A laser-based UAV bridge defect detection method and system

Abstract

The present invention relates to the technical field of bridge defect detection, and relates to a laser-based unmanned aerial vehicle (UAV) bridge defect detection method and system, the method comprising obtaining first information and second information; establishing a load model according to the first information and the second information, the load model being used to calculate the load borne by key nodes of the bridge; determining third information according to the load model, the third information comprising the life span corresponding to each key node of the bridge; judging whether the third information is less than a preset life span threshold, wherein when the third information is less than the preset life span threshold, obtaining a laser detection point; determining fourth information according to the laser detection point, the fourth information comprising a detection line of the UAV; detecting defects of key nodes of the UAV bridge according to the fourth information, the present invention determines the laser detection point of a laser scanner according to the life span corresponding to each key node, and then plans the detection line according to the laser detection point, thereby effectively improving the inspection efficiency of bridge defects.

Description

Technical Field

[0001] The present invention relates to the technical field of bridge defect detection, and in particular to a laser-based unmanned aerial vehicle bridge defect detection method and system. Background Art

[0002] Bridge defect detection is the key to ensuring the safety of bridge structures, eliminating bridge safety hazards, ensuring the safety and smooth operation of bridges, and reducing the occurrence of disasters and accidents. Existing technologies usually use drones to detect bridge defects, but the flight time of drones is limited, generally between tens of minutes and several hours. Bridge inspections usually need to cover a large area and a long route, and drones may need to take off and land multiple times to complete the inspection task, which not only increases the complexity of the operation, but also reduces the efficiency of defect detection. Summary of the invention

[0003] The purpose of the present invention is to provide a laser-based UAV bridge defect detection method and system to improve the above-mentioned problems.

[0004] In order to achieve the above objectives, the present application provides the following technical solutions:

[0005] On the one hand, an embodiment of the present application provides a laser-based drone bridge defect detection method, the method comprising:

[0006] Acquire first information and second information, wherein the first information includes historical traffic flow information of the bridge, and the second information includes environmental information of key nodes of the bridge, wherein the key nodes include locations where stress is concentrated;

[0007] Establishing a load model according to the first information and the second information, wherein the load model is used to calculate the load borne by the key nodes of the bridge;

[0008] Determining third information according to the load model, wherein the third information includes the life span corresponding to each key node of the bridge;

[0009] Determine whether the third information is less than a preset life threshold, wherein when the third information is less than the preset life threshold, obtain a laser detection point;

[0010] Determine fourth information according to the laser detection point, wherein the fourth information includes a detection route of the drone;

[0011] Defects of key nodes of the UAV bridge are detected based on the fourth information.

[0012] In a second aspect, an embodiment of the present application provides a laser-based drone bridge defect detection system, the system comprising:

[0013] An acquisition module, configured to acquire first information and second information, wherein the first information includes historical traffic flow information of the bridge, and the second information includes environmental information of key nodes of the bridge, wherein the key nodes include locations where stress is concentrated;

[0014] A first processing module, used for establishing a load model according to the first information and the second information, wherein the load model is used for calculating the load borne by the key nodes of the bridge;

[0015] A second processing module is used to determine third information according to the load model, wherein the third information includes the life span corresponding to each key node of the bridge;

[0016] A judging module, used to judge whether the third information is less than a preset life threshold, wherein when the third information is less than the preset life threshold, a laser detection point is acquired;

[0017] A third processing module, configured to determine fourth information according to the laser detection point, wherein the fourth information includes a detection route of the drone;

[0018] The fourth processing module is used to detect defects of key nodes of the UAV bridge according to the fourth information.

[0019] In a third aspect, an embodiment of the present application provides a laser-based drone bridge defect detection device, the device comprising a memory and a processor. The memory is used to store a computer program; the processor is used to implement the steps of the laser-based drone bridge defect detection method when executing the computer program.

[0020] In a fourth aspect, an embodiment of the present application provides a readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned laser-based UAV bridge defect detection method are implemented.

