A bridge pier rigidity detection method and system

Abstract

The present invention provides a method and system for detecting the rigidity of bridge piers, and relates to the technical field of bridge pier detection. The method comprises: setting a sample point to be measured, and obtaining the center position of the area to be measured; setting the preset horizontal distance of the center position as the hovering position of a drone, so that the laser emitted by the laser rangefinder provided on the drone is irradiated onto the sample point to be measured, and determining the measurement distance measured by the laser rangefinder, as well as the pitch angle and yaw angle of the laser rangefinder when measuring multiple sample points to be measured; determining the rigidity drop coefficient; obtaining the image to be measured of the area to be measured; determining the rigidity risk coefficient; and determining the rigidity detection result. According to the present invention, non-contact detection is performed by using a drone equipped with a laser rangefinder, and there is no need to install equipment on the bridge pier, thereby improving the efficiency and safety of rigidity detection, and comprehensively evaluating the rigidity of the bridge pier from two dimensions: geometric deformation and surface cracks, thereby improving the comprehensiveness and accuracy of rigidity detection.

Description

Technical Field

[0001] The present invention relates to the technical field of bridge pier detection, and in particular to a bridge pier rigidity detection method and system. Background Art

[0002] Although current technologies can detect quality issues on bridge piers, installing equipment on them may cause potential interference to the pier structure and does not consider the risk of pier rigidity degradation. In other words, it is impossible to comprehensively evaluate pier rigidity from the two dimensions of geometric deformation and surface cracks.

[0003] The information disclosed in the background technology section of this application is only intended to deepen the understanding of the general background technology of this application, and should not be regarded as an admission or any form of suggestion that the information constitutes the prior art already known to those skilled in the art. Summary of the Invention

[0004] The present invention provides a bridge pier rigidity detection method and system, which can solve the technical problems that related technologies require equipment to be installed on the bridge pier and cannot comprehensively evaluate the rigidity of the bridge pier from the two dimensions of geometric deformation and surface cracks.

[0005] According to a first aspect of the present invention, a bridge pier rigidity detection method is provided, comprising: setting the side of a bridge pier to be detected as four areas to be detected, setting a plurality of sample points to be detected in the areas to be detected, and obtaining the center position of the areas to be detected; setting a preset horizontal distance from the center position as a hovering position of an unmanned aerial vehicle (UAV), irradiating the sample points to be detected with a laser emitted by a laser rangefinder provided on the UAV at multiple moments in a current detection cycle, and determining the measured distances of the multiple sample points to be detected measured by the laser rangefinder, as well as the pitch angle and yaw angle of the laser rangefinder when measuring the multiple sample points to be detected; determining a rigidity reduction coefficient based on the measured distances, the pitch angle, the yaw angle, and the preset horizontal distance; obtaining images of the areas to be detected at the start and end of the current detection cycle; determining a rigidity risk coefficient based on the images to be detected; and determining a rigidity detection result of the bridge pier to be detected in the current detection cycle based on the rigidity reduction coefficient and the rigidity risk coefficient.

[0006] Furthermore, the number of the sample points to be tested in each area to be tested is the same, but the positions are randomly distributed.

[0007] Furthermore, a rigidity reduction coefficient is determined based on the measured distance, the pitch angle, the yaw angle and the preset horizontal distance, including: establishing a coordinate system of the sample point to be measured with the hovering position of the UAV as the origin, the orientation of the laser rangefinder when the pitch angle is 0° and the yaw angle is 90° as the X-axis, the orientation of the laser rangefinder when the pitch angle and yaw angle are both 0° as the Y-axis, and the vertical direction as the Z-axis; obtaining the center position coordinates of the center position in the coordinate system of the sample point to be measured based on the preset horizontal distance; determining the position vectors of multiple sample points to be measured in multiple areas to be measured at multiple moments in the current detection cycle based on the measured distance, the pitch angle, the yaw angle and the center position coordinates; and determining the rigidity reduction coefficient based on the position vectors to be measured.

[0008] Further, according to the measured distance, the pitch angle, the yaw angle and the center position coordinates, determining the position vectors of the plurality of test points in the plurality of test areas at the plurality of moments in the current detection cycle, including: according to the formula , , determine the position vector of the jth sample point to be tested in the i-th test area at the k-th moment of the current detection cycle ,in, is the measured distance of the jth sample point in the i-th test area at the k-th moment of the current detection cycle, is the pitch angle of the jth sample point to be tested in the i-th test area at the k-th moment of the current detection cycle. The unit of the pitch angle is degree. is the yaw angle of the jth sample point to be tested in the i-th test area at the k-th moment of the current detection cycle. The unit of the yaw angle is degree. is the coordinate of the jth sample point to be tested in the i-th test area at the k-th moment of the current detection cycle, is the preset horizontal distance, are the center position coordinates, and i, j and k are all positive integers.

[0009] Furthermore, determining the rigidity reduction coefficient according to the position vector to be measured includes: obtaining the width and height of the pier to be measured; and determining the rigidity reduction coefficient according to the position vector to be measured, the width, and the height.

[0010] Further, determining the rigidity reduction coefficient according to the position vector to be measured, the width and the height includes: according to the formula , , , determine the rigidity reduction coefficient G, where is the cosine similarity between the position vector of the jth sample point to be tested in the i-th test area at the k-th moment of the current detection cycle and the position vector of the jth sample point to be tested in the i-th test area at the k-1-th moment of the current detection cycle, is the position vector of the jth sample point to be tested in the i-th test area at the k-1th moment of the current detection cycle, is the cosine similarity between the position vector of the jth sample point to be tested in the ith test area at the k+1th moment of the current detection cycle and the position vector of the jth sample point to be tested in the ith test area at the kth moment of the current detection cycle, is the position vector of the jth sample point to be tested in the i-th test area at the k+1th moment in the current detection cycle, is the horizontal coordinate of the measured position coordinate of the jth measured sample point in the i-th measured area at the k-th moment of the current detection cycle, H is the height of the bridge pier to be measured, W is the width of the bridge pier to be measured, 4 is the number of measured areas, N is the number of measured sample points in each measured area, M is the number of detection cycle moments, i≤4, j≤N, k≤M, and i, j, k, N and M are all positive integers, and if is a conditional function.

