Ground displacement monitoring system based on Beidou No.3

By using the BeiDou-3 unmanned aerial vehicle system, and by employing flight cost functions and trajectory optimization algorithms, ground displacement detection equipment can be automatically deployed, solving the problem of low efficiency in manual deployment and achieving efficient and accurate ground displacement monitoring.

CN119001786APending Publication Date: 2024-11-22HENAN DONGSHENG INTELLIGENT CONTROL TECH CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411128585.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-16
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

The existing technology requires a large amount of labor costs and is inefficient in deploying ground displacement detection equipment to the target area.

Method used

Using a BeiDou-3-based unmanned aerial vehicle (UAV) system, the UAV is controlled by flight cost function and trajectory optimization algorithm to deploy on-site detection equipment to preset detection points in the target area, and ground displacement is monitored using acceleration and position information.

Benefits of technology

It reduces the cost of deploying detection equipment, improves work efficiency, and can accurately monitor ground displacement.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119001786A_ABST
    Figure CN119001786A_ABST
Patent Text Reader

Abstract

The invention provides a ground displacement monitoring system based on Beidou No.3, and the system comprises a plurality of on-site detection devices, and each on-site detection device comprises an acceleration detection device and a positioning device based on Beidou No.3; the plurality of unmanned aerial vehicles are used for putting the field detection devices to the preset detection points respectively; and the monitoring information processing equipment is configured to control the unmanned aerial vehicle to put the field detection equipment, and monitor the ground displacement of the target area according to the acceleration information and the position information. According to the technical scheme of the invention, the monitoring information processing device can adopt the flight cost function, obtain the optimal delivery strategy of each field detection device according to the position of each preset detection point in the target area, and then control each unmanned aerial vehicle according to the optimal delivery strategy, so that the cost of delivering each field detection device can be reduced, and the unmanned aerial vehicle delivery efficiency is improved. And moreover, the working efficiency of putting the field detection equipment can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of geological disaster monitoring, and in particular to a ground displacement monitoring system based on BeiDou-3. Background Art

[0002] Geological disasters refer to phenomena or processes that endanger human life and property, life and economic activities, or destroy the resources and environment on which humans depend for survival and development, such as abnormal energy release, material movement, deformation and displacement of rock and soil bodies, and abnormal environmental changes caused by the earth's internal and external forces or artificial geological forces. It includes both disasters caused by natural factors and disasters induced by human activities.

[0003] BeiDou-3 is a global satellite navigation system independently developed by China. The system has global coverage capabilities and can accurately locate targets around the world. It also uses this positioning capability to monitor targets in the target area and can accurately detect ground displacement information in the target area.

[0004] In the prior art, the method of deploying detection equipment to the target area is that the staff first sets up the detection points according to the terrain information of the target area, and then manually places the detection equipment at the detection points. This process requires a lot of labor costs and has the problem of low efficiency. Summary of the invention

[0005] The present invention provides a ground displacement monitoring system based on BeiDou-3, which is used to control a drone to place various on-site detection equipment into a target area, so as to reduce the cost of placing various on-site detection equipment and improve the work efficiency of the placement.

[0006] Specifically, the present invention provides a ground displacement monitoring system based on BeiDou-3, comprising:

[0007] A plurality of on-site detection devices, which are respectively used to be set at each preset detection point in the target area, and each of the on-site detection devices includes an acceleration detection device and a positioning device based on Beidou-3, wherein the acceleration detection device is used to collect acceleration information of the on-site detection device, and the positioning device is used to collect position information of the on-site detection device;

[0008] A plurality of drones, which are used to respectively place the on-site detection equipment at the preset detection points;

[0009] A monitoring information processing device, which is communicatively connected with each of the on-site detection devices and each of the drones, and is configured to: control the drone to drop each of the on-site detection devices, and monitor the ground displacement of the target area according to the acceleration information and the position information;

[0010] Wherein, controlling the drone to place each of the on-site detection equipment includes:

[0011] Obtaining an optimal flight path between each of the preset detection points, and obtaining an optimal flight path between each of the preset detection points and a preset starting position;

[0012] Obtaining a flight cost function, using the flight cost function to obtain an optimal delivery strategy according to each of the optimal flight paths, and controlling each of the drones according to the optimal delivery strategy to deliver each of the on-site detection equipment to a corresponding preset detection;

[0013] The method of adopting the flight cost function and obtaining the optimal delivery strategy according to each of the optimal flight paths includes:

[0014] Acquire multiple preset delivery strategies, and use the flight cost function to calculate the flight cost of the drone executing each of the preset delivery strategies, including:

[0015] Assume that the preset detection points in the preset delivery strategy are divided into N detection groups, and the flight cost of the UAV executing the preset delivery strategy is P, then

[0016]

[0017] Among them, F n represents the flight cost of the UAV to deliver the on-site inspection equipment to the nth inspection group, and

[0018]

[0019] In the above formula, M n is the number of preset detection points in the nth detection group, h(M n ) represents the flight correction factor of the nth detection group, h(M n -m) represents the correction coefficient of the mth flight track in the nth detection group, f() is the flight cost function, L n,1 represents the flight path from the first detection point in the nth detection group to the preset starting position, Indicates the Mth detection group in the nth detection group n The flight path between the detection point and the preset starting position, l n,m represents the flight path of the mth track point and the m+1th track point in the nth detection group;

[0020] The preset delivery strategy with the minimum flight cost is used as the optimal delivery strategy.