[0021] The beneficial effects of the present invention are:

[0022] The present invention calculates the load borne by the key nodes of the bridge by establishing a load model, and then determines the corresponding life of the key nodes according to the load borne by the key nodes of the bridge, so as to screen the laser detection points for the drone to perform laser detection according to the corresponding life of each key node, and plan the detection route of the drone according to the laser detection points, so as to avoid the need for the drone to return and recharge multiple times to complete the drone's inspection task, reduce the complexity of drone operation and improve the efficiency of defect detection.

[0023] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by implementing the embodiments of the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 Schematic diagram of the flow chart of the laser-based UAV bridge defect detection method described in an embodiment of the present invention.

[0026] Figure 2 Schematic diagram of the structure of the laser-based UAV bridge defect detection system described in an embodiment of the present invention.

[0027] Figure 3 It is a schematic diagram of the structure of the laser-based UAV bridge defect detection equipment described in an embodiment of the present invention.

[0028] Labels in the figure: 800, laser-based UAV bridge defect detection equipment; 801, processor; 802, memory; 803, multimedia component; 804, I / O interface; 805, communication component; 901, acquisition module; 902, first processing module; 903, second processing module; 904, judgment module; 905, third processing module; 906, fourth processing module. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0030] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0031] Embodiment 1:

[0032] This embodiment provides a laser-based drone bridge defect detection method. It can be understood that in this embodiment, a scene can be laid out, for example: using a drone equipped with laser equipment to detect bridge defects.

[0033] See also Figure 1 , the figure shows that the method includes step S1, step S2, step S3, step S4, step S5 and step S6, which specifically include:

[0034] Step S1, obtaining first information and second information, wherein the first information includes historical traffic flow information of the bridge, and the second information includes environmental information of key nodes of the bridge, wherein the key nodes include stress concentration locations;

[0035] In this step, the bridge nodes include stress concentration areas including but not limited to the mid-span area of ​​the beam, beam supports, and the connection between the pier top and the beam. The environmental information includes but is not limited to wind data, air composition data, sunshine data, rainfall data, and temperature data.

[0036] Step S2: establishing a load model according to the first information and the second information, wherein the load model is used to calculate the load borne by the key nodes of the bridge;

[0037] Under the influence of traffic flow and environment, the stability and integrity of the stress concentration points of the bridge are easily affected, resulting in defects. Therefore, in this step, the first information and the second information are collected to establish a model to explore the loads exerted on the bridge by traffic flow and environment, so as to accurately infer the life of the key nodes of the bridge.

[0038] The step S2 also includes step S21, step S22 and step S23, which specifically include:

[0039] Step S21, determining the types of vehicles passing through the bridge and the traffic flow corresponding to each type of vehicle according to the historical traffic flow information of the bridge;

[0040] Step S22, determining axle weight information corresponding to each vehicle according to the vehicle type;

[0041] In this step, the vehicle types include six types: sedan, passenger car, bus, small truck, medium truck, and large truck. The standard axle weight of each type of vehicle can be selected according to the design standards based on the traffic volume of each type of vehicle.

[0042] Step S23: Calculate the equivalent load according to the axle weight information corresponding to each vehicle type and the traffic flow corresponding to each vehicle type.

[0043] ;

[0044] In the above formula, W is the equivalent load, Indicates the proportion of different types of traffic flow, Indicates the axle weight information corresponding to different types of vehicles.

[0045] Step S3, determining third information according to the load model, wherein the third information includes the life span corresponding to each key node of the bridge;

[0046] In this step, the finite element analysis software is used to calculate the stress state of the key nodes under different load combinations, and then the stress amplitude is calculated; the fatigue damage degree is calculated based on the stress amplitude using the Miner linear cumulative damage criterion; and the remaining life of the key nodes is determined based on the fatigue damage degree.

[0047] Step S4, determining whether the third information is less than a preset life threshold, wherein when the third information is less than the preset life threshold, obtaining a laser detection point;

[0048] In this step, for key nodes whose life span is greater than the preset threshold, it means that their integrity has only been slightly affected and no inspection is required. For key nodes whose life span is less than the preset threshold, it means that there are greater safety hazards and they need to be inspected using drones.

