A bridge alignment monitoring system and method

Abstract

This application relates to the field of bridge monitoring technology, and discloses a bridge alignment monitoring system and method. The bridge alignment monitoring method first determines the high-incidence areas of bridge defects based on defect identification results, and uses these high-incidence areas as the target areas for bridge alignment monitoring. Then, it uses a laser emitter to automatically match target monitoring points, fitting the bridge alignment of the monitoring point intervals based on the settlement height data of the target monitoring points. In this way, while ensuring that the alignment data accurately reflects the structural deformation state of the defective areas, it avoids the resource waste caused by indiscriminate monitoring of the entire bridge, effectively improving the efficiency, targeting, and reliability of bridge alignment monitoring, and contributing to real-time early warning and scientific management of bridge structural safety.

Description

Technical Field

[0001] This invention relates to the field of bridge monitoring technology, specifically to a bridge alignment monitoring system and a bridge alignment monitoring method. Background Technology

[0002] As a crucial component of transportation infrastructure, the structural safety and operational stability of bridges directly impact traffic safety. Among related technologies, bridge alignment, as a core indicator reflecting structural health, directly reflects the extent to which bridge structural safety is affected by changes in its shape (such as bending deformation). However, existing monitoring methods largely rely on periodic manual measurements (such as total stations and levels), which suffer from low efficiency, poor real-time performance, and difficulty in accurately monitoring areas prone to bridge defects. Therefore, there is an urgent need for a bridge alignment monitoring method that can dynamically trigger defect risks and accurately acquire alignment data for key areas, enabling real-time assessment and risk warning of bridge safety status. Summary of the Invention

[0003] The main objective of this invention is to provide a bridge alignment monitoring system and method, aiming to solve the technical problems of low efficiency, poor real-time performance, and difficulty in accurately monitoring areas with high rates of bridge defects in the prior art.

[0004] To achieve the above objectives, in a first aspect, this application provides a bridge alignment monitoring system, including a memory and a processor. The memory stores executable program code, and the processor is used to call and run the executable program code to implement the following steps of the bridge alignment monitoring method: Obtain the defect index of the target area of ​​the bridge, where the target area is a high-incidence area of ​​defects determined based on the defect identification results, and the defect index is a comprehensive characterization of the risk level caused by defects in the target area; If the defect index is greater than or equal to the index threshold, a bridge alignment monitoring command is triggered. Based on the bridge alignment monitoring instruction, multiple target monitoring points associated with the target area are determined, and the target monitoring points cover the defective areas within the target area; A curve showing the change in the emission angle of the laser emitting device is generated based on the target monitoring point, wherein the laser emitting device is pre-fixed at a preset height position under the bridge; The laser emitting device is controlled to emit lasers sequentially according to the emission angle change curve, and the sinking height value corresponding to each of the multiple target monitoring points is calculated by receiving the laser reflection signal. Data fitting is performed on the subsidence height values ​​corresponding to the multiple target monitoring points to generate the bridge alignment of the monitoring point interval.

[0005] In one possible implementation, when the processor executes the computer-readable instructions, prior to obtaining the defect index of the target area of ​​the bridge, it includes: Obtain the target image data by acquiring the global image data of the bridge; The target image data is subjected to surface defect identification, and the defect area of ​​each candidate region is determined based on the surface defect identification results. The candidate regions are regions that are pre-divided according to the bridge length. The candidate region with the largest cumulative surface defect area is selected as the target region, and the defect area within the target region is defined as the target defect area.

[0006] In one possible implementation, when the processor executes the computer-readable instructions, obtaining the defect index of the bridge target area includes: Local image data of the target defect area is acquired, and an exposure index corresponding to each target defect area is determined based on the local image data. The exposure index is used to characterize the degree of exposure of the reinforcing steel in the target defect area. The pre-trained bridge stress model is invoked, and each of the target defect areas is matched with the bridge stress points under different traffic conditions in the bridge stress model to obtain the matching probability value between each target defect area and the corresponding stress point. The matching probability value is used to characterize the probability that the bridge stress point is located in the target defect area. The defect index of the target area is determined based on the matching probability value and the corresponding exposure index of each target defect area.

[0007] In one possible implementation, when the processor executes the computer-readable instructions, the step of identifying surface defects in the target image data and determining the defect area of ​​each candidate region based on the surface defect identification results includes: Crack identification is performed on target image data containing candidate regions to determine whether each candidate region has a corresponding target connectivity crack. If it is determined that the target connectivity crack does not exist in the candidate region, the defect area corresponding to each candidate region is determined according to the pixel range of the defect area in the candidate region. If it is determined that there is a corresponding target connectivity crack in the candidate region, the explicit defect area is determined according to the pixel range of the defect area in the candidate region, and the implicit defect area is determined according to the contour of the target connectivity crack. The defect area of ​​each candidate region is determined based on the area of ​​the visible defect and the area of ​​the hidden defect.

[0008] In one possible implementation, when the processor executes the computer-readable instructions, determining whether each candidate region has a corresponding target connectivity fracture includes: If one end of a candidate crack is connected to the defect area and the other end is not connected to the defect area, a preset number of feature points are collected along the path direction of the candidate crack. Obtain the normal vector of each feature point, and determine the proportion of feature points corresponding to normal vectors with opposite directions; Candidate cracks with a percentage ratio greater than or equal to a preset ratio are identified as target connected cracks.

