A smart park unmanned aerial vehicle patrol path optimization method, device and equipment

Abstract

The present application relates to the technical field of flight path control, in particular to a smart park unmanned aerial vehicle patrol path optimization method, device and equipment, comprising the following steps: obtaining task point three-dimensional coordinates and analyzing interval trend, screening dense path section to extract task set, adjusting path structure to form distribution set, identifying high temperature zone disturbance path section to mark changes, and judging distribution balance to optimize path structure. In the present application, by obtaining task point three-dimensional coordinates and identifying path interval changes, dense section is marked to enhance space perception, combined with the relationship between the center of gravity and the boundary to realize set screening, improve path division independence, extract attitude data to identify disturbance trend and locate wind disturbance area, uniformly adjust offset node to complete position information and optimize path stability, extract path parameters to analyze distribution balance, dynamically reconstruct path structure, realize multi-path load coordination, and the overall processing logic covers data perception, structure identification and scheduling optimization, improves flight efficiency and path adaptability.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of flight path control, in particular to a smart park unmanned aerial vehicle patrol path optimization method, device and equipment. BACKGROUND

[0002] The technical field of flight path control relates to the control and adjustment of non-electric variables such as the position, speed, and heading of an aircraft in space, and its core matters include aircraft attitude stabilization, heading keeping, trajectory tracking, and path planning. This technical field mainly realizes the autonomous navigation and path control of the aircraft by establishing a dynamic model of the aircraft, designing a control law, and implementing a path generation algorithm. This field is widely used in civilian unmanned aerial vehicles, industrial inspection, logistics transportation, and military reconnaissance. The traditional smart park unmanned aerial vehicle patrol path optimization method refers to arranging and optimizing the patrol path of the unmanned aerial vehicle in the park environment to improve the coverage efficiency and operation rationality. It usually uses a path planning method based on graph theory to solve the technical matters, such as constructing a park area graph model to obtain the relationship between patrol points, and then using a depth-first search or greedy algorithm to perform path traversal and sorting to realize the preliminary planning and optimization of the unmanned aerial vehicle patrol path.

[0003] The traditional path optimization method has problems such as excessive dependence on the area graph model, single path traversal algorithm, and low utilization rate of spatial parameters. It often maps the patrol point relationship with a graph structure, ignores the three-dimensional relationship in the spatial distribution of task points, and is difficult to capture the dense fluctuation phenomenon in the path segment, resulting in rough path structure division, fuzzy operation interval boundaries, and affecting the accuracy of path scheduling. The path allocation does not fully consider the coupling relationship between the task point aggregation trend and the boundary position, which may cause flight task overlap or repeated coverage. When dealing with high-temperature disturbance areas, there is a lack of path disturbance discrimination mechanism based on attitude-related parameters, which makes the path adjustment lag and easy to form flight trajectory deviation, further affecting the coverage integrity of key areas. The existing path coordination mechanism is based on a static graph model and cannot dynamically evaluate the coordination degree of the number and distribution state of task points in the path, which may cause task load deviation and reduce the efficiency of cooperative flight. The above problems are particularly prominent in the context of multiple aircrafts performing high-density patrol tasks, and it is difficult to meet the high requirements of actual operations on path rationality, node stability, and scheduling efficiency. SUMMARY

[0004] The purpose of the present application is to solve the problems in the prior art and to provide a smart park unmanned aerial vehicle patrol path optimization method, device and equipment.

[0005] To achieve the above purpose, the present application adopts the following technical scheme: a smart park unmanned aerial vehicle patrol path optimization method, comprising the following steps:

[0006] S1: Obtain the three-dimensional coordinates of the closed area channel patrol task points, identify the distance change trend between the task points in the path segment, extract the average distance value, compare it with the preset distance threshold, determine the path segment area whose change amplitude exceeds the threshold interval, and establish the path segment density identification result;

[0007] S2: Extract the task point set according to the path segment density identification result, judge the positional relationship between the center of gravity of the set and the boundary of the task segment, screen the independence of the task set, adjust the path structure of the substation fence and the high-voltage line tower area, and establish the patrol path distribution set;

[0008] S3: Call the plant heat pipe high-temperature area path segment in the patrol task distribution path set, extract the flight attitude related data of the inertia monitoring point in the path, identify and label the path segment with continuous change in the monitoring period, and establish the path disturbance influence section identification information;

[0009] S4: Extract the affected path segment according to the path disturbance influence section identification information, analyze the angle relationship between the advancing direction and the wind disturbance direction, judge whether the offset value exceeds the deviation range, if the condition is met, uniformly adjust the node position in the path segment, and establish the path point position adjustment list after disturbance.

[0010] As a further scheme of the present application, the path segment density identification result includes the distance change amplitude between the task points, the path segment area exceeding the threshold, and the area label information, the patrol task distribution path set includes the independence screening task point set, the path connection structure, and the initial path division result, the path disturbance influence section identification information includes the abnormal change segment position, the wind disturbance direction trend, and the disturbed path segment summary information, and the path point position adjustment list after disturbance includes the node position adjustment value, the key node position information, and the adjusted path node set.