[0049] Step S5, determining fourth information according to the laser detection point, wherein the fourth information includes a detection route of the drone;

[0050] In this step, the inspection route of the UAV is planned according to the multiple laser inspection points on the bridge, which greatly reduces the mileage of the UAV for bridge defect inspection, eliminates the need for multiple return flights for charging, and improves the inspection efficiency. Furthermore, the BIM model of the bridge can be obtained; the layout location of the UAV's charging facilities is determined according to the BIM model of the bridge and the laser inspection points of the UAV; the UAV charging equipment is installed according to the layout location of the charging facilities, and the UAV charging equipment is installed near the laser inspection points, which can further improve the UAV's endurance and improve the inspection efficiency.

[0051] The step S5 also includes step S51, step S52 and step S53, which specifically include:

[0052] Step S51, constructing a first three-dimensional map model with the bridge as the center and the motion range of the drone as the radius;

[0053] Since the flight altitude of the UAV also affects the endurance of the UAV, in this step, a first three-dimensional map model is established to plan the detection route of the UAV.

[0054] Step S52: Mapping the location information and laser detection points of the bridge to corresponding three-dimensional grid cells in the first three-dimensional map model to obtain a second three-dimensional map model;

[0055] In this step, the position information of the bridge in the first three-dimensional map model is determined based on the BIM model of the bridge, and the position information is mapped to the first three-dimensional map model to fill the first three-dimensional map model and mark it as a no-travel area to prevent the UAV from colliding with the bridge. At the same time, the laser detection points are mapped to the first three-dimensional map model as the target grid to obtain the second three-dimensional map model.

[0056] The step S52 also includes step S521, step S522, step S523, step S524 and step S525, which specifically include:

[0057] Step S521, obtaining wind direction information;

[0058] In this step, high-precision wind direction information is collected by using the laser wind measurement radar carried by the drone.

[0059] Step S522: Send the wind direction information to the wind direction prediction model to obtain a wind direction prediction result;

[0060] In this step, the wind direction prediction model is a nonlinear echo state network. Compared with the linear echo state network, the nonlinear echo state network can further reduce the complexity of model calculation by reducing the reserve pool neurons and reducing the dimensions of the weight matrix and feedback matrix inside the reserve pool. It can also increase the speed at which the wind direction prediction model outputs wind direction prediction results, thereby achieving real-time updates of wind direction predictions, avoiding UAVs from flying against the wind, reducing the UAV's endurance, and reducing the efficiency of bridge defect detection.

[0061] Step S523, calculating the angle between the UAV flight and the wind direction according to the wind direction prediction result and the UAV flight direction, to obtain a first calculation result;

[0062] Step S524, determining whether the first calculation result is less than a preset angle threshold, and obtaining a determination result;

[0063] In this step, the angle threshold is 90 degrees.

[0064] Step S525: fill the corresponding three-dimensional grid cells in the first three-dimensional map model according to the judgment result.

[0065] When the first calculation result is less than the preset angle threshold, it means that the UAV is flying with the wind, which can improve the UAV's endurance; when the first calculation result is greater than or equal to the preset angle threshold, it means that the UAV is flying against the wind, which will affect the UAV's endurance. Therefore, in this step, when the judgment result is that the first calculation result is greater than or equal to the preset angle threshold, the area corresponding to its wind direction is filled as an inaccessible area; when the judgment result is that the first calculation result is less than the preset angle threshold, the area corresponding to its wind direction is filled as a passable area.

[0066] In this embodiment, by considering the impact of wind direction on the flight endurance of the UAV, the area corresponding to headwind flight is marked as an inaccessible area, and the area corresponding to tailwind flight is marked as a passable area. By improving the endurance of the UAV, the purpose of improving the efficiency of UAV detection of bridge defects is achieved.

[0067] Step S53: Plan a detection route for the UAV according to the second three-dimensional map model to obtain fourth information.