[0009] In one possible implementation, when the processor executes the computer-readable instructions, determining the area of ​​the latent defect based on the contour of the target connected crack includes: The end of the target connecting crack that is not connected to the defect area is extended in a predetermined direction so that the target connecting crack forms an enclosed area; The area of ​​the hidden defect is determined based on the pixel range of the region enclosed by the target connected crack.

[0010] In one possible implementation, when the processor executes the computer-readable instructions, determining the exposure index corresponding to each target defect area based on the local image data includes: The local image data is input into a semantic recognition model to obtain the pixel semantic category of each pixel, wherein the pixel semantic category is either steel reinforcement or concrete. The total number of pixels whose semantic category is represented by the rebar is counted, and the exposed area of ​​the rebar is determined based on the total number of pixels and the pixel size. The exposure index is determined based on the exposed area of ​​the reinforcing steel and the area of ​​the target defective area.

[0011] In one possible implementation, when the processor executes the computer-readable instructions, determining the defect index based on the matching probability value and the corresponding exposure index of each target defect region includes: The matching probability value and the corresponding exposure index of each target defect area are input into the risk assessment model to obtain the comprehensive risk characterization value of each target defect area; The defect index of the target area is determined based on the comprehensive risk characterization value of each target defect area.

[0012] In one possible implementation, when the processor executes the computer-readable instructions, the step of calculating the subsidence height value corresponding to each of the plurality of target monitoring points by receiving laser reflection signals includes: Record the laser emission time and the reflected signal reception time, and calculate the laser propagation time difference; Calculate the actual distance from the laser emitter to the target monitoring point based on the laser propagation speed and time difference; Based on the preset height, emission angle, and actual distance of the laser emitting device, the actual elevation of the target monitoring point is calculated using trigonometric functions. The difference between the actual elevation and the design elevation at that point is used to obtain the corresponding settlement height value. The same target monitoring point is measured a preset number of times, and the average value of the sinking height is taken as the final sinking height value.

[0013] Secondly, embodiments of this application also provide a bridge alignment monitoring method, the method comprising: Obtain the defect index of the target area of ​​the bridge, where the target area is a high-incidence area of ​​defects determined based on the defect identification results, and the defect index is a comprehensive characterization of the risk level caused by defects in the target area; If the defect index is greater than or equal to the index threshold, a bridge alignment monitoring command is triggered. Based on the bridge alignment monitoring instruction, multiple target monitoring points associated with the target area are determined, and the target monitoring points cover the defective areas within the target area; A curve showing the change in the emission angle of the laser emitting device is generated based on the target monitoring point, wherein the laser emitting device is pre-fixed at a preset height position under the bridge; The laser emitting device is controlled to emit lasers sequentially according to the emission angle change curve, and the sinking height value corresponding to each of the multiple target monitoring points is calculated by receiving the laser reflection signal. Data fitting is performed on the subsidence height values ​​corresponding to the multiple target monitoring points to generate the bridge alignment of the monitoring point interval.

[0014] Unlike existing technologies, the bridge alignment monitoring method provided in this application first obtains the defect index of the target area of ​​the bridge. The target area is a high-incidence area of ​​defects determined based on the defect identification results, and the defect index comprehensively characterizes the risk level caused by defects in the target area. When the defect index is greater than or equal to the index threshold, a bridge alignment monitoring command is triggered. Then, multiple target monitoring points associated with the target area are determined according to the bridge alignment monitoring command. The target monitoring points cover the defect areas within the target area. Next, a curve of the emission angle change of a laser emitting device is generated based on the target monitoring points. The laser emitting device is pre-fixed at a preset height position under the bridge. The laser emitting device is then controlled to emit lasers sequentially according to the emission angle change curve. The sinking height value corresponding to each of the multiple target monitoring points is calculated by receiving the laser reflection signal. Finally, the sinking height values ​​corresponding to the multiple target monitoring points are fitted to generate the bridge alignment of the measurement point interval. In other words, this application first identifies high-incidence areas of bridge defects based on defect identification results, designating these areas as target regions for bridge alignment monitoring. Then, it uses a laser emitter to automatically match target monitoring points, fitting the bridge alignment within the monitoring point intervals based on the settlement height data of these points. This ensures that the alignment data accurately reflects the structural deformation state of the defective areas, avoiding resource waste caused by indiscriminate monitoring of the entire bridge. It effectively improves the efficiency, targeting, and reliability of bridge alignment monitoring, contributing to real-time early warning and scientific management of bridge structural safety. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0016] Figure 1 This is a flowchart illustrating the bridge alignment monitoring method in some embodiments of this application; Figure 2 This is a schematic diagram of bridge area division in some embodiments of this application; Figure 3 This is a schematic diagram of the state of the target connected crack in some embodiments of this application; Figure 4 This is a flowchart illustrating step S100 of the bridge alignment monitoring method in some embodiments of this application; Figure 5 This is a flowchart illustrating step S500 of the bridge alignment monitoring method in some embodiments of this application; Figure 6This is a schematic diagram of the hardware structure of the bridge alignment monitoring system in some embodiments of this application.

[0017] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0019] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indication will also change accordingly.

[0020] Furthermore, the use of terms such as "first" and "second" in this invention is for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the term "and / or" throughout the text includes three solutions; taking A and / or B as an example, it includes technical solution A, technical solution B, and a technical solution that simultaneously satisfies A and B. Furthermore, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of a person skilled in the art to implement them. When the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by this invention.