[0011] Furthermore, a rigid risk coefficient is determined based on the image to be tested, including: in the image to be tested, identifying whether there is a crack in the area to be tested through an image detection model; if there is a crack in the area to be tested, determining the target area to be tested where the crack exists; performing crack feature extraction processing on the image to be tested of the target area to be tested at the start moment of the current detection cycle through a trained image recognition neural network model to obtain a starting target area to be tested feature vector; performing crack feature extraction processing on the image to be tested of the target area to be tested at the end moment of the current detection cycle through a trained image recognition neural network model to obtain an ending target area to be tested feature vector; determining a rigid risk coefficient based on the starting target area to be tested feature vector and the ending target area to be tested feature vector; if there is no crack in the area to be tested, determining the rigid risk coefficient to be 0.

[0012] Further, according to the feature vector of the starting target area to be measured and the feature vector of the ending target area to be measured, a rigid risk coefficient is determined, including: according to the formula , determine the rigid risk factor F, where is the starting target area feature vector of the sth target area to be tested, is the ending target region feature vector of the sth target region to be tested, n is the number of target regions to be tested, s≤n, and both s and n are positive integers.

[0013] Furthermore, based on the rigidity drop coefficient and the rigidity risk coefficient, the rigidity detection result of the bridge pier to be measured in the current detection period is determined, including: if the rigidity risk coefficient is greater than or equal to the set rigidity risk coefficient threshold, then the rigidity detection result of the bridge pier to be measured in the current detection period is determined to be severely rigidity degraded, and the pier structure is dangerous; if the rigidity drop coefficient is greater than or equal to the set rigidity drop coefficient threshold, and the rigidity risk coefficient is less than the set rigidity risk coefficient threshold, then the rigidity detection result of the bridge pier to be measured in the current detection period is determined to be severely rigidity degraded, and the pier structure is dangerous; if the rigidity drop coefficient is less than the set rigidity drop coefficient threshold, and the rigidity risk coefficient is less than the set rigidity risk coefficient threshold, then the rigidity detection result of the bridge pier to be measured in the current detection period is determined to be normal rigidity, and the pier structure is safe.

[0014] According to a second aspect of the present invention, a bridge pier rigidity detection system is provided, comprising: a sample point and center position module for setting the side of the bridge pier to be measured as four test areas, setting multiple sample points to be measured in the test areas, and obtaining the center position of the test areas; a distance, pitch angle, and yaw angle measurement module for setting a preset horizontal distance from the center position as a drone hovering position, causing a laser rangefinder provided on the drone to emit laser light onto the sample points to be measured at multiple times during the current detection cycle, and determining the measured distances of the multiple sample points to be measured as measured by the laser rangefinder. , and the pitch angle and yaw angle of the laser rangefinder when measuring multiple sample points to be measured; a rigidity drop coefficient module, used to determine the rigidity drop coefficient according to the measured distance, the pitch angle, the yaw angle and the preset horizontal distance; a test image module, used to obtain the test image of the test area at the start time and the end time of the current detection cycle respectively; a rigidity risk coefficient module, used to determine the rigidity risk coefficient according to the test image; a rigidity detection result module, used to determine the rigidity detection result of the bridge pier to be measured in the current detection cycle according to the rigidity drop coefficient and the rigidity risk coefficient.

[0015] Technical Effect: According to the present invention, non-contact inspection is performed by using a laser rangefinder mounted on a drone, eliminating the need to install equipment on the piers, reducing potential interference with the pier structure, and improving the efficiency and safety of rigidity testing. By measuring distance, pitch angle, yaw angle, and preset horizontal distance, the three-dimensional coordinates of the test points of the pier to be tested can be accurately calculated, reflecting the local deformation of the pier to be tested. Furthermore, by combining the rigidity reduction coefficient and the rigidity risk coefficient, the rigidity of the pier is comprehensively evaluated from the two dimensions of geometric deformation and surface damage, improving the comprehensiveness and accuracy of rigidity testing and enabling large-scale pier screening and long-term rigidity testing. When determining the test position vectors of multiple test points in multiple test areas at multiple times in the current detection cycle, the test position vectors of multiple test points in multiple test areas at multiple times in the current detection cycle can be determined based on the test position coordinates and the center position coordinates. The test position vectors achieve a unified measurement benchmark, reducing errors caused by fluctuations in the drone's hovering position. By comparing the changes in the test position vectors for multiple measurements of the same test point at different times, the temporal pattern of rigidity degradation can be quantified. When determining the rigidity reduction coefficient, the relative difference in cosine similarity of the position vectors to be tested at adjacent moments can be used as a weight. The weight is also set based on the characteristic that the closer the position vector to the horizontal direction is to the deformation, the more dangerous it is. Furthermore, the weight is set based on the characteristic that the farther the test point is from the center position, the stronger the deformation representation ability is. Thus, the relative difference in cosine similarity of the position vectors to be tested at multiple adjacent moments in the current test cycle for multiple test points in multiple test areas can be weighted and averaged to obtain the rigidity reduction coefficient, thereby improving the accuracy of identifying the degree of rigidity reduction. When determining the rigidity risk coefficient, the rigidity risk coefficient can be determined by the similarity between the feature vectors of the starting target test area and the feature vectors of the ending target test area. This allows the degree of change in the crack characteristics within the test cycle to be quantified, the degree of danger of the bridge pier structure to be tested to be determined, and the reliability of the rigidity risk coefficient to be improved.