[0068] In this step, there is no limitation on the algorithm for searching the drone detection route using the second three-dimensional map model.

[0069] Step S6: Detect defects of key nodes of the UAV bridge according to the fourth information.

[0070] The step S6 also includes step S61, step S62, step S63, step S64 and step S65, which specifically include:

[0071] Step S61, obtaining point cloud data at key nodes of the bridge;

[0072] In this step, the laser equipment carried by the drone is used to scan the key nodes of the bridge to obtain its three-dimensional point cloud data.

[0073] Step S62, performing denoising processing on the point cloud data at the key nodes of the bridge to obtain first point cloud data;

[0074] In this step, denoising the point cloud data is a technical solution well known to those skilled in the art, so it will not be described in detail here.

[0075] Step S63, performing registration processing on the first point cloud data to obtain second point cloud data;

[0076] The step S63 also includes step S631, step S632, step S633 and step S634, which specifically include:

[0077] Step S631, using a normal distribution transformation algorithm to perform a rough registration on the first point cloud data to obtain a transformation matrix;

[0078] Step S632: using a K-dimensional tree algorithm to search for corresponding information, where the corresponding information is the corresponding relationship between the target point cloud and the point cloud to be registered;

[0079] Step S633, using the Gauss-Newton method to solve the transformation matrix to obtain a second calculation result;

[0080] Step S634: determine whether the threshold information is satisfied according to the second calculation result, wherein, if it is less than the threshold information, the registration is terminated.

[0081] In this embodiment, since the registration accuracy of the point cloud data by the orthogonal distribution transformation algorithm is low, a rough registration is performed through the orthogonal distribution transformation algorithm to provide a transformation matrix, and then the transformation matrix is ​​used as the initial pose of the iterative closest point algorithm to further align the point cloud data. This ensures that the three-dimensional point cloud data completely restores the three-dimensional shape of defects at the key nodes of the bridge while improving the restoration speed.

[0082] Step S64: segment the second point cloud data using a clustering segmentation algorithm to obtain third point cloud data;

[0083] Step S65: Project the third point cloud data onto a two-dimensional plane to calculate the length and width of the defect to obtain a defect detection result.

[0084] In this step, the average normal vector at the defect is determined based on the third point cloud data; the average normal vector is subjected to coordinate transformation processing to obtain a coordinate transformation matrix; the coordinate transformation matrix is ​​projected onto a two-dimensional plane to obtain two-dimensional point cloud data; the length and width of the defect are determined based on the two-dimensional point cloud data. By projecting the three-dimensional point cloud at the key nodes of the bridge onto a two-dimensional plane, the dimension of data processing can be effectively reduced, the complexity of data processing can be reduced, and the detection accuracy and efficiency can be improved.

[0085] In this embodiment, the life of the key nodes of the bridge can be predicted through the defect detection results, so that the life of the key nodes detected by each laser detection point can be updated in real time. In the next round of defect detection, the detection route is re-planned according to the updated life of the key nodes, which improves the accuracy of the planned detection route and improves the efficiency of the drone for bridge defect detection.

[0086] Embodiment 2:

[0087] like Figure 2As shown, this embodiment provides a laser-based UAV bridge defect detection system, the system includes an acquisition module 901, a first processing module 902, a second processing module 903, a judgment module 904, a third processing module 905 and a fourth processing module 906, which specifically include:

[0088] An acquisition module 901 is used to acquire first information and second information, wherein the first information includes historical traffic flow information of the bridge, and the second information includes environmental information of key nodes of the bridge, wherein the key nodes include stress concentration locations;

[0089] A first processing module 902 is used to establish a load model according to the first information and the second information, wherein the load model is used to calculate the load borne by the key nodes of the bridge;

[0090] The second processing module 903 is used to determine third information according to the load model, wherein the third information includes the life span corresponding to each key node of the bridge;

[0091] A judgment module 904 is used to judge whether the third information is less than a preset life threshold, wherein when the third information is less than the preset life threshold, a laser detection point is obtained;

[0092] A third processing module 905 is used to determine fourth information according to the laser detection point, where the fourth information includes a detection route of the drone;

[0093] The fourth processing module 906 is used to detect defects of key nodes of the UAV bridge according to the fourth information.