[0021] As a crucial component of transportation infrastructure, the structural safety and operational stability of bridges directly impact traffic safety. Among related technologies, bridge alignment, as a core indicator reflecting structural health, directly reflects the extent to which bridge structural safety is affected by changes in its shape (such as bending deformation). However, existing monitoring methods largely rely on periodic manual measurements (such as total stations and levels), which suffer from low efficiency, poor real-time performance, and difficulty in accurately monitoring areas prone to bridge defects. Therefore, there is an urgent need for a bridge alignment monitoring method that can dynamically trigger defect risks and accurately acquire alignment data for key areas, enabling real-time assessment and risk warning of bridge safety status.

[0022] To address the aforementioned technical problems, this application provides a bridge alignment monitoring method. This method can be applied to a bridge alignment monitoring system. The following description uses the execution of this bridge alignment monitoring method within a bridge alignment monitoring system as an example. It should be noted that although the logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order. Please refer to the appendix. Figure 1 The method includes the following steps S100-S600: Step S100: Obtain the defect index of the target area of ​​the bridge. The target area is a high-incidence area of ​​defects determined based on the defect identification results. The defect index is a comprehensive characterization of the risk level caused by defects in the target area. It is understandable that areas of bridges with severe defects face a higher risk of corrosion due to exposed reinforcing steel, and the concrete structure is susceptible to wind erosion, leading to a decrease in structural strength. Therefore, these severely damaged areas need to be designated as key monitoring areas, for example, through bridge alignment monitoring, to keep track of changes in structural condition in real time.

[0023] The target area refers to areas with a high incidence of bridge defects. Specifically, defects refer to the phenomenon that the concrete surface layer has detached or is about to detach from the bridge body; high-incidence areas of defects refer to areas within the region where surface defects are concentrated, which can be manifested as a high density of defects or a large area of ​​single or cumulative defects. The target area can be determined based on the defect identification results. For example, high-definition images of bridges can be obtained through drone aerial photography, and image analysis technology can be used to quantitatively evaluate parameters such as the location, quantity, and area of ​​defects, thereby accurately locating areas with high incidence of defects.

[0024] Among them, the defect index is a comprehensive characterization of the risk level caused by defects in the target area. In other words, the higher the defect index value, the higher the risk level that defects in the target area pose to the overall structural safety of the bridge.

[0025] In one embodiment, before obtaining the defect index of the target area of ​​the bridge, the method includes: obtaining global image data of the bridge to obtain target image data; performing surface defect identification on the target image data, and determining the defect area of ​​each candidate area based on the surface defect identification result, wherein the candidate area is an area pre-divided according to the bridge length; taking the candidate area with the largest cumulative surface defect area as the target area, and defining the defect area within the target area as the target defect area.

[0026] Specifically, the bridge can be pre-divided into multiple candidate areas along its length, and then the area with the largest defect can be selected as the target area for bridge monitoring.

[0027] For example, such as Figure 2The bridge is divided into a first candidate region A1, a second candidate region A2, and a third candidate region A3, wherein the first candidate region A1 and the third candidate region A3 are end regions, and the second candidate region A2 is the middle region.

[0028] Before obtaining the defect index of the target area of ​​the bridge, the target image data is first obtained by acquiring global image data of the bridge using a drone. Global image data refers to state images that can completely cover all key structural surfaces or a specific structural surface of the target bridge, specifically including images of the top surface (bridge deck), bottom surface (lower edge of beams, bottom of piers), or left and right sides of the bridge. Considering that defects on the bridge bottom surface have a more significant impact on structural safety, the bottom surface of the bridge is photographed globally using a drone first, and the target image data used for analysis is finally obtained.

[0029] Then, surface defect identification is performed on the acquired target image data, and the total defect area in each candidate region is calculated based on the identification results. For example, if the identification determines that there are defect locations Q1, Q2, and Q3 in the second candidate region A2, the areas of these three defect locations are summed to obtain the total defect area S2 of the second candidate region A2. Using the same method, the total defect areas of the first candidate region A1 and the third candidate region A3 are summed and recorded as S1 and S3 respectively.

[0030] Finally, the candidate region with the largest total surface defect area is determined as the target region. Taking the case of "S2>S1>S3" as an example, the second candidate region A2 is the target region. Furthermore, the defect locations (Q1, Q2, Q3) identified within the target region (i.e., A2) are defined as the target defect area.

[0031] In this way, by identifying the candidate area with the largest total surface defect area as the target area, we can prioritize the core area in the bridge structure where the defect problems are most concentrated and the potential risk base is the largest, thus anchoring the key direction for subsequent accurate monitoring and risk assessment.

[0032] In one embodiment, the step of identifying surface defects in the target image data and determining the defect area of ​​each candidate region based on the surface defect identification results includes: identifying cracks in the target image data containing candidate regions, and determining whether each candidate region has a corresponding target connected crack; if it is determined that the candidate region does not have the target connected crack, then determining the defect area corresponding to each candidate region based on the pixel range of the defect area within the candidate region; if it is determined that the candidate region has a corresponding target connected crack, then determining the explicit defect area based on the pixel range of the defect area within the candidate region, and determining the implicit defect area based on the contour of the target connected crack; and determining the defect area of ​​each candidate region based on the explicit defect area and the implicit defect area.