[0011] As a further scheme of the present application, the specific steps of S1 are:

[0012] S101: Obtain the three-dimensional coordinate information of the patrol task points, construct the path segment and sequentially extract the three-dimensional coordinate values between adjacent task points, calculate the distance between the task points according to the three-dimensional coordinate values, and generate the path segment distance value between the task points;

[0013] S102: Call the path segment distance value between the task points, calculate the average distance value between the task points in the path segment, and make a difference judgment with the set distance threshold, extract the path segment number and task point number exceeding the threshold, and obtain the path segment distance exceeding number value;

[0014] S103: Based on the path segment distance exceeding number value, combine adjacent exceeding path segments, extract the start and end task point numbers, construct the path segment area boundary and label it, and establish the path segment density identification result.

[0015] As a further aspect of the present invention, the specific steps of S2 are as follows:

[0016] S201: Obtain the set of trajectory nodes in the path segment density recognition result, call the node coordinate values ​​to calculate the centroid position of the path segment in the set, and generate the centroid position coordinate set of the path segment;

[0017] S202: Based on the set of coordinates of the centroid of the path segment, extract the spatial distance between the centroid and the boundary point of the task segment, determine whether the centroid is outside the boundary distance threshold range, and obtain a set of independent task path segments.

[0018] S203: Based on the path connection relationship between the set of independent task path segments and the fence area and high-voltage line tower area, detect the connection structure between the path segments and the area nodes, establish a multi-path segment connection matrix, and generate a set of collaborative path segments for multiple UAVs.

[0019] As a further aspect of the present invention, the specific steps of S3 are as follows:

[0020] S301: Obtain inertial monitoring point data from the set of collaborative path segments of the multiple UAVs, and combine the flight attitude information of each UAV to integrate and analyze the data of each monitoring point in the path segment to generate flight attitude data.

[0021] S302: Based on the flight attitude data, abnormal fluctuations within the monitoring period are judged by setting a threshold, abnormal change segments in the path segment are identified, and abnormal change identifiers are generated.

[0022] S303: Based on the abnormal change identifier, analyze the changing trend of the disturbed path segment and the direction of wind disturbance, mark the location and direction of the disturbed path segment, and generate the identification information of the path disturbance affected area.

[0023] As a further aspect of the present invention, the specific steps of S4 are as follows:

[0024] S401: Obtain the identification information of the affected section of the path disturbance, extract the associated parameters of the affected path segment, calculate and record the offset of the path segment, determine whether the conditions are met, and generate the offset analysis result of the disturbed path segment.

[0025] S402: Obtain the advancing direction and wind disturbance direction of the path segment, calculate the angle difference, determine whether it exceeds the preset deviation range, and generate the offset angle analysis value;

[0026] S403: Based on the angle offset analysis results, filter out path segments with excessive offset, adjust the positions of key nodes, supplement the node position information in the high-rise backflow area, and generate a list of path point position adjustments after disturbance.

[0027] As a further scheme of the present application, the method further comprises:

[0028] S5: adjusting the path data in the list based on the disturbed path point positions, extracting the number of task points and the length of the path, judging the balanced state of the task point distribution between paths, if the coordination standard is not met, adjusting the path segment structure and updating the task point position index, and establishing an optimized path coordination distribution structure;

[0029] The optimized path coordination distribution structure comprises a task point number distribution, a path length parameter, and a coordination configuration structure.

[0030] As a further scheme of the present application, the specific steps of S5 are:

[0031] S501: obtaining the disturbed path point position data, extracting the number of task points and the distance between task points of each path, obtaining the number of task points and the length parameter of the path, detecting the task point distribution state, and generating path task point distribution data;

[0032] S502: based on the path task point distribution state data, judging by comparing the distribution density of the task points with the preset balanced standard, screening the paths with uneven task point distribution, calculating the offset of the path, and generating path balance deviation data;

[0033] S503: based on the path balance deviation data, adjusting the paths with uneven distribution, reorganizing the path segment structure and adjusting the task point position index, outputting the optimized multi-machine coordination configuration result, and obtaining the optimized path coordination distribution structure.

[0034] A smart park unmanned aerial vehicle patrol path optimization device, the smart park unmanned aerial vehicle patrol path optimization device is used for executing the above-mentioned smart park unmanned aerial vehicle patrol path optimization method, comprising:

[0035] The task point recognition module is used for executing S1: obtaining the three-dimensional coordinate information of the task points in the patrol area, recognizing the distance change trend of the path segment between the task points, calculating the average distance of the task points in the path segment, and comparing with the preset distance threshold, screening the path segment exceeding the set threshold, and obtaining the path segment density recognition result;

[0036] The path density analysis module is used for executing S2: according to the path segment density recognition result, extracting the task point set and calculating the center of gravity position of the set, judging the position relationship between the set and the task segment boundary point, adjusting the path connection structure, forming the preliminary division of the multi-unmanned aerial vehicle coordination path, and obtaining the patrol task allocation path set;

[0037] The flight path interference monitoring module is configured to perform S3: extracting flight attitude data of an inertial monitoring point of a high-temperature path segment of the plant heat pipe, identifying abnormal changes in a monitoring period, analyzing a wind disturbance direction trend, identifying an interference path segment and a disturbed direction, and generating path disturbance influence segment identification information.

[0038] The path adjustment optimization module is configured to perform S4: extracting an affected path segment according to the path disturbance influence segment identification information, analyzing an angle relationship between a propulsion direction and a wind disturbance direction, judging whether an offset exceeds a deviation range, adjusting a path node position, supplementing key node information, and obtaining an adjusted path point position list after disturbance.

[0039] The multi-machine cooperative path allocation module is configured to perform S5: extracting task point quantity and length parameters of a path based on the adjusted path point position list after disturbance, analyzing a task point distribution state, reorganizing a path structure if the task point distribution state is uneven, adjusting a task point position index, and obtaining an optimized path coordination distribution structure.