[0016] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and not limiting of the present invention. Other features and aspects of the present invention will become more apparent from the following detailed description of exemplary embodiments with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can derive other embodiments based on these drawings without inventive efforts.

[0018] Figure 1 A schematic flow chart of a bridge pier rigidity detection method according to an embodiment of the present invention is exemplarily shown;

[0019] Figure 2 A flowchart of calculating a rigidity reduction coefficient according to an embodiment of the present invention is exemplarily shown;

[0020] Figure 3 A flowchart of calculating a rigid risk coefficient according to an embodiment of the present invention is exemplarily shown;

[0021] Figure 4 The following is a flowchart of determining a rigidity detection result according to an embodiment of the present invention;

[0022] Figure 5 A block diagram of a bridge pier rigidity detection system according to an embodiment of the present invention is exemplarily shown. DETAILED DESCRIPTION

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0024] The following specific embodiments are used to describe the technical solution of the present invention in detail. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0025] Figure 1 A flow chart of a bridge pier rigidity detection method according to an embodiment of the present invention is exemplarily shown, the method comprising: step S1, setting the side of the bridge pier to be detected as four areas to be detected, setting a plurality of sample points to be detected in the areas to be detected, and obtaining the center position of the areas to be detected; step S2, setting a preset horizontal distance from the center position as the hovering position of an unmanned aerial vehicle, irradiating the sample points to be detected with laser light emitted by a laser rangefinder provided on the unmanned aerial vehicle at multiple moments in the current detection cycle, and determining the measured distances of the multiple sample points to be detected measured by the laser rangefinder, as well as the pitch angle and yaw angle of the laser rangefinder when measuring the multiple sample points to be detected; step S3, determining a rigidity reduction coefficient based on the measured distances, the pitch angle, the yaw angle, and the preset horizontal distance; step S4, obtaining images of the areas to be detected at the start and end of the current detection cycle; step S5, determining a rigidity risk coefficient based on the images to be detected; and step S6, determining a rigidity detection result of the bridge pier to be detected in the current detection cycle based on the rigidity reduction coefficient and the rigidity risk coefficient.

[0026] The bridge pier rigidity testing method according to an embodiment of the present invention utilizes a laser rangefinder mounted on an unmanned aerial vehicle for non-contact testing. This eliminates the need for equipment installation on the pier, reduces potential interference with the pier structure, and improves the efficiency and safety of rigidity testing. By measuring distance, pitch angle, yaw angle, and preset horizontal distance, the three-dimensional coordinates of the test points on the pier can be accurately calculated, reflecting the local deformation of the pier. Furthermore, the rigidity reduction coefficient and rigidity risk coefficient are combined to comprehensively assess pier rigidity from two perspectives: geometric deformation and surface damage. This improves the comprehensiveness and accuracy of rigidity testing and enables large-scale pier screening and long-term rigidity testing.

[0027] According to one embodiment of the present invention, in step S1, a pier to be measured may be selected based on its age. The side surfaces of the pier to be measured are then configured as four measurement areas. The configuration may be determined based on the cross-sectional geometry of the pier to be measured. If the cross-section of the pier to be measured is rectangular, the four rectangular side surfaces of the pier to be measured are directly configured as the four measurement areas. If the cross-section of the pier to be measured is circular, the side surfaces of the pier to be measured are evenly divided into four measurement areas along the circumference (e.g., at intervals of 0°-90°, 90°-180°, 180°-270°, and 270°-360°). For each measurement area, its center is determined using geometric calculations or measurement tools (e.g., a total station or laser rangefinder). The center is defined as the centroid of the area's geometry (e.g., the intersection of the diagonals of the rectangular area).

[0028] According to an embodiment of the present invention, step S1 includes: the number of the sample points to be tested in each area to be tested is the same, but the positions are randomly distributed.

[0029] According to one embodiment of the present invention, in step S2, a drone hovering position is set at a preset horizontal distance (e.g., 2.5 meters) from the center position (at the same height as the center position and directly opposite the center position). Specifically, a line is drawn connecting the centroid (e.g., the center of the circle) of the cross section of the bridge pier to be measured at the height of the centroid of the measured area and the centroid of the measured area, with the drone hovering position located on the extension of this line. Consequently, there are four drone hovering positions, allowing the laser emitted by the drone's laser rangefinder to illuminate all sample points to be measured, reducing manual operations, labor costs, and safety risks. The interval between adjacent time points can be set to 3 days, 7 days, etc., and each measurement cycle can be set to 24 hours, 1 month, etc., although this is not limited by the present invention. While the drone is hovering for measurement, the laser rangefinder rotates up, down, left, and right to ensure that the emitted laser accurately illuminates the sample points to be measured, thereby determining the measured distance, pitch angle, and yaw angle of the laser rangefinder at that time. The pitch angle is used to describe the angle at which the laser rangefinder rotates upward or downward, and the yaw angle is used to describe the angle at which the laser rangefinder rotates left or right.

[0030] According to an embodiment of the present invention, in step S3, a rigidity reduction coefficient is determined according to the measured distance, the pitch angle, the yaw angle, and the preset horizontal distance.

[0031] Figure 2 The flowchart of calculating the rigidity reduction coefficient according to an embodiment of the present invention is exemplarily shown.

