent crack sub-regions, obtain a plurality of harmful cracks; Determine the harm degree of the harmful cracks according to the harm degrees of all crack sub-regions in all harmful cracks; obtain the harm degree of the harmful cracks to the bridge according to the distances between the harmful cracks and all other harmful cracks, in combination with the harm degrees of all harmful cracks, where the harm degree and the harm degree are positively correlated; evaluate the bridge quality according to the harm degrees of all harmful cracks, in combination with the areas of all harmful cracks.

[0005] Preferably, the specific method for dividing the crack region into several crack sub-regions includes: For any crack region, use the Guo-Hall algorithm to obtain the skeleton of the crack region; mark the pixel points on the skeleton as skeleton pixel points. For any skeleton pixel point, if there are three or more skeleton pixel points in its eight-neighborhood, then use the skeleton pixel point as a segmentation point; divide the skeleton into several segments through all the segmentation points in the skeleton to obtain several skeleton segments; For any pixel point in the crack region, obtain the distance between the pixel point and each skeleton segment, and use the skeleton segment with the closest distance to the pixel point as the skeleton segment corresponding to the pixel point; Obtain the skeleton segment corresponding to each pixel point in the crack region, and classify several pixel points corresponding to the same skeleton segment into the same crack sub-region to obtain several crack sub-regions.

[0006] Preferably, the specific method for dividing the crack sub-region into several local crack sub-regions includes: For any crack sub-region, equally divide the skeleton segment of the crack sub-region into several sub-skeleton segments with a length of , where the is the preset length of the sub-skeleton segment; For any pixel point in the crack sub-region, obtain the distance between the pixel point and each sub-skeleton segment, and use the sub-skeleton segment with the closest distance to the pixel point as the sub-skeleton segment corresponding to the pixel point; Obtain the sub-skeleton segment corresponding to each pixel point in the crack sub-region, and classify several pixel points corresponding to the same sub-skeleton segment into the same local crack sub-region to obtain several local crack sub-regions.

[0007] Preferably, the specific method for obtaining the harmful factor of the local crack sub-region according to the extension direction of the local crack sub-region and the principal tensile stress direction at the corresponding position includes: For any local crack sub-region, through the least squares method, according to the coordinate positions of all pixel points in the local crack sub-region, perform linear fitting on it to obtain the fitting line of the local crack sub-region, and use the direction of the fitting line of the local crack sub-region as the extension direction of the local crack sub-region; Obtain the harmful factor of the local crack sub-region according to the extension direction of the local crack sub-region and the principal tensile stress direction at each pixel position in the local crack sub-region.

[0008] Preferably, the specific calculation formula for obtaining the harmful factor of the local crack sub-region is: In the formula, represents the harmful factor of the local crack sub-region; represents the number of pixel points in the local crack sub-region; the extension direction of the local crack sub-region; represents the principal tensile stress direction at the position of the th pixel point in the local crack sub-region; represents the sine trigonometric function;

[0009] Preferably, obtaining the harmful degree of the crack sub-region according to the difference between the harmful factors of each local crack sub-region and the adjacent local crack sub-regions in the crack sub-region includes the following specific methods: For any crack sub-region, obtain the harmful degree of the crack sub-region according to the harmful factor of each local crack sub-region in the crack sub-region and the difference in the harmful factor of the adjacent local crack sub-regions in the crack sub-region. The specific calculation formula is: In the formula, represents the harmful degree of the crack sub-region; represents the number of local crack sub-regions in the crack sub-region; represents the harmful factor of the th local crack sub-region in the crack sub-region; represents the number of local crack sub-regions adjacent to the th local crack sub-region in the crack sub-region; represents the harmful factor of the th local crack sub-region adjacent to the th local crack sub-region in the crack sub-region;

[0010] Preferably, combining the extension consistency and the parameter consistency to determine the joining degree between adjacent crack sub-regions includes the following specific methods: For any crack sub-region, denote the crack sub-region as the reference region, and denote the crack sub-region adjacent to the reference region as the target region; The calculation formula for the degree of fitting between the reference region and the target region is: In the formula, represents the degree of fitting between the reference region and the target region; represents the slope of the fitting line of the target region; represents the slope of the fitting line of the reference region; represents the degree of harm of the target region; represents the degree of harm of the reference region; represents the arctangent function; represents a preset hyperparameter; represents the linear normalization function; is the extension consistency between the reference region and the target region; is the inclination angle of the target region; is the inclination angle of the reference region; is the parameter consistency between the reference region and the target region; Among them, the method for obtaining the slope of the fitting line of each crack sub-region is: for each crack sub-region, according to the position coordinates of the respective pixel points in the crack sub-region, use the least squares method to fit the crack sub-region respectively to obtain the fitting line of the crack sub-region; use the slope of the fitting line of the crack sub-region as the slope of the fitting line of the crack sub-region.