[0094] In a specific embodiment of the present disclosure, the first processing module includes a first processing unit, a second processing unit and a third processing unit, which specifically include:

[0095] A first processing unit is used to determine the types of vehicles passing through the bridge and the traffic flow corresponding to each type of vehicle according to the historical traffic flow information of the bridge;

[0096] A second processing unit, used to determine axle weight information corresponding to each vehicle according to the vehicle type;

[0097] The third processing unit is used to calculate the equivalent load according to the axle weight information corresponding to each vehicle type and the traffic flow corresponding to each vehicle type.

[0098] In a specific embodiment of the present disclosure, the third processing module includes a fourth processing unit, a fifth processing unit and a sixth processing unit, which specifically include:

[0099] A fourth processing unit is used to construct a first three-dimensional map model with the bridge as the center and the movement range of the drone as the radius;

[0100] a fifth processing unit, configured to map the location information and the laser detection points of the bridge to corresponding three-dimensional grid cells in the first three-dimensional map model to obtain a second three-dimensional map model;

[0101] The sixth processing unit is used to plan a detection route of the UAV according to the second three-dimensional map model to obtain fourth information.

[0102] In a specific implementation of the present disclosure, the fifth processing unit includes a first acquisition unit, a seventh processing unit, an eighth processing unit, a judgment unit, and a ninth processing unit, which specifically include:

[0103] A first acquisition unit, used to acquire wind direction information;

[0104] The seventh processing unit is used to send the wind direction information to the wind direction prediction model to obtain a wind direction prediction result;

[0105] an eighth processing unit, configured to calculate an angle between the flight direction of the UAV and the wind direction according to the wind direction prediction result and the flight direction of the UAV, to obtain a first calculation result;

[0106] A judgment unit, used to judge whether the first calculation result is less than a preset angle threshold, and obtain a judgment result;

[0107] The ninth processing unit is used to fill the corresponding three-dimensional grid unit in the first three-dimensional map model according to the judgment result.

[0108] In a specific implementation of the present disclosure, the fourth processing module includes a second acquisition unit, a tenth processing unit, an eleventh processing unit, a twelfth processing unit and a thirteenth processing unit, which specifically include:

[0109] The second acquisition unit is used to acquire point cloud data at key nodes of the bridge;

[0110] a tenth processing unit, configured to perform denoising processing on the point cloud data at the key nodes of the bridge to obtain first point cloud data;

[0111] an eleventh processing unit, configured to perform registration processing on the first point cloud data to obtain second point cloud data;

[0112] a twelfth processing unit, configured to segment the second point cloud data using a clustering segmentation algorithm to obtain third point cloud data;

[0113] The thirteenth processing unit is used to project the third point cloud data onto a two-dimensional plane to calculate the length and width of the defect to obtain a defect detection result.

[0114] In a specific implementation of the present disclosure, the eleventh processing unit includes a fourteenth processing unit, a fifteenth processing unit, a sixteenth processing unit, and a seventeenth processing unit, which specifically include:

[0115] A fourteenth processing unit, configured to perform a rough registration on the first point cloud data using a normal distribution transformation algorithm to obtain a transformation matrix;

[0116] A fifteenth processing unit, configured to search for corresponding information using a K-dimensional tree algorithm, wherein the corresponding information is a corresponding relationship between a target point cloud and a point cloud to be registered;

[0117] A sixteenth processing unit, configured to solve the transformation matrix using a Gauss-Newton method to obtain a second calculation result;

[0118] A seventeenth processing unit is used to determine whether the threshold information is satisfied according to the second calculation result, wherein if it is less than the threshold information, the registration is terminated.

[0119] It should be noted that, regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0120] Embodiment 3:

[0121] Corresponding to the above method embodiment, a laser-based UAV bridge defect detection device is also provided in this embodiment. The laser-based UAV bridge defect detection device described below and the laser-based UAV bridge defect detection method described above can be referenced to each other.