[0021] Furthermore, the obtaining of the optimal flight path between the preset detection points includes:

[0022] It is determined whether there is a flight obstacle area between the preset detection points, and a flight path between the preset detection points is obtained according to the flight obstacle area.

[0023] Furthermore, the step of obtaining the optimal flight path between each of the preset detection points and the preset starting position includes:

[0024] Obtaining a preset number of track points corresponding to each of the preset detection points according to the distance between each of the preset detection points and the preset starting position;

[0025] A preset track optimization algorithm is used to obtain the optimal solution of each of the preset detection points, and based on the optimal solution of each of the preset detection points, an optimal flight path between each of the preset detection points and the preset starting position is obtained.

[0026] Furthermore, the preset track optimization algorithm is a non-monopolistic optimization algorithm.

[0027] Furthermore, the flight cost function includes a flight length cost function, a flight turning angle cost function and a flight pitch angle cost function.

[0028] Furthermore, the drone is configured to: after placing the on-site detection equipment at the corresponding preset detection point, send a placement completion message to the monitoring information processing device;

[0029] The monitoring information processing device is configured to: after receiving the delivery completion information, send activation information to the on-site detection device to control the on-site detection device to start working.

[0030] Furthermore, the detection information processing device is also configured to: determine whether each of the on-site detection devices has been illegally moved based on the acceleration signal and the position information, and track the illegally moved on-site detection devices.

[0031] Further, monitoring the ground displacement of the target area according to the acceleration information and the position information includes:

[0032] Obtain a pre-trained ground displacement monitoring model;

[0033] The acceleration signals and the position information are input into the ground displacement monitoring model to obtain the ground displacement information.

[0034] Furthermore, the method of obtaining a pre-trained ground displacement monitoring model includes:

[0035] Constructing a three-dimensional simulation model of the target area, and setting a field detection equipment model in the three-dimensional simulation model according to each of the preset detection points;

[0036] Simulating a variety of geological disasters in the three-dimensional simulation model, and obtaining acceleration information and displacement information detected by each of the on-site detection equipment models under each of the geological disasters;

[0037] A pre-training data set is constructed according to the acceleration information and displacement information detected by each of the on-site detection equipment models, and the ground displacement monitoring model is trained using the pre-training data set to obtain the pre-trained ground displacement monitoring model.

[0038] Furthermore, the construction of the three-dimensional simulation model of the target area includes:

[0039] Acquire a three-dimensional electronic map of the target area, and load the three-dimensional electronic map into a three-dimensional coordinate system to obtain an initial three-dimensional model of the target area;

[0040] The geology of the initial three-dimensional model is configured according to the geological information of the target area to obtain the three-dimensional simulation model.

[0041] In the technical solution of the present invention, the monitoring information processing equipment can adopt a flight cost function to obtain the optimal deployment strategy for each field detection equipment according to the position of each preset detection point in the target area, and then control each drone according to the optimal deployment strategy. The field detection equipment can be deployed to each preset detection point in the target area with the minimum flight cost. No human participation is required in this process. Therefore, it can not only reduce the cost of deploying each field detection equipment, but also improve the work efficiency of deploying each field detection equipment.

[0042] Based on the following detailed description of specific embodiments of the present invention in conjunction with the accompanying drawings, those skilled in the art will become more aware of the above and other objects, advantages and features of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Hereinafter, some specific embodiments of the present invention will be described in detail in an exemplary and non-limiting manner with reference to the accompanying drawings. The same reference numerals in the accompanying drawings indicate the same or similar components or parts. It should be understood by those skilled in the art that these drawings are not necessarily drawn to scale. In the accompanying drawings:

[0044] Figure 1 is a schematic structural diagram of a ground displacement monitoring system based on BeiDou-3 according to an embodiment of the present invention;

[0045] Figure 2is a schematic diagram of controlling a drone to place a field inspection device at a preset inspection point in a target area according to an embodiment of the present invention;

[0046] Figure 3 is a schematic flow chart of obtaining an optimal delivery strategy according to an embodiment of the present invention;

[0047] Figure 4 is a schematic flow chart of obtaining an optimal flight path between two preset detection points according to an embodiment of the present invention;

[0048] Figure 5 is a schematic flow chart of obtaining an optimal flight path between a preset detection point and a preset starting position according to an embodiment of the present invention;

[0049] Figure 6 is a schematic flow chart of obtaining ground displacement data of a target area according to an embodiment of the present invention;

[0050] Figure 7 is a schematic flow chart of obtaining a pre-trained ground displacement monitoring model according to an embodiment of the present invention;

[0051] Figure 8 is a schematic flow chart of constructing a three-dimensional simulation model of a target area according to an embodiment of the present invention. DETAILED DESCRIPTION

[0052] Refer to the following Figures 1 to 8 To describe a ground displacement monitoring system based on BeiDou-3 according to an embodiment of the present invention. In the description of this embodiment, it should be understood that the terms "first" and "second" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features, that is, include one or more of the features. In the description of the present invention, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. When a feature "includes or contains" one or some of the features it covers, unless otherwise specifically described, this indicates that other features are not excluded and may further include other features.