[0011] Preferably, the specific method for obtaining several harmful cracks according to the degree of fitting between adjacent crack sub-regions includes: Preset a fitting degree threshold ; if the degree of fitting between the reference region and the target region is greater than or equal to , classify the reference region and the target region as the same harmful crack; Judge the degree of fitting of all crack sub-regions and the crack sub-regions adjacent to them to obtain several harmful cracks.

[0012] Preferably, the calculation formula for the harm degree of the harmful cracks to the bridge is: In the formula, represents the harm degree of the th harmful crack; represents the degree of harm of the th harmful crack; represents the degree of harm of the th harmful crack; Represents the number of harmful cracks; Represents the th harmful crack and the th harmful crack; Represents the sigmoid function.

[0013] Preferably, evaluating the bridge quality according to the harm levels of all harmful cracks and combining with the areas of all harmful cracks, the specific method includes: Obtaining the bridge quality according to the harm levels of all harmful cracks and the areas of all harmful cracks, and its specific calculation formula is: In the formula, Represents the bridge quality; Represents the number of harmful cracks; Represents the th harm level of the harmful crack; Represents the th area of the harmful crack; Represents the exponential function with the natural constant as the base.

[0014] The beneficial effects of the technical solution of the present invention are as follows: In this application, the crack area is divided into several crack sub-areas; the crack sub-areas are further divided into several local crack sub-areas. Since the crack area in the bridge may be composed of multiple intersecting cracks, and when the crack area is composed of the intersection of harmful cracks and harmless cracks, the harmful cracks and harmless cracks in the crack area will interfere with each other, resulting in the inability to accurately quantify the harm degree of the crack area to the bridge. Therefore, it is necessary to divide the crack area into several crack sub-areas; and because harmful cracks are caused by the concrete at the crack being subjected to stress exceeding its load limit, harmful cracks always distribute along the direction perpendicular to the principal tensile stress. Therefore, according to the perpendicular degree between the extension direction of the local crack sub-area and the principal tensile stress direction at the corresponding position, the harmful factor of the local crack sub-area is obtained; according to the harmful factors of each local crack sub-area in the crack sub-area, the harm degree of the crack sub-area is obtained. Since when evaluating the harm degree of cracks to a bridge, a complete crack cannot be split into several crack segments to evaluate its harm degree to the bridge, the degree of joining between adjacent crack sub-regions is obtained according to the differences in the extension directions of adjacent crack sub-regions and by combining the respective harmful degrees of adjacent crack sub-regions; several harmful cracks are obtained according to the degree of joining between adjacent crack sub-regions; the harm degree of harmful cracks is obtained according to the harm degree of harmful cracks and by combining the distribution positions of all harmful cracks in the bridge; and the quality of the bridge is evaluated according to the harm degrees of all harmful cracks and by combining the areas of all harmful cracks. By analyzing the causes of harmful cracks formed in the bridge, extracting the characteristics of harmful cracks, obtaining harmful cracks according to the characteristics of harmful cracks, and further combining the distribution of harmful cracks with the size of harmful cracks, the accuracy of evaluating the quality of the bridge is improved in this application. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following-described drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0016] Figure 1 It is a flowchart of the steps of a concrete crack detection method for a bridge project according to the present invention; Figure 2 It is a gray scale legend diagram of the bridge; Figure 3 It is a legend diagram of the edges of the cracks in the bridge. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following, in combination with the drawings and preferred embodiments, details the specific implementation manner, structure, features, and effects of a concrete crack detection method for a bridge project according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0019] The following specifically describes the specific solution of a concrete crack detection method for a bridge project provided by the present invention with reference to the drawings.

[0020] Please refer to Figure 1, which shows a flow chart of the steps of a concrete crack detection method for bridge engineering provided by an embodiment of the present invention, the method comprising the following steps: Step S001: Obtain several crack areas in the bridge and the principal tensile stress directions at various positions.

