Method and system for rapidly detecting ponding of bridge crane cable based on infrared phase-locked thermal imaging

Abstract

The invention discloses a bridge crane cable ponding rapid detection method and system based on infrared phase-locked thermal imaging, and belongs to the technical field of cable-supported bridge detection, and the method comprises the following steps: deploying an unmanned aerial vehicle airport and an unmanned aerial vehicle around a bridge crane cable site; acquiring bridge image data and reconstructing to generate a preliminary three-dimensional model of the bridge; planning a fine inspection route for covering the hoisting cable; according to a set sampling frequency, collecting infrared video data of the suspension cable along the fine inspection route of the suspension cable; training and optimizing to obtain a pulling and lifting cable water accumulation disease evaluation and detection model; and inputting the stay cable infrared video data into the stay cable waterlogging disease assessment and detection model for assessment and detection so as to obtain a bridge stay cable waterlogging disease result. According to the detection method and system, large-area non-contact rapid scanning of the bridge crane cable is achieved, the detection efficiency is improved, and the risk and cost of manual detection are reduced.

Description

Technical Field

[0001] This invention belongs to the field of cable-stayed bridge inspection technology, specifically relating to a rapid detection method and system for water accumulation in bridge suspension cables based on infrared phase-locked thermal imaging. Background Technology

[0002] Cable-stayed bridges, with their superior spanning capacity and elegant design, have become the mainstream structural form for achieving ultra-long-distance crossings and creating landmark architectural features. Typical types include cable-stayed bridges, arch bridges, and suspension bridges. The cables are crucial load-bearing components of cable-stayed bridges. They primarily utilize steel wire ropes, steel strands, and parallel wire bundles. The steel wires are generally galvanized, with a double-coated protective structure consisting of an iron-zinc alloy layer and an outer pure zinc layer formed by hot-dip galvanizing. Furthermore, the cable body is typically protected with high-density polyethylene (HDPE) sheaths. However, during bridge operation, the sheaths are affected by cyclical vehicle loads, collisions, ultraviolet radiation, rainwater erosion, and corrosion from harmful gases. This causes aging and cracking, manifesting as crazing, scratches, abrasions, and fissures.

[0003] Cable-stayed bridges are under high stress, which can lead to stress corrosion, accelerating the rusting, corrosion, and eventual breakage of the cables. This causes the cable tension to deviate from the bridge's overall cable tension, reducing structural safety and service life. Ultimately, cable-stayed bridges often require premature cable replacement, resulting in significant economic losses and severely impacting normal bridge operation. Therefore, it is urgent to strengthen the inspection of cable-stayed bridges in service.

[0004] The inspection of cables in cable-stayed bridges currently in service mainly relies on manual inspection, cable robots, and magnetostrictive waveguide technology, but these methods all have significant limitations. Manual inspection requires aerial work platforms and telescopes, resulting in low efficiency, high cost, high rates of false positives and false negatives, and frequent traffic disruptions. While cable robots can photograph the cable's exterior, minor wear, dirt, or cracks on the surface cannot directly reflect the corrosion or breakage of the internal steel wires. Destructive window opening verification based solely on visual results would easily lead to resource waste, which is inconsistent with the current situation of generally tight maintenance budgets. In addition, for cables with smaller diameters, robots face safety hazards such as insufficient wheel traction and easy slippage and fall. The vertical arrangement of suspension bridge cables places extremely high demands on their dynamic performance, and the cable force sensors installed on the cables also pose challenges to their crossing capabilities. Furthermore, the cost of a single unit often reaches hundreds of thousands to millions of yuan, limiting the further promotion and application of cable robots. While magnetostrictive guided wave technology has the advantage of single-point excitation and long-distance detection, it actually requires the installation of multiple magnetization units, which is time-consuming and labor-intensive. The weak original signal at its receiving end is easily drowned out by environmental electromagnetic noise (such as vehicle electromagnetic interference) and mechanical noise (such as wind vibration and vehicle vibration). Furthermore, it is not sensitive enough to early corrosion or micro-broken wires (such as the breakage of a single steel wire), resulting in a high risk of missed detection. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of the prior art and provide a rapid detection method and system for water accumulation in bridge suspension cables based on infrared phase-locked thermal imaging.

[0006] To achieve the above objectives, the present invention is implemented using the following technical solution.