[0040] Compared with the prior art, the application has the following advantages and positive effects:

[0041] In the application, by acquiring three-dimensional coordinates of task points and analyzing path spacing trends, dense segments can be identified and labeled, spatial distribution structure perception is enhanced, task set screening is realized in combination with barycenter and boundary relationship judgment, path division independence is ensured, disturbance trends are identified by combining flight attitude data, wind disturbance influence areas are located, offset nodes are adjusted and key position information is supplemented, path stability is optimized, path parameters are extracted to analyze task point distribution balance, path structure is dynamically reconstructed, multi-path load coordination is realized, and the overall processing logic constitutes a closed loop of data perception, structure identification, interference analysis and scheduling optimization, thereby improving flight efficiency and path adaptability. BRIEF DESCRIPTION OF DRAWINGS

[0042] Figure 1 The figure is a work flow diagram of the application;

[0043] Figure 2 The figure is a detailed flowchart of S1 of the application;

[0044] Figure 3 The figure is a detailed flowchart of S2 of the application;

[0045] Figure 4 The figure is a detailed flowchart of S3 of the application;

[0046] Figure 5 The figure is a detailed flowchart of S4 of the application;

[0047] Figure 6 The figure is a detailed flowchart of S5 of the application;

[0048] Figure 7 System flowchart of the present application. DETAILED DESCRIPTION

[0049] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and should not be used to limit the present application.

[0050] In the description of the present application, it should be understood that the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only used to facilitate the description of the present application and simplify the description, and therefore cannot be understood as indicating or implying that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application. In addition, in the description of the present application, the meaning of "a plurality of" is two or more, unless otherwise explicitly and specifically limited.

[0051] Embodiment one

[0052] Please refer to Figure 1 The present application provides a technical solution: a smart park unmanned aerial vehicle patrol path optimization method, comprising the following steps:

[0053] S1: Obtain the three-dimensional coordinate information of the patrol task points in the closed area channel, identify the distance change trend between the task points in the continuous path segment, extract the average distance value between the task points in the path segment, and compare it with the preset distance threshold value, identify the path segment area whose distance change amplitude exceeds the threshold setting interval, and complete the area label division, and establish the path segment density identification result;

[0054] S2: Extract the task point set according to the path segment density identification result, obtain the center of gravity position of the set, and judge the positional relationship with the existing task segment boundary point, perform task set independence screening according to the judgment result, adjust the path connection structure of the substation fence and the high-voltage line tower area, form the initial division of the cooperative path of multiple unmanned aerial vehicles, and establish the patrol task allocation path set;

[0055] S3: Call the path segment of the plant heat pipe high-temperature area in the patrol task allocation path set, extract the flight attitude related data of the inertia monitoring point in the path, identify the abnormal change segment in the continuous monitoring period, identify the wind disturbance direction change trend, and summarize the disturbed path segment position and the disturbance direction, and establish the path disturbance influence segment identification information;

[0056] S4: Extract the affected path segment according to the path disturbance influence section identification information, analyze the angle relationship between the propulsion direction and the wind disturbance direction, judge whether the deviation value exceeds the deviation range, if the condition is met, uniformly adjust the node position in the path segment, supplement the key node position information in the building entrance high-rise backflow area, and establish the path point position adjustment list after disturbance;

[0057] S5: Based on the path data of the unmanned aerial vehicle in the path point position adjustment list after disturbance, extract the task point quantity and length parameters of each path, judge whether the task point distribution state between paths is balanced, if the coordination condition is not met, reorganize the path segment structure, adjust the task point position index and output the multi-machine collaborative configuration result, and establish the optimized path coordination distribution structure.

[0058] The path segment intensity recognition result includes the task point spacing variation amplitude, the threshold value path segment area, and the area label information. The patrol task allocation path set includes the independence screening task point set, the path connection structure, and the initial path division result. The path disturbance influence section identification information includes the abnormal change segment position, the wind disturbance direction trend, and the disturbed path segment summary information. The path point position adjustment list after disturbance includes the node position adjustment value, the key node position information, and the adjusted path node set. The optimized path coordination distribution structure includes the task point quantity distribution, the path length parameter, and the collaborative configuration structure.

[0059] Please refer to Figure 2 , the specific steps of S1 are as follows:

[0060] S101: Obtain the three-dimensional coordinate information of the patrol task point, construct the path segment and sequentially extract the three-dimensional coordinate values between adjacent task points, calculate the distance between task points according to the three-dimensional coordinate values, and generate the path segment distance value between task points;

[0061] By obtaining the three-dimensional coordinate information of the patrol task point, the position of each task point in space is obtained. The coordinates of the task point include X, Y, and Z three dimensions, which can be collected by GPS equipment, unmanned aerial vehicle or three-dimensional scanning technology. Through these coordinate information, the path segment between task points can be constructed, and each path segment is a straight line segment connected by adjacent task points. When constructing the path segment, the three-dimensional distance between each two adjacent task points needs to be calculated first, which can be realized by calculating the Euclidean distance between two points. This distance calculation considers the difference of X, Y, and Z coordinate axes. For example, if the coordinates of task point A are (3, 4, 5) and the coordinates of task point B are (6, 8, 9), the distance between them will be 3 units of X difference, 4 units of Y difference, and 4 units of Z difference, and finally the distance between task point A and task point B is about 6.4 units. The result of each calculation will be used as the distance value of the path segment for subsequent analysis and judgment.