[0021] It should be noted that in order to ensure the safety of the overall structure of the bridge and extend the service life of the bridge, it is necessary to evaluate the quality of the bridge, and the cracks in the bridge will seriously affect the quality of the bridge. In order to accurately evaluate the quality of the bridge, it is necessary to obtain the cracks in the bridge, but the traditional method of evaluating the quality of the bridge is only based on the size of the cracks in the bridge, without considering the different degrees of harm to the bridge caused by the cracks in different bridges, that is, the traditional method of evaluating the quality of the bridge based on the cracks in the bridge cannot accurately evaluate the quality of the bridge. Therefore, this embodiment proposes a concrete crack detection method for bridge engineering, which specifically analyzes the morphological characteristics of each crack in the bridge and evaluates the degree of harm to the bridge caused by each crack, so as to improve the accuracy of evaluating the quality of the bridge. To this end, it is necessary to first collect the surface image of the bridge and obtain the crack area therein; and because the cracks that seriously endanger the safety of the bridge are caused by the concrete bearing stress exceeding its load upper limit, they are always distributed in the vertical direction of the principal tensile stress. In order to evaluate the degree of harm of the cracks to the bridge, it is necessary to further obtain the principal tensile stress direction at each position in the bridge.

[0022] Specifically, the bridge surface image is captured by a high-definition camera, and the bridge surface image is grayed and denoised by Gaussian filtering to obtain a bridge grayscale image, such as Figure 2 As shown, Figure 2 For the bridge grayscale image, we further use the edge detection algorithm to obtain the edges in the bridge grayscale image, such as Figure 3 As shown, Figure 3 It is a bridge crack edge diagram, and the edge of the bridge grayscale image and the area surrounded by the edge are regarded as the crack area; Furthermore, based on the structure of the bridge, the finite element analysis method is used to obtain the direction of the principal tensile stress at various positions in the bridge.

[0023] It should be noted that, since grayscale, Gaussian filtering, finite element analysis, and edge detection algorithms are all well-known existing technologies, they will not be described in detail in this embodiment. This embodiment does not impose a rigid requirement on the edge detection algorithm for obtaining the edge in the bridge grayscale image. In this embodiment, the Sobel edge detection algorithm is used to obtain the edge in the bridge grayscale image. The edge in the bridge grayscale image is the crack edge in the bridge.

[0024] At this point, the crack area in the bridge and the direction of the principal tensile stress at each position are obtained.

[0025] Step S002: Divide the crack region into several crack sub-regions; divide the crack sub-regions into several local crack sub-regions; according to the extension direction of the local crack sub-regions and the principal tensile stress direction at the corresponding positions, obtain the harmful factors of the local crack sub-regions, where the harmful factors characterize the perpendicularity between the extension direction and the principal tensile stress direction; according to the differences between the harmful factors of each local crack sub-region and adjacent local crack sub-regions in the crack sub-region, obtain the harmful degree of the crack sub-region.

[0026] It should be noted that the cracks in the bridge can be divided into harmful cracks and harmless cracks. Among them, harmful cracks are caused by the concrete at the crack being subjected to stress exceeding its load limit, which usually seriously endangers the safety of the bridge structure; while harmless cracks are caused by the evaporation of moisture and volume shrinkage during the solidification of the concrete, which usually do not endanger the safety of the bridge structure; however, when evaluating the quality of the bridge through the cracks in the bridge in the traditional way, only the size of the cracks in the bridge is considered, without considering the harm degree of different cracks to the bridge. Therefore, the quality of the bridge cannot be accurately evaluated by the cracks in the bridge in the traditional way; thus, this embodiment proposes a method for detecting concrete cracks for bridge engineering, specifically by analyzing the morphological characteristics of each crack to obtain the harm degree of each crack to the bridge, so as to accurately evaluate the quality of the bridge.

[0027] It should be further noted that since the crack region in the bridge may be composed of multiple intersecting cracks, and when the crack region is composed of the intersection of harmful cracks and harmless cracks, the harmful cracks and harmless cracks in the crack region will interfere with each other, resulting in the inability to accurately quantify the harm degree of the crack region to the bridge. Therefore, it is necessary to divide the crack region into several crack sub-regions; and since harmful cracks are caused by the concrete at the crack being subjected to stress exceeding its load limit, harmful cracks always distribute along the direction perpendicular to the principal tensile stress. Therefore, based on this, the harmful factors of the crack sub-region can be obtained.