[0032] According to one embodiment of the present invention, step S3 includes: step S31, establishing a coordinate system of the sample point to be measured with the hovering position of the drone as the origin, the orientation of the laser rangefinder when the pitch angle is 0° and the yaw angle is 90° as the X-axis, the orientation of the laser rangefinder when the pitch angle and yaw angle are both 0° as the Y-axis, and the vertical direction as the Z-axis; step S32, obtaining the center position coordinates of the center position in the coordinate system of the sample point to be measured based on the preset horizontal distance; step S33, determining the position vectors of multiple sample points to be measured in multiple areas to be measured at multiple moments in the current detection cycle based on the measured distance, the pitch angle, the yaw angle and the center position coordinates; step S34, determining the rigidity reduction coefficient based on the position vector to be measured.

[0033] According to one embodiment of the present invention, four coordinate systems for the sample points to be measured are established with the four drone hovering positions (i.e., at preset horizontal distances from the four center positions) as the origins, without interfering with each other. The X-axis of the coordinate system for the sample points to be measured is oriented in the direction where the laser rangefinder's pitch angle is 0° and its yaw angle is 90° (90° to the right), the Y-axis is oriented in the direction where the laser rangefinder's pitch angle is 0° (no deviation up or down) and its yaw angle is 0° (no deviation left or right), and the Z-axis is vertically upward. When the laser rangefinder's pitch angle is 0° and its yaw angle is 0°, the emitted laser is directly aimed at the center position. The center position coordinates are the same in each coordinate system for the sample points to be measured.

[0034] According to one embodiment of the present invention, based on the measured distance, the pitch angle, the yaw angle and the center position coordinates, determining the position vectors of the plurality of test points in the plurality of test areas at the plurality of moments in the current detection cycle includes: determining the position vector of the jth test point in the i-th test area at the kth moment in the current detection cycle according to formulas (1) and (2): ,

[0035] (1),

[0036] (2),

[0037] in, is the measured distance of the jth sample point in the i-th test area at the k-th moment of the current detection cycle, is the pitch angle of the jth sample point to be tested in the i-th test area at the k-th moment of the current detection cycle. The unit of the pitch angle is degree. is the yaw angle of the jth sample point to be tested in the i-th test area at the k-th moment of the current detection cycle. The unit of the yaw angle is degree. is the coordinate of the jth sample point to be tested in the i-th test area at the k-th moment of the current detection cycle, is the preset horizontal distance, are the center position coordinates, and i, j and k are all positive integers.

[0038] According to one embodiment of the present invention, in formula (1), the laser rangefinder is at the origin of the coordinate system of the sample point to be measured, and the distance from the origin to the sample point to be measured is the measurement distance of the laser rangefinder. is the projection length of the jth sample point to be tested in the ith test area at the kth moment in the current detection cycle in the X-axis direction in the coordinate system of the sample point to be tested, that is, the coordinate value of the jth sample point to be tested in the ith test area at the kth moment in the current detection cycle on the X-axis. is the projection length of the jth sample point to be tested in the i-th test area in the Y-axis direction in the coordinate system of the sample point to be tested at the k-th moment in the current detection cycle, that is, the coordinate value of the jth sample point to be tested in the i-th test area on the Y-axis at the k-th moment in the current detection cycle. is the projection length of the jth sample point to be tested in the i-th test area at the k-th moment of the current detection cycle in the Z-axis direction of the coordinate system of the sample point to be tested, that is, the coordinate value of the jth sample point to be tested in the i-th test area at the k-th moment of the current detection cycle on the Z-axis. The above three coordinate values ​​can be used to obtain the coordinates of the test position of the jth sample point to be tested in the i-th test area at the k-th moment of the current detection cycle. In formula (2), the preset horizontal distance of the center position is taken as the origin, and when the pitch angle of the laser rangefinder is 0° and the yaw angle is 0°, the emitted laser is facing the center position, so, is the center position coordinate. When the coordinates of the jth sample point to be tested in the i-th test area at the k-th moment of the current detection cycle are subtracted from the center position coordinates, that is, the vector pointing from the center position coordinates to the coordinates of the jth sample point to be tested in the i-th test area at the k-th moment of the current detection cycle can be obtained.

[0039] In this way, based on the coordinates of the position to be measured and the coordinates of the center position, the position vectors of multiple test points in multiple test areas at multiple times in the current detection cycle can be determined. The position vectors to be measured achieve the unification of the measurement benchmark and reduce the error caused by the fluctuation of the drone's hovering position. By comparing the changes in the position vectors to be measured for multiple measurements of the same test point at different times, the time course of rigid degradation can be quantified.

[0040] According to one embodiment of the present invention, step S34 includes: step S341, obtaining the width and height of the bridge pier to be measured; step S342, determining the rigidity reduction coefficient according to the position vector to be measured, the width and the height.

[0041] According to one embodiment of the present invention, the width and height of the bridge pier to be measured are obtained through the construction drawings of the bridge pier to be measured, and the rigidity reduction coefficient is determined through the position vector to be measured, the width and the height.

[0042] According to one embodiment of the present invention, determining the rigidity reduction coefficient according to the position vector to be measured, the width and the height includes: determining the rigidity reduction coefficient G according to formulas (3), (4) and (5),

[0043] (3),

[0044] (4),

[0045] (5),

[0046] in, is the cosine similarity between the position vector of the jth sample point to be tested in the i-th test area at the k-th moment of the current detection cycle and the position vector of the jth sample point to be tested in the i-th test area at the k-1-th moment of the current detection cycle, is the position vector of the jth sample point to be tested in the i-th test area at the k-1th moment of the current detection cycle, is the cosine similarity between the position vector of the jth sample point to be tested in the ith test area at the k+1th moment of the current detection cycle and the position vector of the jth sample point to be tested in the ith test area at the kth moment of the current detection cycle, is the position vector of the jth sample point to be tested in the i-th test area at the k+1th moment in the current detection cycle, is the horizontal coordinate of the measured position coordinate of the jth measured sample point in the i-th measured area at the k-th moment of the current detection cycle, H is the height of the bridge pier to be measured, W is the width of the bridge pier to be measured, 4 is the number of measured areas, N is the number of measured sample points in each measured area, M is the number of detection cycle moments, i≤4, j≤N, k≤M, and i, j, k, N and M are all positive integers, and if is a conditional function.