[0033] It is understood that each candidate region may contain one or more defect areas (including visible defect areas and / or hidden defect areas), and the structural risk or internal corrosion risk of the defect area is mainly reflected in the fact that the concrete surface layer has peeled off, directly leading to a reduction in the structural strength of the area; or although the surface layer has not completely peeled off, substantial separation has occurred, and its structural bearing capacity has been significantly affected. Therefore, the defect area of ​​the defect area can include the visible defect area where the concrete surface layer has detached, and the hidden defect area where the concrete surface layer has not completely detached but there is a great risk of detachment.

[0034] Target-connecting cracks refer to cracks that can significantly improve the risk of escaping hidden defects. Specifically, they include two types: one is a "through crack" in which both ends of the crack are directly connected to the visible defect; the other is an "extended crack" in which only one end is connected to the visible defect, but it has a long length and local symmetry.

[0035] For target connected cracks that are connected to visible defect areas at both ends, the overlap relationship between the crack contour and the boundary of the visible defect area can be directly extracted using image recognition technology to quickly complete the identification and judgment.

[0036] For candidate cracks that are "connected to the visible defect area at one end and not connected at the other end", this application embodiment determines whether they are target connected cracks by feature point normal vector analysis. The specific process is as follows: First, a preset number of feature points (such as 10, 20 or 100) are uniformly collected along the extension path of the candidate crack; then, the normal vector of each feature point along the crack width direction is calculated, the number of feature points corresponding to the two types of normal vectors with opposite directions is counted, and the ratio of the two is calculated; finally, the ratio is compared with a preset ratio. If the ratio is greater than or equal to the preset ratio, the candidate crack is determined to be a target connected crack.

[0037] For example, such as Figure 3As shown, for a candidate crack F1 (the solid line represents candidate crack F1, one end of which is connected to the visible defect area S1, and the other end is not connected), 13 feature points (marked as N1 to N13) were uniformly collected along its extension path. After calculating the normal vectors of each feature point along the crack width direction, it was found that the normal vectors of feature points N5 and N13 are in opposite directions (or approximately opposite), N6 and N12 are in opposite directions, and N7 and N11 are in opposite directions. That is, there are a total of 6 feature points with opposite normal vector directions. Based on this, the calculated ratio is 6 / 13≈0.46, which is greater than the preset ratio of 0.1. This result indicates that the candidate crack exhibits obvious local symmetry characteristics. Such symmetry characteristics usually mean that the crack continues to crack in a regular manner, easily accelerating the peeling of the concrete surface layer from the base layer, and significantly increasing the risk of detachment from the hidden defect area. Therefore, this candidate crack is determined to be a target connected crack.

[0038] In this embodiment, crack identification is first performed on the target image data containing candidate regions to determine whether each candidate region has a corresponding target connected crack. If the candidate region does not have the target connected crack, it indicates that the candidate region only has a visually visible explicit defect and no potential latent defect risk. In this case, the area is directly calculated based on the pixel range of the explicit defect area within the candidate region, that is, by counting the total number of pixels in the explicit defect area within the region and combining it with the pixel size (the actual physical size after image scale calibration), and the result is used as the actual defect area of ​​the candidate region. If the candidate region has a corresponding target connected crack, it indicates that the candidate region not only has an explicit defect area but also a latent defect area. In this case, the explicit defect area is determined based on the pixel range of the explicit defect area, and the latent defect area is determined based on the contour of the target connected crack. Finally, the explicit defect area and the latent defect area are added together to obtain the actual defect area of ​​each defect region.

[0039] When determining the area of ​​a latent defect based on the outline of a target connected crack, the end of the target connected crack that is not connected to the visible defect area can be extended in a preset direction to make the target connected crack form an enclosed area; then the area of ​​the latent defect can be determined based on the pixel range of the enclosed area of ​​the target connected crack.

[0040] For example, such as Figure 3As shown, for the identified target connected crack F1, starting from the end that is not connected to the explicit defect area, the crack is fitted and extended along the direction of the end that is connected to the explicit defect area to form an extended crack F2 (represented by a dashed line). After the target connected crack F1 and the extended crack F2 jointly enclose and form a closed region S2, the total number of pixels in the enclosed region S2 can be counted, and the area of ​​the region can be calculated by combining the pixel size. This area is the latent defect area corresponding to the defect area.

[0041] In one embodiment, such as Figure 4 As shown, step S100: obtaining the defect index of the target area of ​​the bridge includes: S110. Acquire local image data of the target defect area, and determine the exposure index corresponding to each target defect area based on the local image data. The exposure index is used to characterize the degree of exposure of the reinforcing steel in the defect area. S120. Call the pre-trained bridge stress model, match each of the target defect areas with the bridge stress points under different traffic conditions in the bridge stress model, and obtain the matching probability value between each of the target defect areas and the corresponding stress points. The matching probability value is used to characterize the probability that the bridge stress points are located in the target defect areas. S130. Determine the defect index of the target area based on the matching probability value and the corresponding exposure index of each target defect area.

[0042] It is understandable that the defect index of the target area is related to the defect indices of each target defect zone. Taking target area A2 as an example, the risk level of target area A2 is jointly determined by the risks of target defect zones (Q1, Q2, Q3), and the higher the cumulative risk of target defect zones (Q1, Q2, Q3), the greater the defect index of the target area. The risk level of the target defect zone is directly related to the degree of rebar exposure. The larger the exposed area of ​​the rebar and the more obvious the exposure state (such as no concrete coverage or severe corrosion), the wider its contact range with external corrosive media (rainwater, salt, etc.), the faster the corrosion rate, and the greater the threat to the durability of the bridge structure.