[0053] Figure 1 It is a structural schematic diagram of a ground displacement monitoring system based on BeiDou-3 according to an embodiment of the present invention. The ground displacement system includes a monitoring information processing device 11, multiple field detection devices 12 and multiple drones 13, wherein each field detection device 12 includes an acceleration detection device 111 and a positioning device 112 based on BeiDou-3.

[0054] Each drone 13 is provided with a plurality of mounting positions, and the drone 13 can mount the field detection equipment 12 through the mounting positions, and after transporting each field detection equipment 12 to the preset detection point of the target area, the field detection equipment 12 is placed at the preset detection point by controlling the mounting position action. For example, the mounting can be a controllable mechanical claw, and the field detection equipment 12 can be mounted on the mounting position of the drone 13 when the mechanical claw is controlled to be tightened, and the field detection equipment 12 can be placed when the mechanical claw is controlled to be loosened. The acceleration detection device 111 of the field detection equipment 12 can detect the acceleration information of the field detection equipment 12, and the positioning device 112 can detect the position information of the field detection equipment 12.

[0055] The monitoring information processing device 11 is communicatively connected with each on-site detection device 12 and each drone 13, and can control the drone 13 to deploy the on-site detection device 12 to each preset detection point in the target area, and obtain the acceleration information and position information of each on-site detection device 12, and obtain the ground displacement information of the target area based on the acceleration information and position information of each on-site detection device 12.

[0056] In this embodiment, the number and position of each preset detection point in the target area are set according to the terrain information and geological information of the target area, and the setting method can be manually set by a staff member, or automatically set by a computer device using a preset computer program according to the terrain information and geological information of the target area. The method of setting the preset detection points in the target area includes: setting the distance between adjacent preset detection points in each area according to whether the geology and terrain of each area in the target area are prone to ground displacement, wherein the more prone the terrain and geology of a certain area are to ground displacement, the greater the distance between adjacent preset detection points in the area. For example, a hillside area is more prone to ground displacement than a flat area, so the distance between adjacent preset detection points on the hillside area is greater than the distance between adjacent preset detection points on the flat area; a soil area is more prone to ground displacement than a rock area, so the distance between adjacent preset detection points on the soil area is greater than the distance between adjacent preset detection points on the rock area.

[0057] In this embodiment, the detection distance corresponding to each type of terrain and geology can be set first, and then the corresponding detection distance can be found according to the terrain information and geological information of each area in the target area, and the detection distance can be used as the distance between adjacent preset detection points in the corresponding area. Finally, according to the size of each area in the target area and the distance between adjacent preset detection points in each area, the number of preset detection points and the position of each preset detection point are determined.

[0058] In this embodiment, the method of controlling the drone to place the on-site detection equipment at each preset detection point in the target area by the monitoring information processing device 11 is as follows: Figure 2As shown, the following steps are included:

[0059] Step S101, obtaining an optimal flight path between each preset detection point, and obtaining an optimal flight path between each preset detection point and a preset starting position;

[0060] Step S102, obtaining a flight cost function, and obtaining an optimal delivery strategy based on the flight cost function and an optimal flight path between each preset detection point and an optimal flight path between each preset detection point and a preset starting position;

[0061] Step S103 , controlling the drone 13 according to the optimal delivery strategy to deliver each on-site detection device 12 to each preset detection point in the target area.

[0062] In the above step S101, the optimal flight path between the preset detection points refers to the flight path with the lowest flight cost when the drone 13 flies between the preset detection points; correspondingly, the optimal flight path between the preset detection points and the preset starting position refers to the flight path with the lowest flight cost when the drone 13 flies between the preset detection points and the preset starting position.

[0063] In the above step S102, the method for obtaining the optimal delivery strategy according to the flight cost function is as follows: Figure 3 As shown, the following steps are included:

[0064] Step S111, obtaining a plurality of preset delivery strategies according to the optimal flight path between the preset detection points and the optimal flight path between the preset detection points and the preset starting position;

[0065] Step S112, calculating the flight cost of the drone 13 executing each preset delivery strategy, and taking the preset delivery strategy with the smallest flight cost as the optimal delivery strategy.

[0066] In the above step S111, the method for obtaining multiple preset delivery strategies is to group the preset detection points according to different grouping strategies, the number of detection groups obtained by each grouping strategy is not greater than the number of drones 13, and the number of preset detection points in each detection group is not greater than the maximum mounting capacity of the drone.

[0067] In the above step S112, taking one of the preset delivery strategies as an example, the method for calculating the flight cost of each drone 13 executing the preset delivery strategy includes:

[0068] Assume that the preset detection points in one of the preset delivery strategies are divided into N detection groups, and the flight cost of the drone 13 executing the preset delivery strategy is P, then

[0069]

[0070] Among them, F n represents the flight cost of the drone 13 to deliver the on-site inspection equipment 12 to the nth inspection group, and

[0071]

[0072] In the above formula, M n is the number of preset detection points in the nth detection group, h(M n ) represents the flight correction factor of the nth detection group, h(M n -m) represents the correction coefficient of the mth flight track in the nth detection group, f() is the flight cost function, L n,1 represents the flight path from the first detection point in the nth detection group to the preset starting position, Indicates the Mth detection group in the nth detection group n The flight path between the detection point and the preset starting position, l n,m Represents the flight path of the mth track point and the m+1th track point in the nth detection group.