[0062] S102: Call the path segment distance value between task points, calculate the average distance value between task points in the path segment, and make a difference judgment with the set distance threshold value, extract the path segment number and task point number that exceeds the threshold value, and get the path segment distance exceeding number value;

[0063] After obtaining the path segment distance value between task points, the next step is to calculate the average distance of all task points in the path segment. The calculation method is to add the distance between all path segments, and then divide by the total number of path segments. Suppose there are multiple task points forming path segments, and the distances of these path segments are 6.4, 7.2, 5.5 and 8.0 units, then the average distance of these path segments is 6.775 units. Then, by comparing with the set distance threshold value, it is judged which path segment distance exceeds the threshold value. Assuming that the set threshold value is 6 units, when the distance of a path segment is greater than 6 units, it is considered that the distance of this path segment exceeds the predetermined range. For example, if the distance of a path segment is 7.2 units, then the distance of this path will be marked as an over-limit path segment. In this step, the over-limit path segments are extracted, and the task point numbers corresponding to these over-limit path segments are also recorded, which helps subsequent density analysis and path optimization.

[0064] S103: Based on the path segment distance exceeding number value, combine adjacent over-limit path segments, extract the start and end task point numbers, construct the path segment area boundary and mark it, and establish the path segment density recognition result;

[0065] Next, adjacent over-limit path segments need to be combined. Through this combination, dense areas can be identified. In this process, first, each over-limit path segment needs to be analyzed to find out which over-limit path segments are adjacent and combine them together to form a dense area. For example, if the distance of path segment C and path segment D is over-limit and they are adjacent, then these two path segments will be considered as a dense area. In this dense area, the start task point and end task point numbers need to be extracted, and the start and end boundaries of the area are marked. For example, assuming that the start task point number of path segment C is T3, the end task point number is T4, the start task point number of path segment D is T4, and the end task point number is T5, then the task point number of this dense area is T3 to T5. Finally, these dense areas will be marked out and form the dense recognition result between task points. In this way, the areas where the task point distances are uneven can be clearly displayed, which facilitates further path adjustment and optimization.

[0066] Please refer to Figure 3 , the specific steps of S2 are:

[0067] S201: Obtain the trajectory node set in the path segment density identification result, call the node coordinate value to calculate the center of gravity position of the path segment in the set, and generate the path segment center of gravity position coordinate set;

[0068] After obtaining the trajectory node set in the path segment density identification result, the node set is first processed to generate the path segment center of gravity position coordinate set. First, for each node on the path segment, the corresponding coordinate value is obtained. The path segment is composed of multiple nodes, so the center of gravity position of each path segment needs to be calculated. The specific operation is to sum the coordinate values of all nodes in the path segment, and then obtain the center of gravity position of the path segment by averaging. In actual application, this calculation can be assisted by map data or geographic information system (GIS) tools. Assuming that the node coordinates of a path segment are (1, 2), (2, 3), and (3, 4), the center of gravity coordinates of the path segment are the arithmetic mean of the node coordinates (2, 3), and this center of gravity point represents the center position of the path segment. By performing this operation on each path segment, the center of gravity coordinate set of all path segments can be obtained, providing a basis for the next calculation.

[0069] S202: Based on the path segment center of gravity position coordinate set, extract the spatial distance between the center of gravity point and the task segment boundary point, judge whether the center of gravity point is located outside the boundary distance threshold range, and obtain the independent task path segment set;

[0070] Based on the path segment center of gravity position coordinate set, the spatial distance between the center of gravity point and the task segment boundary point needs to be extracted, and it is judged whether the center of gravity point is located outside the boundary distance threshold range. For the center of gravity position of each path segment, it is compared with the corresponding task segment boundary point. The distance between the center of gravity point and the boundary point can be obtained by simple distance calculation. According to the calculated distance, it is compared with the pre-set boundary distance threshold. If the distance between the center of gravity point and the boundary point is greater than the threshold, it means that the center of gravity position of the path segment is located outside the boundary distance threshold range. In this case, the path segment will be considered as an independent task path segment. For example, if the center of gravity point coordinate of the path segment is (2, 3), and the boundary point coordinate of the task segment is (5, 7), the spatial distance between them is 5, and when the pre-set threshold is 3, it means that the path segment belongs to the independent task path segment. Such calculation can be processed through the GIS platform, and in actual operation, the distance between the path segment and the boundary point can be calculated through a script or program, and whether the path segment is an independent task path segment can be judged according to the threshold.

[0071] S203: According to the path connection relationship of the independent task path segment set and the fence area and the high-voltage line tower area, detect the connection structure of the path segment and the area node, establish a multi-path segment connection matrix, and generate a multi-path segment set for cooperative unmanned aerial vehicles;

[0072] The specific calculation formula for the connection structure between path segments and region nodes is as follows:

[0073]

[0074] Calculate the connection matrix between path segments and region nodes to generate a set of collaborative path segments for multiple UAVs;

[0075] Among them, C ij P represents the connectivity between path segment i and region node j. ik P represents the coordinates of path segment i in the k-th dimension. jk d represents the coordinates of region node j in the k-th dimension. ij w is the distance between path segment i and region node j. m Let n be the weight of the m-th path segment, n be the number of dimensions of the path segment, and N be the total number of path segments.