[0047] According to one embodiment of the present invention, in formula (3), is the cosine similarity between the position vector of the jth sample point to be tested in the i-th test area at the k-th moment of the current detection cycle and the position vector of the jth sample point to be tested in the i-th test area at the k-1-th moment of the current detection cycle. The closer the cosine similarity is to 1, the more similar the position vectors of the sample point to be tested at the k-1-th moment and the k-th moment of the current detection cycle are, that is, the smaller the displacement of the sample point to be tested is between the k-1-th moment and the k-th moment of the current detection cycle. Similarly, in formula (4), is the cosine similarity between the position vector of the jth sample point to be tested in the i-th test area at the k+1th moment of the current detection cycle and the position vector of the jth sample point to be tested in the i-th test area at the kth moment of the current detection cycle. The closer the cosine similarity is to 1, the more similar the position vectors of the sample point to be tested at the kth moment and the k+1th moment of the current detection cycle are, that is, the smaller the displacement of the sample point to be tested is between the kth moment and the k+1th moment of the current detection cycle. In formula (5), It is the relative difference between the cosine similarity of the position vector of the sample point to be tested at the k-1th moment and the kth moment of the current detection cycle, and the cosine similarity of the position vector of the sample point to be tested at the kth moment and the k+1th moment of the current detection cycle. The larger the relative difference, the greater the change in the displacement of the sample point to be tested during the adjacent interval time of the current detection cycle, that is, the greater the degree of decrease in the rigidity of the bridge pier to be tested. is the minimum angle between the position vector to be measured and the vertical direction (i.e., the Z axis). For example, if the position vector to be measured points to the positive direction of the Z axis (e.g., the sample point at the top of the bridge pier), the minimum angle is the angle between the position vector to be measured and the positive direction of the Z axis. If the position vector to be measured points to the negative direction of the Z axis (e.g., the sample point at the bottom of the bridge pier), the minimum angle is the angle between the position vector to be measured and the negative direction of the Z axis. is the minimum angle with The ratio between the two is because bridge design can usually tolerate slight vertical settlement, but horizontal displacement will directly change the force path of the structure, leading to overturning or shear failure. Therefore, the larger the ratio, the larger the minimum angle between the measured position vector and the Z axis (the closer the measured position vector is to the horizontal direction), indicating that the measured pier is more susceptible to damage when the measured position vector changes. That is, the more dangerous the deformation of the measured pier in this direction is, the greater the degree of decrease in the rigidity of the measured pier is, and therefore, the higher its weight. When the height of the bridge pier to be measured is greater than or equal to the width of the bridge pier to be measured, the conditional function value is the height of the bridge pier to be measured; otherwise, the conditional function value is the width of the bridge pier to be measured. It is the ratio between the modulus of the position vector to be measured and the corresponding condition function. The larger the ratio, the larger the modulus of the position vector to be measured, indicating that the farther the sample point to be measured is from the center position, the more accurate the measurement result of the position vector to be measured. When the position vector to be measured changes, the stronger the ability of the measurement result to represent the overall deformation of the pier, that is, the position change of the sample point to be measured far away from the center position of the pier can better reflect the overall deformation trend of the pier, and therefore, it is given a higher weight. and The relative differences of the cosine similarities of the position vectors of multiple test points in multiple test areas at multiple adjacent moments in the current detection cycle are multiplied by corresponding weights and then averaged to obtain the rigidity reduction coefficient. The larger the rigidity reduction coefficient is, the greater the degree of rigidity reduction of the test pier is, that is, the more serious the rigidity degradation is.

[0048] In this way, weights can be set based on the relative difference in cosine similarity of the position vectors to be measured at adjacent moments, and based on the characteristic that the closer the position vector to be measured is to the horizontal direction, the more dangerous the deformation is, and the characteristic that the farther the sample point to be measured is from the center position, the stronger the deformation representation ability is. In this way, the relative difference in cosine similarity of the position vectors to be measured at multiple adjacent moments in the current detection cycle of multiple sample points to be measured in multiple areas to be measured is weighted and averaged to obtain the rigidity reduction coefficient, thereby improving the accuracy of identifying the degree of rigidity reduction.

[0049] According to one embodiment of the present invention, in step S4, images of the area to be tested at the start and end of the current detection cycle are collected by an image acquisition device, for example, a camera mounted on a drone, and the images of the area to be tested at the start and end of the current detection cycle are compared to analyze the changes in the surface cracks of the pier to be tested.

[0050] According to an embodiment of the present invention, in step S5, a rigid risk coefficient is determined based on the image to be tested.

[0051] Figure 3 The flowchart of calculating the rigid risk coefficient according to an embodiment of the present invention is exemplarily shown.

[0052] According to one embodiment of the present invention, step S5 includes: step S51, in the image to be tested, identifying whether there is a crack in the area to be tested through an image detection model; step S52, if there is a crack in the area to be tested, determining the target area to be tested where the crack exists; step S53, using a trained image recognition neural network model to perform crack feature extraction processing on the image to be tested of the target area to be tested at the start time of the current detection cycle, and obtaining a starting target area to be tested feature vector; step S54, using a trained image recognition neural network model to perform crack feature extraction processing on the image to be tested of the target area to be tested at the end time of the current detection cycle, and obtaining an ending target area to be tested feature vector; step S55, determining a rigid risk coefficient based on the starting target area to be tested feature vector and the ending target area to be tested feature vector; step S56, if there is no crack in the area to be tested, determining the rigid risk coefficient to be 0.