[0073] In the above step S103, it is assumed that the preset detection points are divided into N' detection groups in the optimal delivery strategy, where the number of preset detection groups in the nth detection group is M' n , then the method for controlling the drone to release the on-site detection equipment 12 according to the optimal release strategy is:

[0074] Get N' drones and mount M' on the nth drone n On-site detection equipment 12; then control the nth UAV to fly to the first preset detection point in the nth detection group, and after dropping a field detection equipment 12 at the first preset detection point, fly to the second preset detection point; and so on, after the UAV completes the dropping of all the mounted field detection equipment 12, it flies back to the preset starting point from the last preset detection point in the nth detection group to complete the dropping of the field detection equipment 12 to the nth detection group.

[0075] By controlling N' drones to drop the on-site detection equipment 12 to the preset detection points in each detection group, the on-site detection equipment 12 can be arranged at each preset detection point in the target area to monitor the ground displacement of the target area.

[0076] To sum up, in the technical solution of this embodiment, the monitoring information processing device 11 can adopt a flight cost function to obtain the optimal delivery strategy of each field detection device 12 according to the position of each preset detection point in the target area, and then control each drone 13 according to the optimal delivery strategy. The field detection equipment 12 can be delivered to each preset detection point in the target area with the minimum flight cost. No human intervention is required in this process. Therefore, it can not only reduce the cost of delivering each field detection equipment 12, but also improve the work efficiency of delivering each field detection equipment 12.

[0077] In some embodiments of the present invention, the method of obtaining the optimal flight path between the preset detection points in the above step S101 includes:

[0078] It is determined whether there is a flight obstacle area between each preset detection point, and the optimal flight path between each preset detection point is obtained according to the flight obstacle area.

[0079] In this embodiment, two preset detection points are taken as an example. The method for obtaining the optimal flight path between the two preset detection points is as follows: Figure 4 As shown, the following steps are included:

[0080] Step S121, determining whether there is a flight obstacle area between two preset detection points;

[0081] If not, execute step S122; if yes, execute step S123;

[0082] Step S122, obtaining a straight line path between two preset detection points, and using the straight line path as the optimal flight path between the two preset detection points;

[0083] Step S123, obtaining a straight line path between two preset detection points, and adjusting the straight line path multiple times according to the flight obstacle area between the two preset detection points to obtain multiple preset flight paths;

[0084] Step S124, using a flight cost function to calculate the flight costs of each preset flight path, and taking the preset flight path with the smallest flight cost as the optimal flight path between the two preset detection points.

[0085] In the above step S121, the flight obstacle area refers to an area that may affect the flight of the drone 13, such as a radar area or other area where there is strong electromagnetic signal interference, or an area where a utility pole or other area may collide with the drone 13.

[0086] In the above step S122, the straight line path between the two preset detection points obtained is the shortest path between the two preset detection points. After taking the straight line path as the optimal flight path between the two preset detection points, the UAV 13 is controlled according to the optimal flight path, which can reduce the flight cost of the UAV 13.

[0087] In the above step S123, the method for adjusting the straight path includes: dividing the straight path into multiple flight segments, with branch points between each flight segment; then adjusting each branch point in the flight obstacle area in multiple directions to move each branch point in the flight obstacle area to the outside of the flight obstacle area; finally, connecting the adjusted branch points in each direction respectively to obtain multiple preset flight paths, wherein each direction corresponds to a preset flight path.

[0088] In the above step S124, the flight path with the lowest flight cost among the multiple preset flight paths is used as the optimal flight path. When the drone is controlled according to the optimal flight path, the flight cost of the drone can be reduced.

[0089] Through the technical solution of this embodiment, the flight path between the preset detection points can be obtained according to whether there is a flight obstacle area between the preset detection points, so that the flight path between the preset detection points is the shortest or the flight cost is the lowest, thereby ensuring that the flight cost of the drone executing various delivery strategies can be accurately calculated, and ensuring the accuracy of obtaining the optimal delivery strategy.

[0090] In some embodiments of the present invention, the method of obtaining the optimal flight path between each preset detection point and the preset starting position in the above step S101 includes:

[0091] The distance between each preset detection point and the preset starting position is obtained, and the preset track optimization algorithm is used to obtain the optimal flight path between each preset detection point and the preset starting position according to the distance between each preset detection point and the preset starting position.

[0092] In this embodiment, taking one of the preset detection points as an example, the method for obtaining the optimal flight path between the preset detection point and the preset starting position is as follows: Figure 5 As shown, the following steps are included:

[0093] Step S201, setting a preset number of track points according to the distance between the preset detection point and the preset starting position;

[0094] Step S202, using a preset track optimization algorithm, iteratively updating the position of each track point according to the flight cost function to obtain the optimal solution for each track point;

[0095] Step S203, constructing an optimal flight path between a preset detection point and a preset starting position according to the optimal solution of each track point.

[0096] In the above step S201, the greater the distance between the preset detection point and the preset starting position, the greater the preset number of track points set. Therefore, in this embodiment, a corresponding relationship between the distance and the preset number can be established in advance, and then when the distance between the preset detection point and the preset starting position is obtained, the preset number of track points is obtained based on the distance and the above corresponding relationship.