[0007] In a first aspect, the present invention provides a rapid detection method for water accumulation in bridge suspension cables based on infrared phase-locked thermal imaging, comprising the following steps: Step S1: Deploy a drone airport and drones around the bridge cable-stayed bridge site; Step S2: Use a drone equipped with a LiDAR L2 to collect bridge image data and reconstruct a preliminary 3D model of the bridge; Step S3: Based on the preliminary three-dimensional model of the bridge cable suspension cables, plan a detailed inspection route covering the cable suspension cables; Step S4: Using a drone equipped with an infrared phase-locked thermal imager, infrared video data of the suspension cable is collected along the fine inspection route of the suspension cable according to the set sampling frequency; Step S5: Construct an infrared detection dataset for water accumulation in suspension cables, input an extended causal temporal convolutional network model, train and optimize it to obtain a detection and assessment model for water accumulation in suspension cables. Step S6: Input the infrared video data of the suspension cable into the water accumulation defect assessment and detection model of the suspension cable for assessment and detection, so as to obtain the water accumulation defect results of the bridge suspension cable.

[0008] Furthermore, in step S1, DJI Pilot 2 is used to plan a five-axis oblique photography route covering the entire steel box girder, including front, rear, left, right, and top. A DJI Matrice series aircraft equipped with a LiDAR L2 is used to collect image data, and the image data is imported into DJI Terra for three-dimensional reconstruction to generate a preliminary three-dimensional model of the bridge.

[0009] Furthermore, in step S3, the method for planning the refined inspection route includes the following steps: Key inspection points for the suspension cables, including connection points, support points, and intermediate points, were identified and marked on the preliminary 3D model of the bridge. In DJI Terra, based on the direction of the suspension cable and the marked key checkpoints, design a basic route that extends along the direction of the suspension cable, and adjust the route height and distance from the suspension cable according to the preset spacing based on the diagonal extension height of the suspension cable. At least one additional route is laid out at a preset interval and parallel to the left, right and above the basic route to ensure that the route can follow the direction of the suspension cable more accurately and avoid obstacles. Simulate flight in DJI Terra to check the feasibility and safety of flight paths and verify coverage, ensuring coverage of at least 90% of the marked key detection points.

[0010] Furthermore, in step S5, an infrared detection dataset for water accumulation in the suspension cable is constructed, including the following steps: Prepare 10 full-scale test specimens of cables of the same material and diameter as the actual bridge; Seven tubes were selected to inject gradient volumes of deionized water, ranging from 5 ml to 50 ml, with a gradient interval of 7 ml, to simulate different water accumulation conditions. The remaining three samples were kept dry as a control group. A high-precision infrared phase-locked thermal imager was used to collect the surface temperature field of the samples under a constant thermal excitation source and a 1Hz square wave. For each cable, at least 143 time-series video segments were collected, with a total sample size of ≥1000 segments. The duration of each video segment covered ≥3 complete thermal cycles, 3s@1Hz, and the spatial resolution was 0.5mm / px.

[0011] Furthermore, in step S5, during the data acquisition process, a nighttime detection window is planned, and phase-locked thermal imaging acquisition is performed when the ambient temperature gradient approaches a steady state.

[0012] Furthermore, in step S6, for the tension / suspension cables where infrared detection indicates water accumulation and the water seepage scale is ≥3, a local manual window opening is performed for re-inspection.

[0013] Secondly, the present invention provides a rapid detection system for water accumulation in bridge suspension cables based on infrared phase-locked thermal imaging, comprising the following modules: The drone terminal module is used to deploy drone airports and drones around the bridge cable-stayed bridge site. The 3D model building module is used to acquire bridge image data using a drone equipped with an L2 lidar and reconstruct a preliminary 3D model of the bridge. The inspection route planning module is used to plan a detailed inspection route covering the bridge suspension cables based on the preliminary three-dimensional model of the bridge suspension cables. The data acquisition module is used to collect infrared video data of the suspension cable along the fine inspection route of the suspension cable by using a drone equipped with an infrared phase-locked thermal imager and according to a set sampling frequency. The evaluation and detection training module is used to construct an infrared detection experimental dataset for water accumulation in cable ties, input an extended causal temporal convolutional network model, train and optimize it to obtain an evaluation and detection model for water accumulation in cable ties. The defect detection module is used to input the infrared video data of the suspension cable into the water accumulation defect assessment and detection model of the suspension cable for assessment and detection, so as to obtain the result of water accumulation defect of bridge suspension cable.

[0014] Thirdly, the present invention provides an electronic device, comprising: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the rapid detection method for water accumulation in bridge suspension cables based on infrared phase-locked thermal imaging as described in any one of the first aspects.

[0015] Fourthly, the present invention provides a computer-readable storage medium that, when the instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to perform the rapid detection method for water accumulation in bridge suspension cables based on infrared phase-locked thermal imaging as described in any one of the first aspects.