[0043] In one embodiment, determining the exposure index corresponding to each target defect area based on the local image data includes: inputting the local image data into a semantic recognition model to obtain the pixel semantic category of each pixel, wherein the pixel semantic category is either steel reinforcement or concrete; counting the total number of pixels whose pixel semantic category is steel reinforcement, and determining the steel reinforcement exposure area based on the total number of pixels and the pixel size; and determining the exposure index based on the steel reinforcement exposure area and the area of ​​the target defect area.

[0044] Specifically, firstly, the local image data of the target defect area is input into the semantic recognition model to obtain the pixel semantic category of each pixel, which is either steel reinforcement or concrete. Then, the total number of pixels whose pixel semantic category is steel reinforcement is counted, and the exposed area of ​​steel reinforcement is determined based on the total number of pixels and the pixel size. Finally, the exposure index is determined based on the exposed area of ​​steel reinforcement and the area of ​​the target defect area.

[0045] When the target defect area only has visible defects (no hidden defects), the exposure index is calculated by dividing the exposed area of ​​the rebar by the visible defect area of ​​the target defect area. This result directly reflects the proportion of exposed rebar within the visible defect area. When the target defect area has both visible and hidden defects, the preliminary exposure index is first calculated by dividing the exposed area of ​​the rebar by the visible defect area of ​​the target defect area. Considering that the larger the hidden defect area, the smaller the effective bond area between the rebar and the concrete, and the higher the potential risk of corrosion of the rebar in the hidden area, the preliminary exposure index needs to be positively corrected based on the hidden defect area. The correction value increases with the increase of the hidden defect area. Finally, the final exposure index is obtained by "preliminary exposure index + correction value" to comprehensively reflect the combined impact of the actual exposure risk of rebar in the visible area and the potential corrosion risk in the hidden area.

[0046] In addition, the risk level of the target defect area is also affected by whether it is a "high-stress point" and whether it has been in a "high-stress point" state for a long time. Among them, "high-stress point" refers to the location in the target defect area where the stress value exceeds the preset threshold. These points are more prone to structural fatigue problems due to long-term exposure to large loads, and the risk is significantly higher than that of ordinary areas.

[0047] To determine whether a target defect area is a high-stress point that is frequently or for a long period of time, a pre-trained bridge stress model can be invoked. Each target defect area can be spatially matched with a high-stress point on the bridge under different traffic conditions in the bridge stress model. The "matching probability value" between the target defect area and the corresponding high-stress point can be calculated based on the matching results, providing data support for risk assessment.

[0048] For example, taking the target defect areas Q1, Q2, and Q3 obtained in step S100 as examples, after simulating 2000 different traffic scenarios (such as different vehicle positions in the bridge width direction) using a pre-trained bridge stress model, it was found that: the probability of a strong stress point on the bridge falling within the target defect area Q1 is 60%, the probability of falling within the target defect area Q2 is 30%, and the probability of falling within the target defect area Q3 is 70%. Based on this, it can be determined that the matching probability between the target defect area Q1 and the strong stress point on the bridge is 60%, the matching probability between the target defect area Q2 and the strong stress point on the bridge is 30%, and the matching probability between the target defect area Q3 and the strong stress point on the bridge is 70%. Furthermore, the matching probability is positively correlated with structural risk; the higher the matching probability, the greater the structural risk in that area.

[0049] After obtaining the matching probability value (reflecting stress risk) and exposure index (reflecting rebar exposure risk) corresponding to each target defect area, the defect index of the target area can be calculated.

[0050] In one embodiment, determining the defect index based on the matching probability value and the corresponding exposure index of each target defect area includes: inputting the matching probability value and the corresponding exposure index of each target defect area into a risk assessment model to obtain a comprehensive risk characterization value for each target defect area; and determining the defect index of the target area based on the comprehensive risk characterization value of each target defect area.

[0051] Specifically, the matching probability value and the corresponding exposure index of each target defect area can be input into the risk assessment model to obtain the comprehensive risk characterization value of each target defect area, that is, to obtain the independent defect index of each target defect area. Then, the average value of the independent defect indices of all target defect areas is taken, and the final result is the defect index of the target area, which can comprehensively reflect the overall risk level of the target area.

[0052] Thus, this application embodiment quantifies the degree of steel bar exposure by using the exposure index and quantifies the correlation of stress-bearing points by using the matching probability value. It transforms the two core hidden dangers of corrosion risk and structural fatigue risk into calculable quantitative indicators, solves the problem of ambiguity of risk factors, and upgrades risk assessment from qualitative judgment to quantitative analysis.

[0053] Step S200: If the defect index is greater than or equal to the index threshold, trigger the bridge alignment monitoring command; It is understandable that when the defect index of the target area is greater than or equal to the index threshold, it indicates that there is a significant structural and / or corrosion risk in the target area. At this time, the bridge alignment monitoring command is automatically triggered, which is used to monitor the bridge alignment of the target area.

[0054] Step S300: Determine multiple target monitoring points associated with the target area according to the bridge alignment monitoring instruction, wherein the target monitoring points cover the defective areas within the target area; After the bridge alignment monitoring command is triggered in step S200, the controller receives the command and starts the point planning process. Based on the command, it determines multiple target monitoring points that are directly associated with the target area. All target monitoring points must achieve full coverage of the defect area within the target area to ensure that the subsequent alignment monitoring data can accurately reflect the structural deformation state of the target area.