[0097] In the above step S202, each track point is iteratively updated using a preset track optimization algorithm; after each iterative update, the flight cost of the preset flight path formed by each track point is calculated using a flight cost function, and then the position of each track point when the flight cost is minimized is used as the optimal solution for each track point.

[0098] In the above step S203, each track point can be connected in sequence, and the first track point can be connected to the preset rider position, and the last track point can be connected to the preset detection point to construct an optimal flight path between the preset detection point and the preset starting position. This optimal flight path can ensure that the flight cost of the drone 13 is minimized during the process of controlling the drone 13 to deliver the on-site detection equipment 12.

[0099] Through the technical solution of this embodiment, a preset track optimization algorithm can be used to obtain the optimal flight path between each preset detection point and the preset starting position, thereby reducing the flight cost of controlling each drone 13 to deploy each on-site detection equipment 12 to ensure the reliability of the deployment of each on-site detection equipment 12.

[0100] In some embodiments of the present invention, the preset track optimization algorithm is a non-monopolistic optimization algorithm, and the method of updating each track point using the non-monopolistic optimization algorithm includes:

[0101] First, obtain the candidate solution population of each track point and initialize the candidate solution population;

[0102] Then, the initialized candidate solution population is optimized for multiple iterations to obtain the optimal solution for each track point;

[0103] Finally, a non-monopolistic optimization algorithm is used to update the position of each track point.

[0104] In this embodiment, the method for initializing the candidate solution population for each track point includes:

[0105] First, obtain the search range of each track point;

[0106] In this embodiment, the height direction is the z-axis delay direction of the search range, and the horizontal plane is the plane determined by the x-axis and the z-axis, where the lower boundaries of the x-axis, y-axis and z-axis are all 0, and the upper boundary of the x-axis is x. max , the upper boundary of the y-axis is y max , the upper boundary of the z-axis is z max , so the search range of each track point is:

[0107] O={(x,y,z)|0≤x≤xmax,0≤y≤ymax,0≤z≤zmax}

[0108] Then, the initial position of each track point is randomly generated within the search range to initialize the candidate solution population. Assume that there are I candidate solutions in the candidate solution population, of which the i-th candidate solution is K i , and the coordinates of the t-th track point in the i-th candidate solution are (x i,t ,y i,t ,z i,t ), then after encoding each candidate solution in the candidate solution population, the i-th candidate solution K i for:

[0109] K i =[x i,1 ,y i,1 ,z i,1 ,x i,2 ,y i,2 ,z i,2 ,......x i,T ,y i,T ,z i,T ]

[0110] In this embodiment, in the process of updating the position of each track point using the non-monopolistic optimization algorithm, the number of iterative updates is set to r. If r is less than the preset iteration threshold, it is in the exploration stage; if r is greater than or equal to the preset iteration threshold, it is in the development stage.

[0111] In the exploration phase, the following calculation formula is used to update the position of each track point:

[0112] K i (r) = K i (r-1)+τ[K best (r-1)-K i (r-1)]

[0113] Among them, K i (r) is the i-th candidate solution in the candidate solution population after the r-th iteration update, K best(r-1) is the optimal candidate solution in the candidate solution population before the r-th iterative update, τ is a random number, and the value range of the random number is greater than or equal to -1 and less than or equal to 1.

[0114] In this embodiment, the best candidate solution K in the candidate solution population before the rth iteration update is obtained. best The method of (r-1) includes: before the rth iteration update, using the flight cost function to calculate the flight cost of each candidate solution in the candidate solution population, and taking the candidate solution with the smallest flight cost as the optimal candidate solution. The method of calculating the flight cost of the candidate solution includes: connecting the first track point in the candidate solution with the preset starting position, and connecting the last track point of the candidate solution with the preset detection point to form a flight track; then using the flight cost function of the drone to calculate the flight cost of the flight track, and the flight cost is the flight cost of the candidate solution.

[0115] During the development phase, the following calculation formula is used to update the position of each track point:

[0116] Obtain a random value b, and determine whether the random value b is greater than a set threshold, where the set threshold is preferably 0.5;

[0117] When the random value b is greater than the above-set threshold, the following calculation formula is used to update each candidate solution in the candidate solution population:

[0118] K i (r) = K i (r-1)-A*D

[0119] Where A is a random value generated according to the number of iterations, D is a random candidate solution generated according to the best candidate solution in the candidate solution population before the rth iteration update, and

[0120] A=2(1-r / R)(2v1-1)

[0121] D=|2v2×K best (r-1)-K i (r-1)

[0122] In the above formula, v1 and v2 are both random values ​​in the range of [0,1], and R is the total number of iterative updates. Parameters A and D in this embodiment can help the improved non-monopoly search algorithm to search in the current last candidate solution and its vicinity to achieve a fast convergence effect.

[0123] When the random value b is less than or equal to the set threshold, the following calculation formula is used to update each candidate solution in the candidate solution population:

[0124] K i(r) = K i (r-1)-[K SRP (r-1)*rand]*eps-[K i (r)-NO]

[0125] Among them, eps represents a small value, that is, a value greater than 0 and less than 1; K SRP (r-1) is the random candidate solution before the development phase update in the rth iterative update; NO is a tuning parameter, and the tuning parameter is preferably 1.