[0028] Preferably, in a specific embodiment of the present invention, for any crack region, use the Guo-Hall algorithm to obtain the skeleton of the crack region. Since the Guo-Hall algorithm is a well-known existing technology, it will not be elaborated in this embodiment; record the pixel points on the skeleton as skeleton pixel points. For any skeleton pixel point, if there are three or more skeleton pixel points in its eight-neighborhood, then use the skeleton pixel point as a segmentation point; through all the segmentation points in the skeleton, divide the skeleton into several segments to obtain several skeleton segments; Furthermore, for any pixel point in the crack region, obtain the distance between the pixel point and each skeleton segment, and use the skeleton segment with the closest distance to the pixel point as the skeleton segment corresponding to the pixel point; Obtain the skeleton segments corresponding to each pixel point in the crack region, and group several pixel points corresponding to the same skeleton segment into the same crack sub-region to obtain several crack sub-regions.

[0029] It should be noted that the pixel points in the crack sub-region are the pixel points in the same crack. The cracks in the bridge do not distribute vertically along the direction of the principal tensile stress corresponding to their positions in a straight line. Therefore, to better capture the harmful crack characteristics of the crack sub-region, it is necessary to further segment the crack sub-region.

[0030] Preferably, in a specific embodiment of the present invention, for any crack sub-region, divide the skeleton segment of the crack sub-region into several sub-skeleton segments with a length of , where the is the preset length of the sub-skeleton segment. The specific value of can be set according to the actual situation by itself, and there is no rigid requirement in this embodiment. In this embodiment, it is described by taking as an example (if the length of the last sub-skeleton segment in the crack sub-region is less than , then the remaining existing skeleton segment is used as the last sub-skeleton segment); Furthermore, for any pixel point in the crack sub-region, obtain the distance between the pixel point and each sub-skeleton segment, and take the sub-skeleton segment with the closest distance to the pixel point as the sub-skeleton segment corresponding to the pixel point; Obtain the sub-skeleton segments corresponding to each pixel point in the crack sub-region, and group several pixel points corresponding to the same sub-skeleton segment into the same local crack sub-region to obtain several local crack sub-regions.

[0031] It should be noted that when the extension direction of the local crack sub-region is more perpendicular to the direction of the principal tensile stress corresponding to its position, the local crack sub-region has more characteristics of harmful cracks. Therefore, first obtain the extension direction of the local crack sub-region, and obtain the harmful factor of the local crack sub-region according to the perpendicular degree between the extension direction of the local crack sub-region and the principal tensile stress direction of the local crack sub-region.

[0032] Preferably, in a specific embodiment of the present invention, for any local crack sub-region, through the least squares method, according to the coordinate positions of all pixel points in the local crack sub-region, perform linear fitting on it. Since the least squares method is a well-known existing technology, it will not be elaborated in this embodiment; obtain the fitting straight line of the local crack sub-region, and take the direction of the fitting straight line of the local crack sub-region as the extension direction of the local crack sub-region, where the extension direction is obtained based on from top to bottom and from left to right; Further, according to the extension direction of the local crack sub-region and the principal tensile stress direction at each pixel position in the local crack sub-region, the harmful factor of the local crack sub-region is obtained, and its specific calculation formula is: In the formula, represents the harmful factor of the local crack sub-region; represents the number of pixel points in the local crack sub-region; the extension direction of the local crack sub-region; represents the principal tensile stress direction at the position of the th pixel point in the local crack sub-region; represents the sine trigonometric function;

[0033] It should be noted that represents the angle between the extension direction of the local crack sub-region and the principal tensile stress direction at each pixel position in the local crack sub-region; therefore, when the value of is larger, it indicates that the extension direction of the local crack sub-region is perpendicular to the principal tensile stress direction at each pixel position in the local crack sub-region, that is, the local crack sub-region is more likely to be a harmful crack, that is, it is more likely to endanger the structure of the bridge.

[0034] It should be further noted that the harmful factor of the local crack sub-region represents the perpendicular degree between the extension direction of the local crack sub-region and the principal tensile stress direction at its position. And when the number of local crack sub-regions with high harmful factors in the crack sub-region is larger and more continuous, then the crack sub-region is more likely to be caused by bearing a load exceeding its upper limit; therefore, based on this, the harmful degree of the crack sub-region can be obtained.