[0076] The parameters in the formula:

[0077] C ij Let be the connectivity between path segment i and region node j, representing the relative tightness between path segment i and region node j;

[0078] P ik Let P be the coordinates of path segment i in the k-th dimension, obtained by monitoring the actual location data of the path segment; for example, if the three coordinate dimensions of path segment i are (10, 20, 30), then P... i1 =10, P i2 =20, P i3 =30;

[0079] P jk Let J be the coordinates of region node j in the k-th dimension, which are obtained similarly through data collection from region nodes;

[0080] For example, if the three coordinate dimensions of region node j are (12, 18, 28), then P j1 =12, P j2 =18, P j3 =28;

[0081] d ij The distance between path segment i and region node j is usually calculated using the Euclidean distance formula, which is:

[0082]

[0083] By substituting specific values, we get:

[0084] ;

[0085] w mThe weight of path segment m, the weight is usually quantified by the importance or coverage of the path segment; the weight w m The allocation can be made according to the criticality of the UAV path;

[0086] Suppose in a certain scenario, the importance of the path segment is allocated by a pre-set coefficient, for example, the weight of path segment m is 1.2;

[0087] n is the number of dimensions of the path segment, usually the number of spatial dimensions in which the path segment is located;

[0088] For example, if the coordinates of the path segment are in three-dimensional space, n = 3;

[0089] N is the total number of path segments, which is the number of all path segments. Suppose in this task, there are 10 path segments, N = 10;

[0090] The calculation process of the formula is as follows: 1. Calculate the sum of the squares of the coordinate differences between path segment i and region node j:

[0091]

[0092] Take the square root of the result to get the distance measure between path segment i and region node j:

[0093]

[0094] Calculate the Euclidean distance between path segment i and region node j:

[0095] d ij = 3.464;

[0096] Calculate the total weight of all path segments. Suppose the weights of the path segments are 1.2, 0.8, 1.5, 1.1, 0.9, 1.3, 1.0, 1.6, 1.2, 0.7 respectively, then the total weight of the path segments is:

[0097] ;

[0098] Substitute all the calculated results into the original formula:

[0099]

[0100] Result interpretation: the result shows that the connection degree between path segment i and region node j is 0.0884. A lower connection degree value means that the connection between path segment i and region node j is relatively distant, and the path may need to be adjusted or the cooperative path planning of the UAVs needs to be further optimized;

[0101] The operation logic in the formula first calculates based on the geometric distance and relative position relationship between the path segment and the region node. First, calculate the square sum of the dimensional coordinate difference between path segment i and region node j. This operation captures the spatial difference between dimensions by subtraction and squaring, aiming to measure the deviation of path segment and node in each dimension. Then, through the square root operation, the square sum is converted into the actual Euclidean distance, which is to restore the square sum of coordinate difference values to the original physical space scale, so that the calculation result reflects the actual spatial distance, not just the square sum of the difference. Then, divide this distance value by the Euclidean distance d ij between the path segment and the region node. This process normalizes the distance value to a unit distance measure, preventing large deviations in numerical values due to spatial differences. Finally, multiply by the reciprocal of the sum of path segment weights to introduce the weight factor of the path segment. This step allows path segments with different weights to reflect their relative importance in the calculation of connectivity, and path segments with high weights will have a greater impact on connectivity calculation, thereby adjusting the accuracy of path planning and the flexibility of unmanned aerial vehicle cooperative path. Overall, the formula comprehensively measures the connection strength between path segments and region nodes through the calculation of spatial distance and the introduction of path weight.

[0102] The connection matrix of path segments and region nodes is used to describe the relative connection relationship and tightness between path segments and region nodes. It calculates the connection degree between each path segment and each region node to form a matrix structure, where each element represents the connection strength between a specific path segment and a specific region node. The significance of this matrix is to provide a quantitative method to help analyze and evaluate the spatial correlation between path segments and region nodes, thereby providing data support for path optimization, unmanned aerial vehicle cooperative operation, and regional monitoring tasks. Through this matrix, it can be identified which path segments have a closer relationship with a specific region node, which plays an important role in unmanned aerial vehicle scheduling, path planning, and reasonable allocation of cooperative operation.

[0103] Please refer to Figure 4 The specific steps of S3 are as follows:

[0104] S301: Obtain the inertial monitoring point data in the cooperative path segment set of multiple unmanned aerial vehicles, and combine the flight attitude information of each unmanned aerial vehicle to integrate and analyze the data of each monitoring point in the path segment, and generate flight attitude data;

[0105] First, collect the inertial monitoring point data from multiple drones, each equipped with an inertial measurement unit (IMU) to collect acceleration, angular velocity, and other information in real time, and combine the position information provided by the GPS module to obtain flight attitude data. The flight attitude can be obtained by calculating the acceleration and angular velocity of the unmanned aerial vehicle's pitch angle, roll angle, heading angle, etc. Assume that the unmanned aerial vehicle's attitude in flight is a pitch angle of 10°, a roll angle of 5°, and a heading angle of 45°, and at a certain monitoring point, the recorded acceleration is 0.03 m / s 2 Using these data, each monitoring point in the path segment can be further analyzed, the flight data of each unmanned aerial vehicle is integrated, and comprehensive flight attitude data is generated for subsequent processing and analysis.