[0016] Fifthly, the present invention provides a computer program product comprising a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps in the rapid detection method for water accumulation in bridge suspension cables based on infrared phase-locked thermal imaging as described in any one of the first aspects.

[0017] Compared with existing technologies, the beneficial effects achieved by this invention are as follows: The rapid detection method and system for bridge suspension cables based on infrared phase-locked thermal imaging provided by this invention utilizes an UAV equipped with an infrared phase-locked thermal imager to achieve large-area non-contact rapid scanning of bridge suspension cables; by processing thermal wave time-series data through a temporal convolutional network, dynamic features can be captured, and the phase difference between the water accumulation area and the steel plate can be accurately identified; by planning a nighttime detection window, phase-locked thermal imaging acquisition is carried out when the ambient temperature gradient approaches a steady state, significantly reducing the interference of solar radiation noise on thermal wave signals; it can achieve early risk warning of water accumulation in bridge suspension cables, which helps to take timely maintenance measures, avoid potential structural damage, improve detection efficiency, reduce the risks and costs of manual inspection, and achieve accurate positioning of water accumulation areas, etc., achieving at least one of the above-mentioned beneficial effects. Attached Figure Description

[0018] Figure 1 The flowchart illustrates a rapid detection method for water accumulation in bridge suspension cables based on infrared phase-locked thermal imaging, as provided in this embodiment of the invention.

[0019] Figure 2 This is a preliminary three-dimensional model rendering of a bridge provided in an embodiment of the present invention.

[0020] Figure 3 This is a rendering of a refined cable inspection route provided in an embodiment of the present invention. Detailed Implementation

[0021] The present invention will be further described below with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and should not be used to limit the scope of protection of the present invention. Example

[0022] like Figure 1 As shown in the figure, this embodiment of the invention provides a rapid detection method for water accumulation in bridge suspension cables based on infrared phase-locked thermal imaging, including the following steps: Step S1: Deploy a drone airport and drones around the bridge cable-stayed bridge site; Step S2: Use a drone equipped with a LiDAR L2 to collect bridge image data and reconstruct a preliminary 3D model of the bridge; Step S3: Based on the preliminary three-dimensional model of the bridge cable suspension cables, plan a detailed inspection route covering the cable suspension cables; Step S4: Using a drone equipped with an infrared phase-locked thermal imager, infrared video data of the suspension cable is collected along the fine inspection route of the suspension cable according to the set sampling frequency; Step S5: Construct an infrared detection dataset for water accumulation in suspension cables, input an extended causal temporal convolutional network model, train and optimize it to obtain a detection and assessment model for water accumulation in suspension cables. Step S6: Input the infrared video data of the suspension cable into the water accumulation defect assessment and detection model of the suspension cable for assessment and detection, so as to obtain the water accumulation defect results of the bridge suspension cable.

[0023] By using drones equipped with infrared phase-locked loop thermal cameras, rapid scanning of large-area non-contact cable-stayed bridges / suspension cables is achieved, overcoming the limitations of conventional manual and cable robot inspections. Temporal convolutional networks are used to process thermal wave time-series data to capture dynamic features, accurately identifying the phase difference between water accumulation areas and steel plates, thus enabling precise location of water accumulation areas. The monitoring method forms a highly efficient, progressive scheme of "comprehensive and rapid screening (water accumulation detection) + key precise verification (window opening detection)," which can achieve early risk warning, optimize resource allocation, and better meet the actual needs of current bridge maintenance.

[0024] like Figure 2 As shown, in step S1, DJI Pilot 2 is used to plan a five-axis oblique photography route covering the entire steel box girder, including front, rear, left, right and top. DJI Matrice series aircraft (such as M350) equipped with LiDAR L2 are used to collect image data, and the image data is imported into DJI Terra for three-dimensional reconstruction to generate a preliminary three-dimensional model of the bridge.

[0025] like Figure 3 As shown, in step S3, the method for planning a refined inspection route includes the following steps: Key inspection points for the suspension cables, including connection points, support points, and intermediate points, were identified and marked on the preliminary 3D model of the bridge. In DJI Terra, based on the direction of the suspension cable and the marked key checkpoints, design a basic route that extends along the direction of the suspension cable, and adjust the route height and distance from the suspension cable according to the preset spacing based on the diagonal extension height of the suspension cable. At least one additional route is laid out at a preset interval and parallel to the left, right and above the basic route to ensure that the route can follow the direction of the suspension cable more accurately and avoid obstacles. Simulate flight in DJI Terra to check the feasibility and safety of flight paths and verify coverage, ensuring coverage of at least 90% of the marked key detection points.