[0053] According to one embodiment of the present invention, the image detection model is a deep learning model (e.g., a convolutional neural network model). The image detection model is trained using historical data to enable the image detection model to identify whether cracks exist in the image to be tested. If the image detection model detects crack features (e.g., linear structures, edge discontinuities, etc.) in any image to be tested, the area to be tested is marked as a target area to be tested. If no cracks are detected, the rigidity risk coefficient is determined to be 0, indicating that the bridge pier structure to be tested is safe. The image recognition neural network model can be a convolutional neural network model capable of extracting features such as crack morphology, length, and width. Crack feature extraction processing is performed on the image to be tested of the target area to be tested at the beginning of the current detection cycle to obtain a starting target area feature vector. Crack feature extraction processing is performed on the image to be tested of the target area to be tested at the end of the current detection cycle to obtain a ending target area feature vector. The starting target area feature vector and the ending target area feature vector are compared to determine the rigidity risk coefficient.

[0054] According to one embodiment of the present invention, determining a rigid risk coefficient according to the feature vector of the starting target area to be measured and the feature vector of the ending target area to be measured includes: determining the rigid risk coefficient F according to formula (6),

[0055] (6),

[0056] in, is the starting target area feature vector of the sth target area to be tested, is the ending target region feature vector of the sth target region to be tested, n is the number of target regions to be tested, s≤n, and both s and n are positive integers.

[0057] According to one embodiment of the present invention, in formula (6), It is the similarity between the feature vector of the starting target area to be tested of the sth target area to be tested and the feature vector of the ending target area to be tested of the sth target area to be tested. The greater the similarity, the more similar the cracks of the target area to be tested at the beginning and end of the current detection cycle are, that is, the structure of the target area to be tested is stable. To average the similarities between the feature vectors of the starting target region to be tested and the feature vectors of the ending target region to be tested of multiple target regions to be tested, subtract 1 from , a rigidity risk coefficient can be obtained. The larger the rigidity risk coefficient is, the more unstable the structure of the target area to be tested is, that is, the more serious the rigidity degradation of the bridge pier to be tested is, and the more dangerous the bridge pier structure to be tested is.

[0058] In this way, the rigidity risk coefficient can be determined by the similarity between the feature vector of the starting target area to be tested and the feature vector of the ending target area to be tested, thereby quantifying the degree of change of the crack characteristics within the detection cycle, judging the degree of danger of the pier structure to be tested, and improving the reliability of the rigidity risk coefficient.

[0059] According to one embodiment of the present invention, in step S6, the rigidity detection result of the bridge pier to be detected in the current detection period is determined based on the rigidity reduction coefficient and the rigidity risk coefficient.

[0060] Figure 4 A flowchart for determining a rigidity detection result according to an embodiment of the present invention is exemplarily shown.

[0061] According to one embodiment of the present invention, step S6 includes: step S61, if the rigidity risk coefficient is greater than or equal to the set rigidity risk coefficient threshold, determining that the rigidity detection result of the bridge pier to be measured in the current detection period is rigidity severely degraded, and the pier structure is dangerous; step S62, if the rigidity reduction coefficient is greater than or equal to the set rigidity reduction coefficient threshold, and the rigidity risk coefficient is less than the set rigidity risk coefficient threshold, determining that the rigidity detection result of the bridge pier to be measured in the current detection period is rigidity severely degraded, and the pier structure is dangerous; step S63, if the rigidity reduction coefficient is less than the set rigidity reduction coefficient threshold, and the rigidity risk coefficient is less than the set rigidity risk coefficient threshold, determining that the rigidity detection result of the bridge pier to be measured in the current detection period is rigidity normal, and the pier structure is safe.

[0062] According to one embodiment of the present invention, if the rigidity risk coefficient is greater than or equal to a set rigidity risk coefficient threshold (e.g., 0.6), regardless of the rigidity risk coefficient, the rigidity test result for the bridge pier to be tested during the current testing period is determined to be severely degraded, and the pier structure is dangerous, requiring immediate maintenance measures, such as immediate traffic closure and initiation of emergency reinforcement procedures. If the rigidity degradation coefficient is greater than or equal to a set rigidity degradation coefficient threshold (e.g., 0.7), and the rigidity risk coefficient is less than the set rigidity risk coefficient threshold, the rigidity test result for the bridge pier to be tested during the current testing period is determined to be severely degraded, and the pier structure is dangerous, requiring immediate maintenance measures. If the rigidity degradation coefficient is less than the set rigidity degradation coefficient threshold, and the rigidity risk coefficient is less than the set rigidity risk coefficient threshold, the rigidity test result for the bridge pier to be tested during the current testing period is determined to be normal, and the pier structure is safe, allowing regular monitoring to continue without requiring maintenance measures.