[0106] S302: Based on the flight attitude data, set a threshold to judge the abnormal fluctuations in the monitoring period, identify the abnormal change segment in the path segment, and generate an abnormal change identifier;

[0107] Based on the flight attitude data, set a threshold to determine whether there is an abnormal fluctuation in flight. The threshold is generally obtained through flight testing or historical data, for example, set the fluctuation range of pitch angle, roll angle, and heading angle. If the attitude angle of a certain monitoring point changes more than the set threshold, such as a pitch angle fluctuation of more than 3°, a roll angle fluctuation of more than 2°, and a heading angle fluctuation of more than 5°, it is determined to be an abnormal fluctuation. These abnormal fluctuations can be used to identify abnormal changes in the path segment. When the monitoring point of a certain path segment fluctuates more than the threshold, mark the path segment as abnormal, record the time point and corresponding position information of the abnormal occurrence, and facilitate further analysis. For example, if the pitch angle of a certain monitoring point changes more than 3°, it is marked as an abnormal segment, which may affect flight safety and require subsequent intervention or adjustment.

[0108] S303: According to the abnormal change identifier, analyze the disturbed path segment and the change trend of the wind disturbance direction, mark the location and direction of the disturbed path segment, and generate path disturbance impact segment identifier information;

[0109] According to the abnormal change identification, the change trend of the disturbed path segment and the influence of wind disturbance direction can be further analyzed. By obtaining the wind speed and wind direction data in flight, combined with the flight attitude information, the influence of wind is analyzed. For example, if the wind speed is large, and the included angle between the wind direction and the flight path direction exceeds 30°, it is considered that the wind has a large influence on the flight path. Assuming that the wind speed is 15 m / s and the wind direction is northwest, there is a large influence on the flight path. In the analysis of the path segment, first, the deviation of the predetermined flight trajectory and the actual flight trajectory is compared, and the offset of the path is calculated. When the offset reaches a certain standard, it is considered that the path segment is significantly disturbed by wind. Assuming that the actual trajectory deviates from the predetermined trajectory by 20 m, the path segment is marked as a wind disturbance segment, and the start and end time of the wind disturbance and the change of the wind direction are recorded. Marking the position and direction of the disturbed path segment helps flight management personnel to adjust or optimize the path segment, ensure flight safety and reduce the influence of disturbance.

[0110] Please refer to Figure 5 , the specific steps of S4 are:

[0111] S401: Obtain path disturbance influence section identification information, extract the relevant parameters of the affected path segment, calculate and record the offset of the path segment, judge whether the condition is met, and generate the offset analysis result of the disturbed path segment;

[0112] Obtain path disturbance influence section identification information, extract the relevant parameters of the affected path segment, calculate and record the offset of the path segment, judge whether the condition is met, and generate the offset analysis result of the disturbed path segment. First, the identification information of the path disturbance influence section is obtained through positioning technology, combined with the geographic coordinates, running state, climate and other data of the path segment, to determine the affected area. Specifically, when there are changes in wind, temperature and other natural factors, these factors will cause some parts of the path segment to be disturbed, and the influence range is determined through the input data of sensors and monitoring systems. Next, the relevant parameters of the affected path segment are extracted, including the length, material, position, load capacity and other parameters of the path segment, which are automatically collected by sensor devices and processed by data analysis systems. When calculating the offset, the physical state of the path segment is analyzed through historical records, real-time data and the health status of the equipment, and the specific offset of the path is recorded. If the path segment has physical offset, such as bending or displacement of the line due to wind influence, the system will record the degree and specific location of the offset. Then, compare the offset of the path segment with the preset tolerance range, if the offset of the path segment exceeds the tolerance limit (for example, the offset exceeds 5 meters), it is considered that the path segment needs to be repaired. Finally, the system generates the offset analysis result, listing the offset data and repair suggestions of each affected path segment, providing a basis for subsequent work.

[0113] S402: Obtain the advancing direction of the path segment and the wind disturbance direction, calculate the angle difference, judge whether it exceeds the preset deviation range, and generate the offset angle analysis value;

[0114] Obtain the advancing direction of the path segment and the wind disturbance direction, calculate the angle difference, judge whether it exceeds the preset deviation range, and generate the offset angle analysis value. First, the advancing direction of the path segment is determined by a data acquisition device, combined with the travel trajectory of the path segment and the actual use (such as the direction of the power transmission line or the transportation route), to obtain the actual advancing direction of the path. At the same time, the wind disturbance direction is obtained by a wind direction monitoring device, recording the change of wind direction and the real-time data of wind speed. Then, the angle difference between the advancing direction of the path segment and the wind disturbance direction is calculated. The angle difference refers to the deviation angle between the advancing direction of the path segment and the wind direction. If there is a large angle difference between the wind direction and the advancing direction of the path segment, it may affect the stability of the path. At this time, by comparing the angle between the two, if the angle difference exceeds the preset tolerance range (for example, 15°), it is considered that the angle offset of the path segment is out of standard. According to this analysis result, the offset angle analysis value is generated, which is used for subsequent judgment and correction, providing reference for path optimization.