[0055] To improve the efficiency of monitoring point determination and ensure monitoring consistency, a fixed association between the target area and the target monitoring points can be established in advance (i.e., the corresponding point information is planned and stored in advance based on the bridge structural characteristics, the target area range, and the distribution pattern of potential defects). Taking the scenario shown in Figure 2 as an example, if the target area is the middle area A2 of the bridge, five target monitoring points (denoted as P1-P5) can be pre-set. The layout of the points needs to take into account the area boundary of A2, the core stress section, and the vulnerable parts, ensuring that P1-P5 can completely cover the spatial range of A2. Subsequently, as long as A2 is determined to be the target area, the controller can directly call the preset P1-P5 as the monitoring points without temporary planning, which greatly shortens the monitoring preparation time.

[0056] Step S400: Generate a curve of the emission angle change of the laser emitting device based on the target monitoring point, wherein the laser emitting device is pre-fixed at a preset height position under the bridge; In the embodiments of this application, such as Figure 2 As shown, the laser emitting device M is pre-fixed at a predetermined height position under the bridge. In step S300, after determining multiple target monitoring points based on the target area, the precise position coordinates of each target monitoring point can be retrieved from the preset point information database. Combined with the preset fixed position parameters of the laser emitting device, a curve of the emission angle change of the laser emitting device is generated through spatial angle calculation and data fitting. This provides an automated control basis for the subsequent precise alignment of the laser device with each monitoring point.

[0057] Step S500: Control the laser emitting device to emit lasers sequentially according to the emission angle change curve, and calculate the sinking height value corresponding to each of the multiple target monitoring points by receiving the laser reflection signal; After obtaining the emission angle change curve of the laser emitting device in step S400, the laser emitting device is controlled to emit lasers sequentially according to the emission angle change curve, and the sinking height value corresponding to each of the multiple target monitoring points is calculated by receiving the laser reflection signal.

[0058] In one embodiment, such as Figure 5As shown, step S500: calculating the subsidence height value corresponding to each of the plurality of target monitoring points by receiving laser reflection signals, including: S510. Record the laser emission time and the reflection signal reception time, and calculate the laser propagation time difference; S520. Calculate the actual distance from the laser emitting device to the target monitoring point based on the laser propagation speed and time difference. S530: Based on the preset height, emission angle, and actual distance of the laser emitting device, the actual elevation of the target monitoring point is calculated using trigonometric functions; S540. Subtract the actual elevation from the design elevation of the point to obtain the corresponding settlement height value; S550. Perform a preset number of measurements on the same target monitoring point and take the average of the sinking height values ​​as the final sinking height value.

[0059] Specifically, the laser emitting device emits a laser beam at a preset angle toward the target monitoring point and starts timing simultaneously; when the device receives the laser signal reflected back from the monitoring point, the timing stops. The system accurately records the laser emission time (T1) and the reflected signal reception time (T2), and the difference between the two (ΔT = T2 - T1) is the time difference of the laser's round-trip propagation between the device and the monitoring point.

[0060] The speed of laser propagation in air (V) is a known constant (approximately 3 × 10⁻⁶). 8 (m / s). Since the time difference recorded in step S510 is the total round-trip time of the laser, the formula for calculating the actual one-way distance (D) from the laser emitting device to the target monitoring point is: D = (V × ΔT) / 2.

[0061] Based on the preset height (H0, i.e., the elevation of the device installation location, which is a known fixed value), emission angle (θ, i.e., the angle between the laser beam and the horizontal direction, taken from the angle change curve generated in step S300) and actual distance (D) of the laser emitting device, the actual elevation (H1) of the monitoring point is calculated by trigonometric functions. The specific calculation process is not described in detail.

[0062] Because each target monitoring point has a corresponding design elevation (H) during the bridge design phase. 设计 (Taken from bridge construction drawings or as-built data). Compare the actual elevation (H1) calculated in step S530 with the design elevation (H... 设计 The difference is calculated to obtain the subsidence height (S) at that point.

[0063] To eliminate potential errors in a single measurement (such as random deviations caused by air disturbances or signal interference), the measurement process S510-S540 is repeated for the same target monitoring point a preset number of times (e.g., 3 times, 5 times) to obtain multiple subsidence height values ​​(S1, S2, ..., Sn). The arithmetic mean of these values ​​is then calculated as the final subsidence height data for that point.

[0064] Step S600: Perform data fitting on the subsidence height values ​​corresponding to the multiple target monitoring points to generate the bridge alignment of the monitoring point interval.

[0065] After obtaining the subsidence height data of each target monitoring point in step S500, the discrete point data can be smoothed by using a data fitting algorithm based on the spatial position relationship of each point (such as the mileage coordinates along the bridge length direction) and the corresponding subsidence height value, so as to generate a continuous bridge alignment covering the measurement point interval and intuitively present the structural deformation trend of the target area.

[0066] Based on this, this application first identifies high-incidence areas of bridge defects based on the defect identification results, and uses these high-incidence areas as target areas for bridge alignment monitoring. Then, it uses a laser emitter to automatically match target monitoring points, fitting the bridge alignment of the monitoring point intervals based on the settlement height data of the target monitoring points. In this way, while ensuring that the alignment data accurately reflects the structural deformation state of the defective areas, it avoids the waste of resources caused by indiscriminate monitoring of the entire bridge, effectively improving the efficiency, targeting, and reliability of bridge alignment monitoring, and helping to achieve real-time early warning and scientific management of bridge structural safety.