[0063] According to an embodiment of the present invention, a bridge pier rigidity testing method uses a laser rangefinder mounted on an unmanned aerial vehicle (UAV) for non-contact testing. This eliminates the need for equipment installed on the pier, reduces potential interference with the pier structure, and improves the efficiency and safety of rigidity testing. By measuring distance, pitch angle, yaw angle, and a preset horizontal distance, the three-dimensional coordinates of the test points of the pier can be accurately calculated, reflecting the local deformation of the pier. Furthermore, by integrating the rigidity degradation coefficient and the rigidity risk coefficient, the rigidity of the pier is comprehensively assessed from the two dimensions of geometric deformation and surface damage. This improves the comprehensiveness and accuracy of rigidity testing and enables large-scale pier screening and long-term rigidity testing. When determining the test position vectors of multiple test points in multiple test areas at multiple times during the current testing cycle, the test position vectors of multiple test points in multiple test areas at multiple times during the current testing cycle can be determined based on the test position coordinates and the center position coordinates. This unifies the measurement benchmark for the test position vectors, reduces errors caused by fluctuations in the drone's hovering position, and quantifies the temporal pattern of rigidity degradation by comparing the changes in the test position vectors for the same test point at different times. When determining the rigidity reduction coefficient, the relative difference in cosine similarity of the position vectors to be tested at adjacent moments can be used as a weight. The weight is also set based on the characteristic that the closer the position vector to the horizontal direction is to the deformation, the more dangerous it is. Furthermore, the weight is set based on the characteristic that the farther the test point is from the center position, the stronger the deformation representation ability is. Thus, the relative difference in cosine similarity of the position vectors to be tested at multiple adjacent moments in the current test cycle for multiple test points in multiple test areas can be weighted and averaged to obtain the rigidity reduction coefficient, thereby improving the accuracy of identifying the degree of rigidity reduction. When determining the rigidity risk coefficient, the rigidity risk coefficient can be determined by the similarity between the feature vectors of the starting target test area and the feature vectors of the ending target test area. This allows the degree of change in the crack characteristics within the test cycle to be quantified, the degree of danger of the bridge pier structure to be tested to be determined, and the reliability of the rigidity risk coefficient to be improved.

[0064] Figure 5 A block diagram of a bridge pier rigidity detection system according to an embodiment of the present invention is exemplarily shown. The system includes: a sample point and center position module for setting the side of the bridge pier to be measured as four test areas, setting multiple sample points to be measured in the test areas, and obtaining the center position of the test areas; a distance, pitch angle, and yaw angle measurement module for setting a preset horizontal distance from the center position as the hovering position of the drone, irradiating the laser emitted by the laser rangefinder provided on the drone at multiple moments in the current detection cycle onto the sample points to be measured, and determining the distances of the multiple sample points to be measured measured by the laser rangefinder. Measuring distance, as well as the pitch angle and yaw angle of the laser rangefinder when measuring multiple sample points to be measured; a rigidity drop coefficient module, used to determine the rigidity drop coefficient based on the measured distance, the pitch angle, the yaw angle and the preset horizontal distance; a test image module, used to obtain the test image of the test area at the start and end times of the current detection cycle respectively; a rigidity risk coefficient module, used to determine the rigidity risk coefficient based on the test image; a rigidity detection result module, used to determine the rigidity detection result of the bridge pier to be measured in the current detection cycle based on the rigidity drop coefficient and the rigidity risk coefficient.

[0065] The present invention may be a method, an apparatus, a system and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present invention.

[0066] Those skilled in the art will appreciate that the embodiments of the present invention described above and shown in the accompanying drawings are intended to be illustrative only and are not intended to limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and illustrated in the embodiments. Any variations or modifications may be made to the embodiments of the present invention without departing from the principles described.

Claims

1. A bridge pier rigidity detection method, characterized in that: include: The side surfaces of the bridge pier to be measured are set as four test areas, a plurality of test points are set in the test areas, and the center positions of the test areas are obtained; The preset horizontal distance of the center position is set as the hovering position of the drone, and at multiple times in the current detection cycle, the laser emitted by the laser rangefinder provided on the drone is irradiated onto the sample points to be measured, and the measured distances of the multiple sample points to be measured measured by the laser rangefinder, as well as the pitch angle and yaw angle of the laser rangefinder when measuring the multiple sample points to be measured are determined; the rigidity reduction coefficient is determined based on the measured distances, the pitch angle, the yaw angle and the preset horizontal distance; at the start time and the end time of the current detection cycle, images of the area to be measured are respectively obtained; and the rigidity risk coefficient is determined based on the images to be measured; Determining a rigidity test result of the bridge pier to be tested in the current test period according to the rigidity reduction coefficient and the rigidity risk coefficient; Determining a rigidity reduction coefficient according to the measured distance, the pitch angle, the yaw angle, and the preset horizontal distance includes: establishing a coordinate system of a sample point to be measured with the hovering position of the UAV as the origin, the orientation of the laser rangefinder when the pitch angle is 0° and the yaw angle is 90° as the X-axis, the orientation of the laser rangefinder when the pitch angle and the yaw angle are both 0° as the Y-axis, and the vertical direction as the Z-axis; obtaining the center position coordinates of the center position in the coordinate system of the sample point to be measured according to the preset horizontal distance; determining the position vectors of multiple sample points to be measured in multiple areas to be measured at multiple times in a current detection cycle according to the measured distance, the pitch angle, the yaw angle, and the center position coordinates; and determining the rigidity reduction coefficient according to the position vectors to be measured.

2. The bridge pier rigidity detection method according to claim 1, characterized in that: The number of the sample points to be tested in each area to be tested is the same, but the positions are randomly distributed.

3. The bridge pier rigidity detection method according to claim 1, characterized in that: Determine the position vectors of the plurality of test points in the plurality of test areas at the plurality of moments in the current detection cycle according to the measured distance, the pitch angle, the yaw angle and the center position coordinates, including: I i，j，k =(x i，j，k ,y i，j，k ,z i，j,k )-(0,L p ,0)=(x i，j，k ,y i，j，k -L p ,z i，j,k ) Determine the position vector I of the jth sample point to be tested in the i-th test area at the k-th moment of the current detection cycle i,j,k , where L i,j,k is the measured distance of the jth sample point in the i-th test area at the kth moment of the current detection cycle, θ i,j,k is the pitch angle of the jth sample point to be tested in the i-th test area at the k-th moment of the current detection cycle. The unit of the pitch angle is degree. is the yaw angle of the jth sample point to be tested in the i-th test area at the k-th moment of the current detection cycle. The unit of the yaw angle is degree. (x i,j,k ,y i,j,k ,z i,j,k ) is the coordinate of the jth sample point to be tested in the i-th test area at the k-th moment of the current detection cycle, L p is the preset horizontal distance, (0,L p ,0) are the center position coordinates, and i, j and k are all positive integers.