[0035] Preferably, in a specific embodiment of the present invention, for any crack sub-region, according to the harmful factors of each local crack sub-region in the crack sub-region and the difference in harmful factors between adjacent local crack sub-regions in the crack sub-region, the harmful degree of the crack sub-region is obtained, and its specific calculation formula is: In the formula, represents the harmful degree of the crack sub-region; represents the number of local crack sub-regions in the crack sub-region; represents the harmful factor of the th local crack sub-region in the crack sub-region; The number of local crack sub-regions adjacent to a local crack sub-region; Indicates the th local crack sub-region in the crack sub-region Harmful factor of the adjacent local crack sub-region; Indicates the absolute value function; Indicates the exponential function with the natural constant as the base. In this embodiment, The model is used to present the inverse proportional relationship and normalization processing. Is the input of the model, and the implementer can set the inverse proportional function and normalization function according to the actual situation.

[0036] It should be noted that Indicates the difference in harmful factors between adjacent local crack sub-regions. Since the overall harmful cracks are distributed along the direction of the principal tensile stress at their corresponding positions, the difference in harmful factors between adjacent local sub-regions in the crack sub-region is small; while The larger the value of , the more and more continuous the number of local crack sub-regions with high harmful factors in the crack sub-region. Therefore,

[0037] So far, the harmful degree of the crack sub-region is obtained.

[0038] Step S003: Determine the extension consistency of adjacent crack sub-regions according to the difference in inclination angles between adjacent crack sub-regions; determine the parameter consistency of adjacent crack sub-regions according to the relative deviation of the harmful degrees of adjacent crack sub-regions; combine the extension consistency and the parameter consistency to determine the fitting degree between adjacent crack sub-regions, where both the extension consistency and the parameter consistency are positively correlated with the fitting degree; obtain several harmful cracks according to the fitting degree between adjacent crack sub-regions.

[0039] It should be noted that since harmful cracks are the external manifestations of the damage to the bridge structure, and usually the stress concentration at the tip of long cracks is more significant, resulting in the tip of long cracks being more likely to approach the critical fracture size of the material; at the same time, long cracks are more likely to directly penetrate the key stress-bearing areas in the bridge, significantly weakening the bearing capacity of the bridge structure and causing overall instability, while the impact of scattered short cracks on the bearing capacity of the remaining material is relatively small; for example, the harm caused by a 10-cm long harmful crack to the bridge is greater than that caused by two 5-cm harmful cracks to the bridge. Therefore, to accurately evaluate the harm degree of cracks to the bridge, a complete crack cannot be split into several crack segments to evaluate its harm degree to the bridge. To accurately evaluate the bridge quality, it is necessary to calculate the degree of fitting of several crack sub-regions decomposed in step S002 and perform fitting on them to obtain several complete harmful cracks; through the whole of the complete harmful cracks, the bridge quality can be accurately evaluated.

[0040] Preferably, in a specific embodiment of the present invention, for any crack sub-region, the crack sub-region is denoted as the reference region, and the crack sub-region adjacent to the reference region is denoted as the target region; The calculation formula for the degree of fitting between the reference region and the target region is: In the formula, represents the degree of fitting between the reference region and the target region; represents the slope of the fitting line of the target region; represents the slope of the fitting line of the reference region; represents the harm degree of the target region; represents the harm degree of the reference region; represents the arctangent function; represents a preset hyperparameter, the purpose of which is to avoid the occurrence of a denominator of 0 during the fractional operation process, The specific value of can be set according to the actual situation, and there is no rigid requirement in this embodiment. In this embodiment, it is described by taking as an example; represents a linear normalization function, and its specific normalization range is between the reference region and all target regions ; is the extension consistency between the reference region and the target region; is the inclination angle of the target region; is the inclination angle of the reference region; is the parameter consistency between the reference region and the target region.

[0041] In a specific embodiment of the present invention, the extension consistency is determined according to the difference in the inclination angles of adjacent crack sub-regions. More specifically: a negative correlation mapping is performed on the sum value of the difference in the inclination angles of adjacent crack sub-regions and a preset hyperparameter, and the result value of this negative correlation mapping is the extension consistency of the adjacent crack sub-regions.

[0042] In a specific embodiment of the present invention, the parameter consistency is determined according to the relative deviation of the harmful degree of adjacent crack sub-regions. More specifically: the sum value of the harmful degrees of adjacent crack sub-regions is used as the numerator, and the sum value of the absolute value of the difference in the harmful degrees of adjacent crack sub-regions and a preset hyperparameter is used as the denominator. The ratio composed of the numerator and the denominator is the parameter consistency of the adjacent crack sub-regions. Here, the relative deviation of the harmful degree of adjacent crack sub-regions is reflected by the ratio of the sum value to the difference value of the harmful degrees of adjacent crack sub-regions.