[0026] In step S5, an infrared detection dataset for water accumulation in the suspension cable is constructed, including the following steps: Prepare 10 full-scale test specimens of cables of the same material and diameter as the actual bridge; Seven tubes were selected to inject gradient volumes of deionized water, ranging from 5 ml to 50 ml, with a gradient interval of 7 ml, to simulate different water accumulation conditions. The remaining three samples were kept dry as a control group. A high-precision infrared phase-locked thermal imager was used to collect the surface temperature field of the samples under a constant thermal excitation source and a 1Hz square wave. For each cable, at least 143 time-series video segments were collected, with a total sample size of ≥1000 segments. The duration of each video segment covered ≥3 complete thermal cycles, 3s@1Hz, and the spatial resolution was 0.5mm / px.

[0027] In step S5, during the data acquisition process, a nighttime detection window is planned, and phase-locked thermal imaging acquisition is implemented when the ambient temperature gradient approaches a steady state. This significantly reduces the interference of solar radiation noise on the thermal wave signal and breaks through the sensitivity bottleneck of daytime detection under conditions of a small amount of water accumulation.

[0028] In step S6, for the tension / suspension cables where infrared detection indicates water accumulation and the water seepage scale is ≥3, a local manual window opening is performed for re-inspection.

[0029] The cable / suspension cable water accumulation defect assessment module, according to the provisions of Tables 7.3.1-1 and 8.2.1-6 of the "Highway Bridge Technical Condition Assessment Standard" (JTG / T H21-2011), qualitatively assesses the cable / suspension cable seepage scale by the number of sheaths where water accumulation occurs.

[0030] This invention provides a rapid detection system for water accumulation in bridge suspension cables based on infrared phase-locked thermal imaging, comprising the following modules: The drone terminal module is used to deploy drone airports and drones around the bridge cable-stayed bridge site. The 3D model building module is used to acquire bridge image data using a drone equipped with an L2 lidar and reconstruct a preliminary 3D model of the bridge. The inspection route planning module is used to plan a detailed inspection route covering the bridge suspension cables based on the preliminary three-dimensional model of the bridge suspension cables. The data acquisition module is used to collect infrared video data of the suspension cable along the fine inspection route of the suspension cable by using a drone equipped with an infrared phase-locked thermal imager and according to a set sampling frequency. The evaluation and detection training module is used to construct an infrared detection experimental dataset for water accumulation in cable ties, input an extended causal temporal convolutional network model, train and optimize it to obtain an evaluation and detection model for water accumulation in cable ties. The defect detection module is used to input the infrared video data of the suspension cable into the water accumulation defect assessment and detection model of the suspension cable for assessment and detection, so as to obtain the result of water accumulation defect of bridge suspension cable.

[0031] In some embodiments, a dilated causal temporal convolutional network model is constructed, including four dilated convolutional layers and a spatial attention module. The infrared detection dataset of water accumulation on cable-stayed bridges is input into the dilated causal temporal convolutional network model to train and optimize the model parameters, and then it is deployed to a cloud platform as an evaluation detection module.

[0032] Infrared video is transmitted via 5G to the cloud platform's cable sling water accumulation disease storage module and assessment and detection module. The assessment and detection module transmits the number of sheaths with water accumulation to the cable sling water accumulation disease detection report module, realizing the automatic assessment of cable sling water accumulation disease and the automatic generation of detection reports.

[0033] This invention provides an electronic device, comprising: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the rapid detection method for water accumulation in bridge suspension cables based on infrared phase-locked thermal imaging as described in any of the above-described methods.

[0034] This invention provides a computer-readable storage medium that, when the instructions in the storage medium are executed by the processor of an electronic device, enables the electronic device to perform the rapid detection method for water accumulation in bridge suspension cables based on infrared phase-locked thermal imaging as described above.

[0035] This invention provides a computer program product comprising a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps in the rapid detection method for water accumulation in bridge suspension cables based on infrared phase-locked thermal imaging as described above.

[0036] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A rapid detection method for water accumulation in bridge suspension cables based on infrared phase-locked thermal imaging, characterized in that, Includes the following steps: Step S1: Deploy a drone airport and drones around the bridge cable-stayed bridge site; Step S2: Use a drone equipped with a LiDAR L2 to collect bridge image data and reconstruct a preliminary 3D model of the bridge; Step S3: Based on the preliminary three-dimensional model of the bridge cable suspension cables, plan a detailed inspection route covering the cable suspension cables; Step S4: Using a drone equipped with an infrared phase-locked thermal imager, infrared video data of the suspension cable is collected along the fine inspection route of the suspension cable according to the set sampling frequency; Step S5: Construct an infrared detection dataset for water accumulation in suspension cables, input an extended causal temporal convolutional network model, train and optimize it to obtain a detection and assessment model for water accumulation in suspension cables. Step S6: Input the infrared video data of the suspension cable into the water accumulation defect assessment and detection model of the suspension cable for assessment and detection, so as to obtain the water accumulation defect results of the bridge suspension cable.