[0067] like Figure 6 As shown, Figure 6 The diagram below shows the hardware structure of a bridge alignment monitoring system in some embodiments of this application. The bridge alignment monitoring system provided in this application also includes a memory 1000 and a processor 2000. The memory 1000 is used to store computer-readable instructions, and the processor 2000 is used to call the computer-readable instructions to execute the bridge alignment monitoring method as described above.

[0068] The processor 2000 provides computing and control capabilities to control the bridge alignment monitoring system to perform corresponding tasks. For example, it controls the bridge alignment monitoring system to perform the bridge alignment monitoring method in any of the above-described method embodiments. The method includes: acquiring a defect index of a target area of ​​the bridge, wherein the target area is a high-incidence defect area determined based on defect identification results, and the defect index comprehensively characterizes the risk level caused by defects in the target area; triggering a bridge alignment monitoring command when the defect index is greater than or equal to an index threshold; determining multiple target monitoring points associated with the target area according to the bridge alignment monitoring command, wherein the target monitoring points cover the defect areas within the target area; generating a laser emitting device emission angle variation curve based on the target monitoring points, wherein the laser emitting device is pre-fixed at a preset height position below the bridge; controlling the laser emitting device to emit lasers sequentially according to the emission angle variation curve, and calculating the subsidence height value corresponding to each of the multiple target monitoring points by receiving laser reflection signals; and performing data fitting on the subsidence height values ​​corresponding to the multiple target monitoring points to generate the bridge alignment of the measurement point interval.

[0069] The processor 2000 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), a hardware chip, or any combination thereof; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The aforementioned PLD can be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0070] The memory 1000, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the bridge alignment monitoring method in the embodiments of this application. The processor 2000 can implement the bridge alignment monitoring method in any of the above method embodiments by running the non-transitory software programs, instructions, and modules stored in the memory 1000.

[0071] Specifically, memory 1000 may include volatile memory (VM), such as random access memory (RAM); memory 1000 may also include non-volatile memory (NVM), such as read-only memory (ROM), flash memory, hard disk drive (HDD), solid-state drive (SSD), or other non-transitory solid-state storage devices; memory 1000 may also include combinations of the above types of memory.

[0072] In summary, the bridge alignment monitoring system of this application adopts the technical solution of any of the above-mentioned bridge alignment monitoring method embodiments. Therefore, it has at least the beneficial effects brought about by the technical solutions of the above embodiments, which will not be elaborated here.

[0073] This application also provides a computer-readable storage medium, such as a memory including program code, which can be executed by a processor to complete the bridge alignment monitoring method described above. For example, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CDROM), magnetic tape, floppy disk, or optical data storage device, etc.

[0074] This application also provides a computer program product comprising one or more lines of program code stored in a computer-readable storage medium. The processor of the early warning system reads the program code from the computer-readable storage medium and executes the program code to complete the steps of the bridge alignment monitoring method provided in the above embodiments.

[0075] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware, or by a program or program code related to hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0076] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0077] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software and a general-purpose hardware platform, or of course, using hardware. Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0078] The above description is merely a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural transformations made using the contents of the present invention's specification and drawings under the inventive concept of the present invention, or direct / indirect applications in other related technical fields, are included within the patent protection scope of the present invention.

Claims

1. A bridge alignment monitoring system, characterized in that, The method includes a memory and a processor. The memory stores computer-readable instructions, and the processor is used to invoke and execute the computer-readable instructions to implement the following steps of the bridge alignment monitoring method: Obtain the defect index of the target area of ​​the bridge, where the target area is a high-incidence area of ​​defects determined based on the defect identification results, and the defect index is a comprehensive characterization of the risk level caused by defects in the target area; If the defect index is greater than or equal to the index threshold, a bridge alignment monitoring command is triggered. Based on the bridge alignment monitoring instruction, multiple target monitoring points associated with the target area are determined, and the target monitoring points cover the defective areas within the target area; A curve showing the change in the emission angle of the laser emitting device is generated based on the target monitoring point, wherein the laser emitting device is pre-fixed at a preset height position under the bridge; The laser emitting device is controlled to emit lasers sequentially according to the emission angle change curve, and the sinking height value corresponding to each of the multiple target monitoring points is calculated by receiving the laser reflection signal. Data fitting is performed on the subsidence height values ​​corresponding to the multiple target monitoring points to generate the bridge alignment of the monitoring point interval; Before obtaining the defect index of the target area of ​​the bridge, the following steps are included: Obtain the target image data by acquiring the global image data of the bridge; The target image data is subjected to surface defect identification, and the defect area of ​​each candidate region is determined based on the surface defect identification results. The candidate regions are regions that are pre-divided according to the bridge length. The candidate region with the largest cumulative surface defect area is selected as the target region, and the defect area within the target region is defined as the target defect area. The acquisition of the defect index of the target area of ​​the bridge includes: Local image data of the target defect area is acquired, and an exposure index corresponding to each target defect area is determined based on the local image data. The exposure index is used to characterize the degree of exposure of the reinforcing steel in the target defect area. The pre-trained bridge stress model is invoked, and each of the target defect areas is matched with the bridge stress points under different traffic conditions in the bridge stress model to obtain the matching probability value between each target defect area and the corresponding stress point. The matching probability value is used to characterize the probability that the bridge stress point is located in the target defect area. The defect index of the target area is determined based on the matching probability value and the corresponding exposure index of each target defect area.