[0115] S403: According to the angle offset analysis result, filter out the path segment with excessive offset, adjust the position of its key node, supplement the node position information in the high-level backflow area, and generate the path point position adjustment list after disturbance;

[0116] The specific calculation formula of the key node position adjustment of the path segment is:

[0117]

[0118] Calculate the key node offset, the path segment adjustment, and the key node backflow information;

[0119] Where ΔP represents the total adjustment amount of the key node position of the path segment, represents the new position of the i-th path point after disturbance adjustment, represents the original position of the i-th path point, d i represents the distance between the i-th path point and the center of the adjustment area, unit: meter (m), r i represents the backflow radius of the i-th path point, unit: meter (m), represents the position of the j-th high-level backflow area node, unit: meter (m), represents the position of the j-th basic node, unit: meter (m), n is the total number of nodes of the path segment, and m is the number of nodes in the backflow area;

[0120] New position of the i-th path point after disturbance adjustment, in meters. Real-time geographic coordinate changes of path points are obtained through monitoring equipment to calculate new position coordinates;

[0121] Original position of the i-th path point, in meters. Obtain the original geographic coordinates of the path point through historical data or initial planning;

[0122] d i Distance of the i-th path point from the center of the adjustment area, in meters. Calculate the straight-line distance from the path point to the center of the adjustment area through the Geographic Information System (GIS);

[0123] r i Reflux radius of the i-th path point, in meters. Determine the reflux influence range of the path point through fluid mechanics models or historical data analysis;

[0124] Position of the j-th high-rise reflux area node, in meters. Determine the node position of the high-rise reflux area by combining wind speed and wind direction models with the height and position data of high-rise buildings;

[0125] Position of the j-th base node, in meters. Obtain the geographic coordinates of the base node through infrastructure design drawings or construction data;

[0126] Parameter value settings:

[0127] And According to actual monitoring data and historical planning data, ensure the accuracy and timeliness of the data;

[0128] d i Calculate the distance from the path point to the center of the adjustment area through the GIS system to ensure the accuracy of the calculation results;

[0129] r i Determine the reflux influence range of the path point according to fluid mechanics models or historical data analysis to ensure the reasonableness of the model;

[0130] And Obtain the node position according to the building height and position data, as well as the infrastructure design drawings, to ensure the accuracy of the data;

[0131] Formula calculation derivation process:

[0132] Assume there are 3 path points and 2 reflux area nodes, with the following specific data:

[0133] Path point data:

[0134]

[0135] Reflux area node data:

[0136]

[0137] Calculate path point adjustment amount:

[0138] 0.0068;

[0139] Total path point adjustment amount:

[0140] ΔP total = 0.0094 + 0.0079 + 0.0068 = 0.0241;

[0141] Calculate reflux area node adjustment amount:

[0142] ΔP high = |105.0-104.5| + |106.0-105.5| = 0.5 + 0.5 = 1.0;

[0143] Final path segment key node position adjustment amount:

[0144] ΔP = 0.0241 + 1.0 = 1.0241;

[0145] Result interpretation:

[0146] The result shows that the total adjustment amount of the path segment key node position is 1.0241 meters. This value reflects the displacement of the path point after disturbance adjustment, as well as the degree of influence of the reflux area node on the path adjustment;

[0147] The operation logic of the formula is based on the actual needs of the position adjustment of the key nodes of the path segment, and the use of addition, multiplication, square root and other operators between parameters embodies the influence of different factors on the path adjustment amount. First, the formula obtains the adjustment amount of the path point by calculating the difference between the new position and the original position of each path point, which is related to the distance of the path point from the center of the adjustment area and its backflow radius. The relationship between the distance and the backflow radius is processed by the square root to reflect the degree of influence of the backflow area. Specifically, the distance of the path point from the center of the adjustment area is combined by addition to ensure that the size of the adjustment range can affect the adjustment amplitude of the path point. The introduction of the square root reflects the nonlinear influence of the backflow radius on the path point adjustment amount, i.e., when the backflow radius is larger, the change of the path point adjustment amount is smaller. The adjustment amounts of all path points are summed to obtain the total path segment adjustment amount. In addition, the adjustment amount of the backflow area node is obtained by directly adding the difference between the node positions, reflecting the contribution of the nodes in the backflow area to the path adjustment. Finally, the total adjustment amount of the path segment is the sum of the path point adjustment amount and the backflow area node adjustment amount, which comprehensively reflects the common influence of all factors on the path adjustment.

[0148] The "key node offset amount" refers to the displacement amount of the position of each key node in the path segment due to disturbance or adjustment, reflecting the relative change degree of each node after the path is adjusted. This offset amount can reveal which node positions have changed greatly in the path optimization process, thereby affecting the overall shape and performance of the path. The "path segment adjustment amount" is the sum of the adjustment amounts of all path points, reflecting the overall adjustment degree of the entire path segment during the optimization process. It is an index for quantifying the overall effect of path optimization, reflecting the overall change amplitude of the path from the original planning to the final adjustment after optimization. The "key node backflow information" refers to the node position information related to the high-level backflow area, showing the change of the node position in the backflow influence area. The backflow information helps to further analyze the performance of the path adjustment in the high-level area, ensuring that the special requirements and influences of the high-level backflow area are fully considered in the path optimization process, thereby improving the overall accuracy and practicality of the path.

[0149] Please refer to Figure 6 The specific steps of S5 are as follows:

[0150] S501: Obtain the disturbed path point position data, extract the number of task points and the distance between task points of each path to obtain the number of task points and the length parameters of the path, detect the distribution state of the task points, and generate path task point distribution data;

[0151] After the path point position data is disturbed, first, the number of task points and the distance between adjacent task points of each path are extracted therefrom. Path point disturbance can be achieved by simulating environmental disturbances, such as adding a certain degree of noise, so that the points in the original path are slightly offset. The disturbed path points provide different task point distributions for subsequent analysis. Next, by counting the number of task points in the path, the total number of task points on each path is obtained, and the distance between adjacent task points is further calculated. For example, if the distance between task point 1 and task point 2 of a path is 2.5 m, the distance between task point 2 and task point 3 is 3.2 m, and so on, the total length of the path can be obtained by adding the distances between these task points. Then, by analyzing the distribution of these task points, it is checked whether the spacing of the task points on the path is uniform, whether there is a phenomenon of over-dense or over-sparse task points. According to this information, path task point distribution data is generated, reflecting the distribution state of the path task points, and providing basic data for subsequent path optimization.