[0126] Through the technical solution of this embodiment, not only can the non-monopoly optimization algorithm be used to obtain the optimal solution for each track point, but the optimal candidate solution is introduced in the exploration stage of the non-monopoly optimization algorithm, and the convergence speed of the non-monopoly optimization algorithm can also be accelerated.

[0127] In some embodiments of the present invention, the flight cost function includes a flight length cost function, a flight turning angle cost function, and a flight pitch angle cost function.

[0128] In this embodiment, the flight length cost function is assumed to be f disl , the flight angle cost function is f turn , the flight pitch angle cost function is f up , the flight cost function is f, then

[0129] f=αf dis +βf turn +γf up

[0130] Among them, α is the weight of the flight length cost function, β is the weight of the flight angle cost function, γ is the weight of the flight pitch angle cost function, and

[0131] α+β+γ=1

[0132] The above flight length cost function f disl for

[0133]

[0134] In the above formula, the preset starting position is taken as the first track point, the preset detection point is taken as the T+1th track point, and (x n ,y n ,z n ) represents the coordinates of the nth track point, (x n-1 ,y n-1 ,z n-1 ), T is the total number of track points.

[0135] The above flight angle cost function f turn for

[0136]

[0137] where δ n Indicates the deflection angle of the drone at the nth track point.

[0138] The above flight pitch angle cost function f up for

[0139]

[0140] where θ n Indicates the pitch angle of the drone at the nth track point.

[0141] In this embodiment, the method for calculating the deflection angle and pitch angle of the drone includes:

[0142] First, the turning angle of the drone at each track point is calculated using the following formula:

[0143]

[0144] In the above calculation formula, φ n is the turning angle of the UAV at the nth track point, Represents the vector from the nth track point to the n-1th track point, W n It represents the nth track point, and takes the preset monitoring point as the N+1th track point.

[0145] Then, the component of the UAV's turning angle at each track point in the height direction (i.e., the z-axis direction) is taken as the corresponding pitch angle, and the component in the horizontal plane (i.e., the plane determined by the x-axis and y-axis) is taken as the corresponding deflection angle. n The component in the height direction (i.e., z-axis direction) is θ n , the component on the horizontal plane (i.e. the plane defined by the x-axis and the y-axis) is δ n .

[0146] Through the technical solution of this embodiment, the constructed flight cost function can comprehensively calculate the flight cost of the drone 13 according to the flight length, flight turning angle and flight pitch angle of the drone 13, thereby ensuring the reliability of the obtained optimal delivery strategy, so that when the drone 13 delivers each on-site detection equipment 12 according to the optimal delivery strategy, the flight cost of each drone 13 is reduced.

[0147] In some embodiments of the present invention, the drone 13 is further configured to:

[0148] After each time the on-site detection device 12 is placed at the corresponding preset detection point, the corresponding placement completion information is sent to the monitoring information processing device 11;

[0149] Accordingly, the monitoring information processing device 11 is also configured to:

[0150] After receiving the delivery completion information from the drone 13 , the delivered on-site detection device 12 is identified, and activation information is sent to the on-site detection device 12 to control the on-site detection device 12 to start working.

[0151] In this embodiment, a corresponding number can be set for each field detection device 12, and after each field detection device 12 is mounted on the drone 13, the number of the field detection device 12 mounted at each position on the drone 13 is saved. After the drone 13 drops the field detection device 12 at the preset detection point, the drone 13 obtains the number of the dropped field detection device 12 according to the mounting position of the dropped field detection device 12, and sends the drop completion information containing the number to the monitoring information processing device 11.

[0152] After receiving the delivery completion information, the monitoring information processing device 11 can obtain the number of the field detection device 12 that has been delivered according to the delivery completion information, and obtain the corresponding communication address according to the number, and then send activation information to the corresponding field detection device 12 according to the communication address to activate the field detection device 12. After receiving the activation information, the field detection device 12 controls the acceleration detection device 111 and the positioning device 112 of the field detection device 12 to start working to detect the acceleration and position information of the field detection device.

[0153] Through the technical solution of this embodiment, after each field detection device 12 is placed at a corresponding preset detection point, each field detection device 12 can be activated to control the acceleration detection device 111 and the positioning device 112 of each field detection device 12 to start working, thereby reducing the power consumption of each field detection device 12 and reducing the amount of data collected by each field detection device 12, thereby improving the accuracy and reliability of ground movement information monitoring in the target area.

[0154] In some embodiments of the present invention, the monitoring information processing device 11 is further configured to:

[0155] After the acceleration signal and the position signal are acquired from each on-site detection device 12 , it is determined whether each on-site detection device 12 is moved.

[0156] In this embodiment, the method for determining whether each on-site detection device 12 is moved includes:

[0157] According to the acceleration signal and the position signal of each field detection device 12, it is determined whether the moving distance of each field detection device 12 is greater than the set distance;

[0158] If so, it is determined whether the number of on-site detection devices 12 whose moving distance is greater than the set distance is less than a set threshold number;

[0159] When the number of on-site detection devices 12 whose moving distance is greater than the set distance is less than the set threshold number, the on-site detection devices 12 whose moving distance is greater than the set distance are regarded as the moved on-site detection devices 12 .