[0043] It should be noted that the degree of fitting between the reference region and the target region represents the possibility that the reference region and the target region belong to the same harmful crack; when the reference region and the target region belong to the same harmful crack, the reference region and the target region are approximately the same in the extension direction, and represents the difference in the extension direction between the reference region and the target region. The smaller its value, the more likely the reference region and the target region belong to the same crack; if the reference region and the target region belong to the same harmful crack, then the reason for dividing the harmful crack into the reference region and the target region is that there are other cracks at the junction of the reference region and the target region, thus dividing the harmful crack into the reference region and the target region. Therefore, if the reference region and the target region belong to the same harmful crack, then the reference region and the target region are similar in terms of harmful degree, and the harmful degree of the reference region and the target region is large. Therefore the larger the value of, the greater the possibility that the reference region and the target region belong to the same harmful crack.

[0044] In a specific embodiment of the present invention, the method for obtaining the fitting line slope of each crack sub-region is as follows: for each crack sub-region, according to the position coordinates of the respective pixel points in the crack sub-region, the least squares method is used to fit each crack sub-region respectively to obtain the fitting line of the crack sub-region; the slope of the fitting line of the crack sub-region is used as the fitting line slope of the crack sub-region.

[0045] Preferably, in a specific embodiment of the present invention, a fitting degree threshold is preset , The specific value of can be set according to the actual situation by itself, and this embodiment does not make a rigid requirement. In this embodiment, Describe; if the degree of fitting between the reference area and the target area is greater than or equal to then classify the reference area and the target area as the same harmful crack; Judge the degree of fitting between all crack sub-regions and their adjacent crack sub-regions to obtain several harmful cracks.

[0046] It should be noted that when evaluating the harm degree of the crack area to the bridge, a complete crack cannot be split into several crack segments to evaluate its harm degree to the bridge; in order to accurately evaluate the harm degree of the crack to the bridge, it is necessary to obtain the part composed of the complete harmful cracks in the crack area; and the harmful cracks in the crack area are composed of several adjacent crack sub-regions; represents the part composed of the complete harmful cracks in the crack area, which is prepared for accurately evaluating the harm degree of the crack area to the bridge subsequently.

[0047] Thus, several harmful cracks are obtained.

[0048] Step S004: Determine the harm degree of the harmful cracks according to the harm degree of all crack sub-regions in all harmful cracks; according to the distance between the harmful cracks and all other harmful cracks, combined with the harm degree of all harmful cracks, obtain the harm degree of the harmful cracks to the bridge, where the harm degree and the harm degree are positively correlated; evaluate the bridge quality according to the harm degree of all harmful cracks, combined with the area of all harmful cracks.

[0049] According to the harm degree of the crack sub-regions in the harmful cracks, combined with the distribution positions of all harmful cracks in the bridge, obtain the harm degree of the harmful cracks; evaluate the bridge quality according to the harm degree of all harmful cracks, combined with the area of all harmful cracks.

[0050] It should be noted that the several harmful cracks obtained in step S003 represent several complete harmful cracks, that is, the harm degree to the bridge can be evaluated through the harmful cracks; however, since the stress fields between the harmful cracks in the bridge may affect each other, when the distance between the harmful cracks in the bridge is closer, their stress fields will affect each other more, resulting in the superposition of stress concentration areas in the bridge, causing the concrete between the harmful cracks to bear greater stress, that is, the closer the distance between the harmful cracks, the easier the harmful cracks are to expand and form larger cracks. Therefore, when evaluating the bridge quality according to several harmful cracks, it is necessary to not only consider each harmful crack itself, but also combine the positional distribution relationship between each harmful crack for comprehensive evaluation.

[0051] Specifically, for any harmful crack, take the average value of the harm degrees of all crack sub-regions in all harmful cracks as the harm degree of the harmful crack; Obtain the harm degree of the harmful crack based on the distance between the harmful crack and all other harmful cracks, in combination with the harm degrees of all harmful cracks. The specific calculation formula is as follows: In the formula, represents the harm degree of the th harmful crack; represents the harm degree of the th harmful crack; represents the harm degree of the th harmful crack; represents the number of harmful cracks; represents the th harmful crack and the th harmful crack; represents the sigmoid function, which is used for normalization operation in this embodiment.