2. The bridge alignment monitoring system as described in claim 1, characterized in that, When the processor executes the computer-readable instructions, the step of identifying surface defects in the target image data and determining the defect area of ​​each candidate region based on the surface defect identification results includes: Crack identification is performed on target image data containing candidate regions to determine whether each candidate region has a corresponding target connectivity crack. If it is determined that the target connectivity crack does not exist in the candidate region, the defect area corresponding to each candidate region is determined according to the pixel range of the defect area in the candidate region. If it is determined that there is a corresponding target connectivity crack in the candidate region, the explicit defect area is determined according to the pixel range of the defect area in the candidate region, and the implicit defect area is determined according to the contour of the target connectivity crack. The defect area of ​​each candidate region is determined based on the area of ​​the visible defect and the area of ​​the hidden defect.

3. The bridge alignment monitoring system as described in claim 2, characterized in that, When the processor executes the computer-readable instructions, the step of determining whether each candidate region has a corresponding target connectivity fracture includes: If one end of a candidate crack is connected to the defect area and the other end is not connected to the defect area, a preset number of feature points are collected along the path direction of the candidate crack. Obtain the normal vector of each feature point, and determine the proportion of feature points corresponding to normal vectors with opposite directions; Candidate cracks with a percentage ratio greater than or equal to a preset ratio are identified as target connected cracks.

4. The bridge alignment monitoring system as described in claim 3, characterized in that, When the processor executes the computer-readable instructions, it determines the area of ​​the latent defect based on the contour of the target connected crack, including: The end of the target connecting crack that is not connected to the defect area is extended in a predetermined direction so that the target connecting crack forms an enclosed area; The area of ​​the hidden defect is determined based on the pixel range of the region enclosed by the target connected crack.

5. The bridge alignment monitoring system as described in claim 1, characterized in that, When the processor executes the computer-readable instructions, determining the exposure index corresponding to each target defect area based on the local image data includes: The local image data is input into a semantic recognition model to obtain the pixel semantic category of each pixel, wherein the pixel semantic category is either steel reinforcement or concrete. The total number of pixels whose semantic category is represented by the rebar is counted, and the exposed area of ​​the rebar is determined based on the total number of pixels and the pixel size. The exposure index is determined based on the exposed area of ​​the reinforcing steel and the area of ​​the target defective area.

6. The bridge alignment monitoring system as described in claim 1, characterized in that, When the processor executes the computer-readable instructions, determining the defect index based on the matching probability value and the corresponding exposure index of each target defect region includes: The matching probability value and the corresponding exposure index of each target defect area are input into the risk assessment model to obtain the comprehensive risk characterization value of each target defect area; The defect index of the target area is determined based on the comprehensive risk characterization value of each target defect area.

7. The bridge alignment monitoring system as described in claim 1, characterized in that, When the processor executes the computer-readable instructions, the step of calculating the subsidence height value corresponding to each of the plurality of target monitoring points by receiving laser reflection signals includes: Record the laser emission time and the reflected signal reception time, and calculate the laser propagation time difference; Calculate the actual distance from the laser emitter to the target monitoring point based on the laser propagation speed and time difference; Based on the preset height, emission angle, and actual distance of the laser emitting device, the actual elevation of the target monitoring point is calculated using trigonometric functions. The difference between the actual elevation and the design elevation at that point is used to obtain the corresponding settlement height value. The same target monitoring point is measured a preset number of times, and the average value of the sinking height is taken as the final sinking height value.

8. A method for monitoring bridge alignment, characterized in that, The method includes: Obtain the defect index of the target area of ​​the bridge, where the target area is a high-incidence area of ​​defects determined based on the defect identification results, and the defect index is a comprehensive characterization of the risk level caused by defects in the target area; If the defect index is greater than or equal to the index threshold, a bridge alignment monitoring command is triggered. Based on the bridge alignment monitoring instruction, multiple target monitoring points associated with the target area are determined, and the target monitoring points cover the defective areas within the target area; A curve showing the change in the emission angle of the laser emitting device is generated based on the target monitoring point, wherein the laser emitting device is pre-fixed at a preset height position under the bridge; The laser emitting device is controlled to emit lasers sequentially according to the emission angle change curve, and the sinking height value corresponding to each of the multiple target monitoring points is calculated by receiving the laser reflection signal. Data fitting is performed on the subsidence height values ​​corresponding to the multiple target monitoring points to generate the bridge alignment of the monitoring point interval; Before obtaining the defect index of the target area of ​​the bridge, the following steps are included: Obtain the target image data by acquiring the global image data of the bridge; The target image data is subjected to surface defect identification, and the defect area of ​​each candidate region is determined based on the surface defect identification results. The candidate regions are regions that are pre-divided according to the bridge length. The candidate region with the largest cumulative surface defect area is selected as the target region, and the defect area within the target region is defined as the target defect area. The acquisition of the defect index of the target area of ​​the bridge includes: Local image data of the target defect area is acquired, and an exposure index corresponding to each target defect area is determined based on the local image data. The exposure index is used to characterize the degree of exposure of the reinforcing steel in the target defect area. The pre-trained bridge stress model is invoked, and each of the target defect areas is matched with the bridge stress points under different traffic conditions in the bridge stress model to obtain the matching probability value between each target defect area and the corresponding stress point. The matching probability value is used to characterize the probability that the bridge stress point is located in the target defect area. The defect index of the target area is determined based on the matching probability value and the corresponding exposure index of each target defect area.

Images