[0160] After the moved on-site detection device 12 is identified, an alarm message is issued and the on-site detection device 12 is continuously tracked to improve the safety of the on-site detection device 12 .

[0161] Through the technical solution of this embodiment, it is possible to detect whether each on-site detection device 12 is moved, so as to identify whether each on-site detection device 12 is moved artificially, thereby improving the safety of each on-site detection device 12.

[0162] In some embodiments of the present invention, the monitoring information processing device 11 obtains the ground displacement data of the target area according to the acceleration and position information detected by each field detection device 12. Figure 6 As shown, the following steps are included:

[0163] Step S211, obtaining a pre-trained ground displacement monitoring model;

[0164] Step S212: input the acceleration information and position information detected by each on-site detection device 12 into a pre-trained ground displacement monitoring model to obtain ground displacement information of the target area.

[0165] In the above step S211, the ground displacement monitoring model may be a model based on a neural network, and a preset training data set may be used to train the ground displacement monitoring model to obtain a pre-trained ground displacement monitoring model.

[0166] In the above step S212, the acceleration and position information detected by each field detection device 12 are input into a pre-trained ground displacement monitoring model, and the ground displacement monitoring model can analyze the ground displacement of the target area according to the acceleration and position information to obtain the ground displacement information of the target area.

[0167] Through the technical solution of this embodiment, the ground displacement information of the target area can be obtained through the pre-trained ground displacement monitoring model according to the acceleration and position information detected by each on-site detection equipment 12, so as to improve the convenience of obtaining the ground displacement information of the target area.

[0168] In some embodiments of the present invention, in the above step S210, the method for obtaining the pre-trained ground displacement monitoring model is as follows: Figure 7 As shown, the following steps are included:

[0169] Step S221, constructing a three-dimensional simulation model of the target area, and detecting the equipment model on-site at the corresponding position in the three-dimensional simulation model according to each preset detection point in the target area;

[0170] Step S222, simulating various geological disasters in the three-dimensional simulation model, and obtaining acceleration information and displacement information detected by each on-site detection equipment model under various geological disasters;

[0171] Step S223, constructing a preset training data set according to the acceleration information and displacement information detected by each on-site detection equipment model, and using the preset training set to train the ground displacement monitoring model to obtain a pre-trained ground displacement monitoring model.

[0172] In the above step S221, the set field detection equipment model is a simulation model corresponding to the field detection equipment 12, including at least a model of the acceleration detection device 111 and a simulation model of the positioning device 112. When each preset detection point in the three-dimensional simulation model is displaced, the field detection equipment model can detect the corresponding signal.

[0173] In the above step S222, the simulated geological disaster is a geological disaster that can cause ground movement, such as an earthquake, a landslide, and a mud-rock flow.

[0174] In the above step S223, after obtaining the acceleration information and displacement information detected by each on-site detection equipment model, each acceleration information and displacement information is stored according to the type of geological disaster and the detection time to obtain a training data set.

[0175] Through the technical solution of this embodiment, various geological disasters can be simulated in a three-dimensional simulation model of the target area, and based on the acceleration information and displacement information detected by each detection equipment model under various geological disasters, a preset training set can be established to train the ground displacement monitoring model, thereby ensuring the accuracy and reliability of the data in the preset training set, and further ensuring the reliability and accuracy of the training of the ground displacement monitoring model.

[0176] In some embodiments of the present invention, the method of constructing a three-dimensional model of a target area is as follows: Figure 8 As shown, the following steps are included:

[0177] Step S231, obtaining a three-dimensional electronic map of the target area, and loading the three-dimensional electronic map into a three-dimensional coordinate system to obtain an initial three-dimensional model of the target area;

[0178] Step S232, configuring the geology of the initial three-dimensional model of the target area according to the geological information of the target area to obtain a three-dimensional simulation model of the target area.

[0179] The above-mentioned configuration of the geology of the initial three-dimensional model of the target area according to the geological information of the target area means that after obtaining the geological type of each location in the target area, the geological type of each location in the initial three-dimensional model is set to the geological type of the corresponding location in the target area, for example, to mountainous area, river, land, etc., to ensure that the geological type in the three-dimensional simulation model is consistent with the geological type of the target area.

[0180] Through the technical solution of this embodiment, after constructing an initial three-dimensional model of the target area according to the three-dimensional electronic map of the target area, the geology of the initial three-dimensional model is also configured according to the geological information of the target area, thereby improving the accuracy of the simulation of the target area, and obtaining a preset training data set based on the three-dimensional simulation model, which can ensure the accuracy of the data in the training data set, thereby improving the accuracy of the obtained ground displacement monitoring model.

[0181] The flow chart provided by the present embodiment is not intended to indicate that the operation of the method will be performed in any particular order, or that all operations of the method are included in all every case. In addition, the method may include additional operations. Within the scope of the technical ideas provided by the present embodiment method, additional changes can be made to the above method.

[0182] At this point, those skilled in the art should recognize that, although multiple exemplary embodiments of the present invention have been shown and described in detail herein, many other variations or modifications that conform to the principles of the present invention can still be directly determined or derived based on the content disclosed in the present invention without departing from the spirit and scope of the present invention. Therefore, the scope of the present invention should be understood and recognized as covering all these other variations or modifications.