[0052] It should be noted that the harm degree of the harmful crack represents the harmful crack characteristics possessed by the harmful crack. The more it has the harmful crack characteristics, the more likely the concrete structure here is to be damaged, and the greater the harm to the bridge. When the harmful cracks with large harm degrees are distributed closer, the stress borne by the concrete between the harmful cracks is greater, and subsequent harmful cracks are more likely to expand into larger cracks, endangering the safety of the bridge structure. And the larger the value of , the more the number of harmful cracks near the th harmful crack and the greater their harm degrees. Therefore, the th harmful crack is more likely to expand, that is, the th harmful crack has a greater harm degree to the bridge. After obtaining the harm degrees of all harmful cracks, the quality of the bridge can be further evaluated accurately in combination with the areas of all harmful cracks.

[0053] Specifically, obtain the bridge quality based on the harm degrees of all harmful cracks and the areas of all harmful cracks. The specific calculation formula is as follows: In the formula, represents the bridge quality; represents the number of harmful cracks; represents the th harmful crack; represents the th harmful crack; represents the exponential function with the natural constant as the base. In this embodiment, the model is used to present the inverse proportional relationship and normalization processing. As the input of the model, the implementer can set the inverse proportional function and the normalization function according to the actual situation.

[0054] It should be noted that in this embodiment, by analyzing the causes of harmful cracks in the bridge, extracting the characteristics of harmful cracks, obtaining harmful cracks according to the characteristics of harmful cracks, and further combining the distribution of harmful cracks with the size of harmful cracks, the accuracy of bridge quality assessment is improved.

[0055] So far, this embodiment is completed.

[0056] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for detecting concrete cracks used in bridge engineering, characterized in that, The method includes the following steps: Obtain several crack regions in the bridge and the principal tensile stress directions at various positions; Divide the crack regions into several crack sub-regions; divide the crack sub-regions into several local crack sub-regions; according to the extension direction of the local crack sub-regions and the principal tensile stress direction at the corresponding position, obtain the harmful factors of the local crack sub-regions, where the harmful factors characterize the perpendicularity between the extension direction and the principal tensile stress direction; according to the differences between the harmful factors of each local crack sub-region and adjacent local crack sub-regions in the crack sub-region, obtain the harmful degree of the crack sub-region; Determine the extension consistency of adjacent crack sub-regions according to the difference in the inclination angles of adjacent crack sub-regions; determine the parameter consistency of adjacent crack sub-regions according to the relative deviation of the harmful degrees of adjacent crack sub-regions; combine the extension consistency and the parameter consistency to determine the joining degree between adjacent crack sub-regions, where both the extension consistency and the parameter consistency are positively correlated with the joining degree; obtain several harmful cracks according to the joining degree between adjacent crack sub-regions; Determine the harmful degree of the harmful cracks according to the harmful degrees of all crack sub-regions in all harmful cracks; according to the distances between the harmful cracks and all other harmful cracks, and in combination with the harmful degrees of all harmful cracks, obtain the harm degree of the harmful cracks to the bridge, where the harmful degree is positively correlated with the harm degree; evaluate the bridge quality according to the harm degrees of all harmful cracks and in combination with the areas of all harmful cracks.

2. The concrete crack detection method for bridge engineering according to claim 1, wherein, The specific method included in dividing the crack region into several crack sub-regions is as follows: For any crack region, use the Guo-Hall algorithm to obtain the skeleton of the crack region; mark the pixel points on the skeleton as skeleton pixel points. For any skeleton pixel point, if there are three or more skeleton pixel points in its eight-neighborhood, then use the skeleton pixel point as a segmentation point; divide the skeleton into several segments through all the segmentation points in the skeleton to obtain several skeleton segments; For any pixel point in the crack region, obtain the distance between the pixel point and each skeleton segment, and use the skeleton segment with the closest distance to the pixel point as the skeleton segment corresponding to the pixel point; Obtain the skeleton segment corresponding to each pixel point in the crack region, and group several pixel points corresponding to the same skeleton segment into the same crack sub-region to obtain several crack sub-regions.

3. The concrete crack detection method for bridge engineering according to claim 1, characterized in that, The specific method included in dividing the crack sub-region into several local crack sub-regions is as follows: For any crack sub-region, equally divide the skeleton segment of the crack sub-region into a number of sub-skeleton segments with a length of , where the is a preset length of the sub-skeleton segment; For any pixel point in the crack sub-region, obtain the distance between the pixel point and each skeleton sub-segment, and use the skeleton sub-segment with the closest distance to the pixel point as the skeleton sub-segment corresponding to the pixel point; Obtain the skeleton sub-segment corresponding to each pixel point in the crack sub-region, and group several pixel points corresponding to the same skeleton sub-segment into the same local crack sub-region to obtain several local crack sub-regions.