4. The bridge pier rigidity detection method according to claim 3, characterized in that: Determining the rigidity reduction coefficient according to the position vector to be measured includes: obtaining the width and height of the pier to be measured; and determining the rigidity reduction coefficient according to the position vector to be measured, the width, and the height.

5. The bridge pier rigidity detection method according to claim 4, characterized in that: Determining a rigidity reduction coefficient according to the position vector to be measured, the width, and the height includes: determining a rigidity reduction coefficient according to the formula Determine the rigidity reduction coefficient G, where D i,j,k is the cosine similarity between the position vector of the jth sample point to be tested in the i-th test area at the k-th moment of the current detection cycle and the position vector of the jth sample point to be tested in the i-th test area at the k-1-th moment of the current detection cycle, I i,j,k-1 is the position vector of the jth sample point to be tested in the i-th test area at the k-1th moment of the current detection cycle, D i，j，k+1 is the cosine similarity between the position vector of the jth sample point to be tested in the ith test area at the k+1th moment of the current detection cycle and the position vector of the jth sample point to be tested in the ith test area at the kth moment of the current detection cycle, I i，j，k+1 is the position vector of the jth sample point to be tested in the i-th test area at the k+1th moment of the current detection cycle, x i,j,k is the horizontal coordinate of the measured position coordinate of the jth measured sample point in the i-th measured area at the k-th moment of the current detection cycle, H is the height of the bridge pier to be measured, W is the width of the bridge pier to be measured, 4 is the number of measured areas, N is the number of measured sample points in each measured area, M is the number of detection cycle moments, i≤4, j≤N, k≤M, and i, j, k, N and M are all positive integers, and if is a conditional function.

6. The bridge pier rigidity detection method according to claim 1, characterized in that: According to the image to be tested, a rigid risk coefficient is determined, including: in the image to be tested, identifying whether there is a crack in the area to be tested through an image detection model; if there is a crack in the area to be tested, determining the target area to be tested where the crack exists; performing crack feature extraction processing on the image to be tested of the target area to be tested at the start moment of the current detection cycle through a trained image recognition neural network model, and obtaining a starting target area to be tested feature vector; performing crack feature extraction processing on the image to be tested of the target area to be tested at the end moment of the current detection cycle through a trained image recognition neural network model, and obtaining an ending target area to be tested feature vector; determining the rigid risk coefficient based on the starting target area to be tested feature vector and the ending target area to be tested feature vector; if there is no crack in the area to be tested, determining the rigid risk coefficient to be 0.

7. The bridge pier rigidity detection method according to claim 6, characterized in that: Determining a rigid risk coefficient based on the feature vector of the starting target area to be measured and the feature vector of the ending target area to be measured includes: Determine the rigid risk factor F, where B s,1 is the starting target region feature vector of the sth target region to be tested, B s，M is the ending target region feature vector of the sth target region to be tested, n is the number of target regions to be tested, s≤n, and both s and n are positive integers.

8. The bridge pier rigidity detection method according to claim 1, characterized in that: According to the rigidity drop coefficient and the rigidity risk coefficient, the rigidity detection result of the bridge pier to be measured in the current detection period is determined, including: if the rigidity risk coefficient is greater than or equal to the set rigidity risk coefficient threshold, then the rigidity detection result of the bridge pier to be measured in the current detection period is determined to be severely rigidly degraded, and the pier structure is dangerous; if the rigidity drop coefficient is greater than or equal to the set rigidity drop coefficient threshold, and the rigidity risk coefficient is less than the set rigidity risk coefficient threshold, then the rigidity detection result of the bridge pier to be measured in the current detection period is determined to be severely rigidly degraded, and the pier structure is dangerous; if the rigidity drop coefficient is less than the set rigidity drop coefficient threshold, and the rigidity risk coefficient is less than the set rigidity risk coefficient threshold, then the rigidity detection result of the bridge pier to be measured in the current detection period is determined to be normal rigidity, and the pier structure is safe.

9. A bridge pier rigidity detection system, used to perform the bridge pier rigidity detection method according to any one of claims 1 to 8, characterized in that: include: The module for measuring sample points and center positions is used to set the side of the bridge pier to be measured as four areas to be measured, set multiple sample points to be measured in the areas to be measured, and obtain the center position of the areas to be measured. The module for measuring distance, pitch angle, and yaw angle is used to set a preset horizontal distance from the center position as the hovering position of the UAV, irradiate the laser emitted by the laser rangefinder provided on the UAV to the sample points to be measured at multiple times during the current detection cycle, and determine the measured distances of the multiple sample points to be measured measured by the laser rangefinder, as well as the pitch angle and yaw angle of the laser rangefinder when measuring the multiple sample points to be measured. a rigidity reduction coefficient module, configured to determine a rigidity reduction coefficient according to the measured distance, the pitch angle, the yaw angle, and the preset horizontal distance; The image module to be tested is used to obtain the image to be tested of the area to be tested at the start time and the end time of the current detection cycle respectively; A rigid risk coefficient module, configured to determine a rigid risk coefficient based on the image to be tested; The rigidity detection result module is used to determine the rigidity detection result of the bridge pier to be measured in the current detection cycle according to the rigidity reduction coefficient and the rigidity risk coefficient.

Images