Claims

1. A ground displacement monitoring system based on BeiDou-3, characterized in that: include: A plurality of on-site detection devices, which are respectively used to be set at each preset detection point in the target area, and each of the on-site detection devices includes an acceleration detection device and a positioning device based on Beidou-3, wherein the acceleration detection device is used to collect acceleration information of the on-site detection device, and the positioning device is used to collect position information of the on-site detection device; A plurality of drones, which are used to respectively place the on-site detection equipment at the preset detection points; A monitoring information processing device, which is communicatively connected with each of the on-site detection devices and each of the drones, and is configured to: control the drone to drop each of the on-site detection devices, and monitor the ground displacement of the target area according to the acceleration information and the position information; Wherein, controlling the drone to place each of the on-site detection equipment includes: Obtaining an optimal flight path between each of the preset detection points, and obtaining an optimal flight path between each of the preset detection points and a preset starting position; Obtaining a flight cost function, using the flight cost function to obtain an optimal delivery strategy according to each of the optimal flight paths, and controlling each of the drones according to the optimal delivery strategy to deliver each of the on-site detection equipment to a corresponding preset detection; The method of adopting the flight cost function and obtaining the optimal delivery strategy according to each of the optimal flight paths includes: Acquire multiple preset delivery strategies, and use the flight cost function to calculate the flight cost of the drone executing each of the preset delivery strategies, including: Assume that the preset detection points in the preset delivery strategy are divided into N detection groups, and the flight cost of the UAV executing the preset delivery strategy is P, then Among them, F n represents the flight cost of the UAV to deliver the on-site inspection equipment to the nth inspection group, and In the above formula, M n is the number of preset detection points in the nth detection group, h(M n ) represents the flight correction factor of the nth detection group, h(M n -m) represents the correction coefficient of the mth flight track in the nth detection group, f() is the flight cost function, L n,1 represents the flight path from the first detection point in the nth detection group to the preset starting position, L n,Mn Indicates the Mth detection group in the nth detection group n The flight path between the detection point and the preset starting position, l n,m represents the flight path of the mth track point and the m+1th track point in the nth detection group; The preset delivery strategy with the minimum flight cost is used as the optimal delivery strategy.

2. The ground displacement monitoring system based on BeiDou-3 according to claim 1 is characterized in that: The step of obtaining the optimal flight path between the preset detection points includes: It is determined whether there is a flight obstacle area between the preset detection points, and a flight path between the preset detection points is obtained according to the flight obstacle area.

3. The ground displacement monitoring system based on BeiDou-3 according to claim 1 is characterized in that: The step of obtaining the optimal flight path between each of the preset detection points and the preset starting position includes: Obtaining a preset number of track points corresponding to each of the preset detection points according to the distance between each of the preset detection points and the preset starting position; A preset track optimization algorithm is used to obtain the optimal solution of each of the preset detection points, and based on the optimal solution of each of the preset detection points, an optimal flight path between each of the preset detection points and the preset starting position is obtained.

4. The ground displacement monitoring system based on BeiDou-3 according to claim 3 is characterized in that: The preset track optimization algorithm is a non-monopolistic optimization algorithm.

5. The ground displacement monitoring system based on BeiDou-3 according to claim 1 is characterized in that: The flight cost function includes a flight length cost function, a flight turning angle cost function and a flight pitch angle cost function.

6. The ground displacement monitoring system based on BeiDou-3 according to claim 1 is characterized in that: The drone is configured to: after placing the on-site detection equipment at the corresponding preset detection point, send a placement completion message to the monitoring information processing device; The monitoring information processing device is configured to: after receiving the delivery completion information, send activation information to the on-site detection device to control the on-site detection device to start working.

7. The ground displacement monitoring system based on BeiDou-3 according to claim 1 is characterized in that: The detection information processing device is further configured to: determine whether each of the on-site detection devices has been illegally moved based on the acceleration signal and the position information, and track the illegally moved on-site detection devices.

8. The ground displacement monitoring system based on BeiDou-3 according to claim 1 is characterized in that: The step of monitoring the ground displacement of the target area according to the acceleration information and the position information includes: Obtain a pre-trained ground displacement monitoring model; The acceleration signals and the position information are input into the ground displacement monitoring model to obtain the ground displacement information.

9. The ground displacement monitoring system based on BeiDou-3 according to claim 8 is characterized in that: The method of obtaining a pre-trained ground displacement monitoring model includes: Constructing a three-dimensional simulation model of the target area, and setting a field detection equipment model in the three-dimensional simulation model according to each of the preset detection points; Simulating a variety of geological disasters in the three-dimensional simulation model, and obtaining acceleration information and displacement information detected by each of the on-site detection equipment models under each of the geological disasters; A pre-training data set is constructed according to the acceleration information and displacement information detected by each of the on-site detection equipment models, and the ground displacement monitoring model is trained using the pre-training data set to obtain the pre-trained ground displacement monitoring model.

10. The ground displacement monitoring system based on BeiDou-3 according to claim 9 is characterized in that: The constructing of the three-dimensional simulation model of the target area comprises: Acquire a three-dimensional electronic map of the target area, and load the three-dimensional electronic map into a three-dimensional coordinate system to obtain an initial three-dimensional model of the target area; The geology of the initial three-dimensional model is configured according to the geological information of the target area to obtain the three-dimensional simulation model.