[0122] Figure 3 8 is a block diagram of a laser-based drone bridge defect detection device 800 according to an exemplary embodiment. Figure 3 As shown, the laser-based UAV bridge defect detection device 800 may include: a processor 801, a memory 802. The laser-based UAV bridge defect detection device 800 may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0123] The processor 801 is used to control the overall operation of the laser-based UAV bridge defect detection device 800 to complete all or part of the steps in the above-mentioned laser-based UAV bridge defect detection method. The memory 802 is used to store various types of data to support the operation of the laser-based UAV bridge defect detection device 800, which may include, for example, instructions for any application or method operating on the laser-based UAV bridge defect detection device 800, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 802 or sent via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, and the above-mentioned other interface modules can be keyboards, mice, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the laser-based drone bridge defect detection device 800 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 can include: Wi-Fi module, Bluetooth module, NFC module.

[0124] In an exemplary embodiment, the laser-based UAV bridge defect detection device 800 can be implemented by one or more application-specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned laser-based UAV bridge defect detection method.

[0125] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned laser-based UAV bridge defect detection method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 802 including program instructions, and the above-mentioned program instructions can be executed by the processor 801 of the laser-based UAV bridge defect detection device 800 to complete the above-mentioned laser-based UAV bridge defect detection method.

[0126] Embodiment 4:

[0127] Corresponding to the above method embodiment, a readable storage medium is also provided in this embodiment. The readable storage medium described below and the laser-based UAV bridge defect detection method described above can be referenced to each other.

[0128] A readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the laser-based drone bridge defect detection method of the above-mentioned method embodiment.

[0129] The readable storage medium may specifically be a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or other readable storage medium that can store program codes.

[0130] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0131] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A laser-based UAV bridge defect detection method, characterized in that: include: Acquire first information and second information, wherein the first information includes historical traffic flow information of the bridge, and the second information includes environmental information of key nodes of the bridge, wherein the key nodes include locations where stress is concentrated; Establishing a load model according to the first information and the second information, wherein the load model is used to calculate the load borne by the key nodes of the bridge; Determining third information according to the load model, wherein the third information includes the life span corresponding to each key node of the bridge; Determine whether the third information is less than a preset life threshold, wherein when the third information is less than the preset life threshold, obtain a laser detection point; Determine fourth information according to the laser detection point, wherein the fourth information includes a detection route of the drone; Detect defects of key nodes of the drone bridge according to the fourth information; Wherein, determining the fourth information according to the laser detection point includes: The first three-dimensional map model is constructed with the bridge as the center and the movement range of the drone as the radius; Mapping the location information and laser detection points of the bridge to corresponding three-dimensional grid cells in the first three-dimensional map model to obtain a second three-dimensional map model; Planning a detection route of the UAV according to the second three-dimensional map model to obtain fourth information; The step of mapping the location information and the laser detection points of the bridge to corresponding three-dimensional grid cells in the first three-dimensional map model includes: Get wind direction information; Send the wind direction information to the wind direction prediction model to obtain the wind direction prediction result; Calculating the angle between the flight direction of the UAV and the wind direction according to the wind direction prediction result and the flight direction of the UAV to obtain a first calculation result; Determine whether the first calculation result is less than a preset angle threshold, and obtain a determination result, wherein the angle threshold is 90 degrees; Filling corresponding three-dimensional grid cells in the first three-dimensional map model according to the judgment result; When the judgment result is that the first calculation result is greater than or equal to the preset angle threshold, the area corresponding to the wind direction is filled as a non-passable area; When the judgment result is that the first calculation result is less than the preset angle threshold, the area corresponding to its wind direction is filled as a passable area.

2. The laser-based UAV bridge defect detection method according to claim 1 is characterized in that: Establishing a load model according to the first information and the second information includes: Determine the types of vehicles passing through the bridge and the traffic volume corresponding to each type of vehicle based on the historical traffic flow information of the bridge; Determine axle weight information corresponding to each vehicle according to the vehicle type; The equivalent load is calculated according to the axle weight information corresponding to each vehicle type and the traffic flow corresponding to each vehicle type.