4. The concrete crack detection method for bridge engineering according to claim 1, characterized in that, The specific method included in obtaining the harmful factors of the local crack sub-regions according to the extension direction of the local crack sub-regions and the principal tensile stress direction at the corresponding position is as follows: For any local crack sub-region, by the least squares method, based on the coordinate positions of all pixel points in the local crack sub-region, perform linear fitting on it to obtain the fitted line of the local crack sub-region, and use the direction of the fitted line of the local crack sub-region as the extension direction of the local crack sub-region; Based on the extension direction of the local crack sub-region and the principal tensile stress direction at each pixel point position in the local crack sub-region, obtain the harmful factor of the local crack sub-region.

5. The concrete crack detection method for bridge engineering according to claim 4, characterized in that, The specific calculation formula for obtaining the harmful factor of the local crack sub-region is: In the formula, represents the harmful factor of the local crack sub-region; represents the number of pixel points in the local crack sub-region; the extension direction of the local crack sub-region; represents the direction of the principal tensile stress at the position of the th pixel point in the local crack sub-region; represents the sine trigonometric function; represents the absolute value function.

6. The concrete crack detection method for bridge engineering according to claim 1, wherein, The specific method for obtaining the harmful degree of the crack sub-region according to the difference between the harmful factors of each local crack sub-region and adjacent local crack sub-regions in the crack sub-region includes: For any crack sub-region, based on the harmful factors of each local crack sub-region in the crack sub-region and the difference in harmful factors between adjacent local crack sub-regions in the crack sub-region, obtain the harmful degree of the crack sub-region. The specific calculation formula is: In the formula, represents the harm degree of the crack sub-region; represents the number of local crack sub-regions in the crack sub-region; represents the th harmful factor of the local crack sub-region in the crack sub-region; represents the number of local crack sub-regions adjacent to the th local crack sub-region in the crack sub-region; represents the th harmful factor of the local crack sub-region adjacent to the th local crack sub-region in the crack sub-region; represents the absolute value function; represents the exponential function with the natural constant as the base.

7. The concrete crack detection method for bridge engineering according to claim 1, characterized in that The specific method for determining the splicing degree between adjacent crack sub-regions by combining the extension consistency and the parameter consistency includes: For any crack sub-region, denote the crack sub-region as the reference region, and denote the crack sub-region adjacent to the reference region as the target region; The calculation formula for the splicing degree between the reference region and the target region is: In the formula, represents the fitting degree between the reference area and the target area; represents the slope of the fitting line of the target area; represents the slope of the fitting line of the reference area; represents the harm degree of the target area; represents the harm degree of the reference area; represents the arctangent function; represents a preset hyperparameter; represents the linear normalization function; is the extension consistency between the reference area and the target area; is the inclination angle of the target area; is the inclination angle of the reference area; is the parameter consistency between the reference area and the target area; Among them, the method for obtaining the slope of the fitted line of each crack sub-region is: for each crack sub-region, based on the position coordinates of its respective pixel points, use the least squares method to perform fitting on the crack sub-region respectively to obtain the fitted line of the crack sub-region; use the slope of the fitted line of the crack sub-region as the slope of the fitted line of the crack sub-region.

8. The concrete crack detection method for bridge engineering according to claim 7, characterized in that, The specific method for obtaining several harmful cracks according to the splicing degree between adjacent crack sub-regions includes: Preset a splicing degree threshold ; If the splicing degree of the reference area and the target area is greater than or equal to , classify the reference area and the target area as the same harmful crack; Judge the splicing degree between all crack sub-regions and their adjacent crack sub-regions to obtain several harmful cracks.

9. The concrete crack detection method for bridge engineering according to claim 1, characterized in that The calculation formula for the harm degree of the harmful cracks to the bridge is: In the formula, represents the harm degree of the th harmful crack; represents the harmful degree of the th harmful crack; represents the harmful degree of the th harmful crack; represents the number of harmful cracks; represents the distance between the th harmful crack and the th harmful crack; represents the sigmoid function.

10. The concrete crack detection method for bridge engineering according to claim 1, characterized in that The specific method for evaluating the bridge quality by combining the harm degrees of all harmful cracks and the areas of all harmful cracks includes: Based on the harm degrees of all harmful cracks and the areas of all harmful cracks, obtain the bridge quality. The specific calculation formula is: In the formula, represents the bridge quality; represents the number of harmful cracks; represents the hazard degree of the represents the area of the represents the exponential function with the natural constant as the base.

Images