2. The rapid detection method for water accumulation in bridge suspension cables based on infrared phase-locked thermal imaging according to claim 1, characterized in that, In step S1, DJI Pilot 2 is used to plan a five-axis oblique photography route covering the entire steel box girder, including front, rear, left, right, and top. DJI Matrice series aircraft equipped with LiDAR L2 is used to collect image data, and the image data is imported into DJI Terra for three-dimensional reconstruction to generate a preliminary three-dimensional model of the bridge.

3. The rapid detection method for water accumulation in bridge suspension cables based on infrared phase-locked thermal imaging according to claim 1, characterized in that, In step S3, the method for planning a refined inspection route includes the following steps: Key inspection points for the suspension cables, including connection points, support points, and intermediate points, were identified and marked on the preliminary 3D model of the bridge. In DJI Terra, based on the direction of the suspension cable and the marked key checkpoints, design a basic route that extends along the direction of the suspension cable, and adjust the route height and distance from the suspension cable according to the preset spacing based on the diagonal extension height of the suspension cable. At least one additional route is laid out at a preset interval and parallel to the left, right and above the basic route to ensure that the route can follow the direction of the suspension cable more accurately and avoid obstacles. Simulate flight in DJI Terra to check the feasibility and safety of flight paths and verify coverage, ensuring coverage of at least 90% of the marked key detection points.

4. The rapid detection method for water accumulation in bridge suspension cables based on infrared phase-locked thermal imaging according to claim 1, characterized in that, In step S5, an infrared detection dataset for water accumulation in the suspension cable is constructed, including the following steps: Prepare 10 full-scale test specimens of cables of the same material and diameter as the actual bridge; Seven tubes were selected to inject gradient volumes of deionized water, ranging from 5 ml to 50 ml, with a gradient interval of 7 ml, to simulate different water accumulation conditions. The remaining three samples were kept dry as a control group. A high-precision infrared phase-locked thermal imager was used to collect the surface temperature field of the samples under a constant thermal excitation source and a 1Hz square wave. For each cable, at least 143 time-series video segments were collected, with a total sample size of ≥1000 segments. The duration of each video segment covered ≥3 complete thermal cycles, 3s@1Hz, and the spatial resolution was 0.5mm / px.

5. The rapid detection method for water accumulation in bridge suspension cables based on infrared phase-locked thermal imaging according to claim 1, characterized in that, In step S5, during the data acquisition process, a nighttime detection window is planned, and phase-locked thermal imaging acquisition is performed when the ambient temperature gradient approaches a steady state.

6. The rapid detection method for water accumulation in bridge suspension cables based on infrared phase-locked thermal imaging according to claim 1, characterized in that, In step S6, for the tension / suspension cables where infrared detection indicates water accumulation and the water seepage scale is ≥3, a local manual window opening is performed for re-inspection.

7. A rapid detection system for water accumulation in bridge suspension cables based on infrared phase-locked thermal imaging, characterized in that, Includes the following modules: The drone terminal module is used to deploy drone airports and drones around the bridge cable-stayed bridge site. The 3D model building module is used to acquire bridge image data using a drone equipped with an L2 lidar and reconstruct a preliminary 3D model of the bridge. The inspection route planning module is used to plan a detailed inspection route covering the bridge suspension cables based on the preliminary three-dimensional model of the bridge suspension cables. The data acquisition module is used to collect infrared video data of the suspension cable along the fine inspection route of the suspension cable by using a drone equipped with an infrared phase-locked thermal imager and according to a set sampling frequency. The evaluation and detection training module is used to construct an infrared detection experimental dataset for water accumulation in cable ties, input an extended causal temporal convolutional network model, train and optimize it to obtain an evaluation and detection model for water accumulation in cable ties. The defect detection module is used to input the infrared video data of the suspension cable into the water accumulation defect assessment and detection model of the suspension cable for assessment and detection, so as to obtain the result of water accumulation defect of bridge suspension cable.

8. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the rapid detection method for water accumulation in bridge suspension cables based on infrared phase-locked thermal imaging as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device is able to perform the rapid detection method for water accumulation in bridge suspension cables based on infrared phase-locked thermal imaging as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps in the rapid detection method for water accumulation in bridge suspension cables based on infrared phase-locked thermal imaging as described in any one of claims 1 to 6.

Images