3. The laser-based UAV bridge defect detection method according to claim 1 is characterized in that: Detecting defects of key nodes of the UAV bridge according to the fourth information includes: Obtain point cloud data at key nodes of the bridge; De-noising the point cloud data at the key nodes of the bridge to obtain first point cloud data; Performing registration processing on the first point cloud data to obtain second point cloud data; Segmenting the second point cloud data using a clustering segmentation algorithm to obtain third point cloud data; The third point cloud data is projected onto a two-dimensional plane to calculate the length and width of the defect to obtain a defect detection result.

4. The laser-based UAV bridge defect detection method according to claim 3 is characterized in that: Performing registration processing on the first point cloud data includes: The first point cloud data is roughly registered using the normal distribution transformation algorithm to obtain a transformation matrix; Using a K-dimensional tree algorithm to search for corresponding information, the corresponding information is the corresponding relationship between the target point cloud and the point cloud to be registered; The transformation matrix is ​​solved by using the Gauss-Newton method to obtain a second calculation result; It is determined whether the threshold information is satisfied according to the second calculation result, wherein the registration is terminated if the threshold information is less than the threshold information.

5. A laser-based UAV bridge defect detection system, characterized in that: include: An acquisition module, configured to acquire first information and second information, wherein the first information includes historical traffic flow information of the bridge, and the second information includes environmental information of key nodes of the bridge, wherein the key nodes include locations where stress is concentrated; A first processing module, used for establishing a load model according to the first information and the second information, wherein the load model is used for calculating the load borne by the key nodes of the bridge; A second processing module is used to determine third information according to the load model, wherein the third information includes the life span corresponding to each key node of the bridge; A judging module, used to judge whether the third information is less than a preset life threshold, wherein when the third information is less than the preset life threshold, a laser detection point is acquired; A third processing module, configured to determine fourth information according to the laser detection point, wherein the fourth information includes a detection route of the drone; a fourth processing module, configured to detect defects of key nodes of the UAV bridge according to the fourth information; Wherein, the third processing module includes: A fourth processing unit is used to construct a first three-dimensional map model with the bridge as the center and the movement range of the drone as the radius; a fifth processing unit, configured to map the location information and the laser detection points of the bridge to corresponding three-dimensional grid cells in the first three-dimensional map model to obtain a second three-dimensional map model; a sixth processing unit, configured to plan a detection route of the UAV according to the second three-dimensional map model to obtain fourth information; Wherein, the fifth processing unit comprises: A first acquisition unit, used to acquire wind direction information; The seventh processing unit is used to send the wind direction information to the wind direction prediction model to obtain a wind direction prediction result; an eighth processing unit, configured to calculate an angle between the flight direction of the UAV and the wind direction according to the wind direction prediction result and the flight direction of the UAV, to obtain a first calculation result; A judging unit, configured to judge whether the first calculation result is less than a preset angle threshold, and obtain a judging result, wherein the angle threshold is 90 degrees; a ninth processing unit, configured to fill corresponding three-dimensional grid cells in the first three-dimensional map model according to the judgment result; When the judgment result is that the first calculation result is greater than or equal to the preset angle threshold, the area corresponding to the wind direction is filled as a non-passable area; When the judgment result is that the first calculation result is less than the preset angle threshold, the area corresponding to its wind direction is filled as a passable area.

6. The laser-based UAV bridge defect detection system according to claim 5 is characterized in that: The first processing module comprises: A first processing unit is used to determine the types of vehicles passing through the bridge and the traffic flow corresponding to each type of vehicle according to the historical traffic flow information of the bridge; A second processing unit, used to determine axle weight information corresponding to each vehicle according to the vehicle type; The third processing unit is used to calculate the equivalent load according to the axle weight information corresponding to each vehicle type and the traffic flow corresponding to each vehicle type.

Images