[0152] S502: Based on the path task point distribution state data, by comparing the distribution density of the task points with the preset balanced standard, the paths with uneven distribution of task points are screened, the offset of the path is calculated, and the path balance deviation data is generated;

[0153] On the basis of the path task point distribution state data, the distribution density of the task points can be calculated by the proportional relationship between the path length and the number of task points. If the path length is L and the total number of task points is n, the task point density on the path can be obtained by simple proportional relationship. The preset balanced standard is the range of target task point density, which can be determined by experience data or actual demand. For example, the target density can be set to 0.2 to 0.5 task points per meter of path. When the actual density of the path exceeds this range, it is considered that the distribution of task points is uneven. Then, the calculation of path offset becomes a key step, which can quantify the deviation degree of path distribution. The offset is calculated by comparing the difference between the actual distribution density and the target balanced density. When the actual density of the path is significantly lower than the target density, the offset is larger, and vice versa. In this way, by calculating the offset of each path, the paths with uneven distribution of task points are screened, and the path balance deviation data is generated, which is convenient for subsequent path adjustment and optimization.

[0154] S503: Based on the path balance deviation data, the paths with uneven distribution are adjusted, the path segment structure is reorganized, and the task point position index is adjusted, the optimized multi-machine collaborative configuration result is output, and the optimized path coordination distribution structure is obtained;

[0155] When adjusting the unbalanced path, first, the deviation of the path needs to be evaluated through the path balance deviation data. If the deviation of a path exceeds the set threshold (for example, the deviation exceeds 0.1), the path is considered to need optimization. Next, the structure of the path segment is reorganized, that is, the distribution of the task points between the segments is adjusted. Each path can be re-divided into several more uniform segments according to the needs of the task point distribution, and the number of task points in each segment tends to be consistent. If there are fewer task points in a segment, the distribution of the task points can be adjusted by inserting new task points or increasing the length of the path segment; if there are more task points, the balance can be achieved by reducing the length of the path segment. When adjusting the position of the task points, the index order of the path points may need to be rearranged so that the distribution of the task points is more uniform. Through a series of adjustment operations, the optimized path will have a more coordinated task point distribution, avoiding the possible situation of dense or sparse task points, and ensuring that the execution effect of multi-machine cooperative tasks is more balanced and efficient.

[0156] Please refer to Figure 7 A smart park unmanned aerial vehicle patrol path optimization device, comprising:

[0157] The task point recognition module obtains the three-dimensional coordinate information of the task points in the patrol area, identifies the distance change trend of the path segments between the task points, calculates the average distance of the task points in the path segment, and compares it with the preset distance threshold to screen the path segments that exceed the set threshold, and obtains the path segment density identification result;

[0158] The path density analysis module extracts the task point set and calculates the center of gravity position according to the path segment density identification result, judges the positional relationship between the set and the task segment boundary point, adjusts the path connection structure, forms the preliminary division of the multi-unmanned aerial vehicle cooperative path, and obtains the patrol task allocation path set;

[0159] The flight path interference monitoring module extracts the inertial monitoring point flight attitude data of the path segment of the high-temperature area of the plant district heat pipe, identifies the abnormal change in the monitoring period, analyzes the wind disturbance direction trend, identifies the disturbed direction of the interference path segment, and generates path disturbance influence section identification information;

[0160] The path adjustment optimization module extracts the affected path segment according to the path disturbance influence section identification information, analyzes the angle relationship between the propulsion direction and the wind disturbance direction, judges whether the deviation exceeds the deviation range, adjusts the path node position, supplements the key node information, and obtains the path point position adjustment list after disturbance;

[0161] The multi-machine cooperative path allocation module extracts the task point number and length parameters of the path based on the path point position adjustment list after disturbance, analyzes the task point distribution state, and if it is unbalanced, reorganizes the path structure, adjusts the task point position index, and obtains the optimized path coordinated distribution structure.

[0162] The above merely describes the preferred embodiments of the present application, but is not intended to limit the present application in other forms. Any person skilled in the art can make changes or modifications to the above disclosed technical contents into equivalent embodiments with equivalent changes, and apply to other fields. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present application without departing from the technical solution content of the present application still belongs to the protection scope of the present application technical solution.

Claims

1. A method for optimizing drone patrol paths in smart parks, characterized in that, Includes the following steps: S1: Obtain the three-dimensional coordinates of the patrol task points in the closed area channel, identify the distance change trend between task points in the path segment, extract the average spacing value, compare it with the preset spacing threshold, determine the path segment area where the change exceeds the threshold range, and generate the path segment density recognition result. S2: Extract the task point set based on the path segment density identification result, determine the positional relationship between the set centroid and the task segment boundary, filter the task set independence, adjust the path structure of the substation fence and high-voltage line tower area, and establish the patrol path allocation set. S3: Call the high-temperature area path segment of the plant thermal pipeline in the set of paths allocated for the inspection task, extract the flight attitude correlation data of the inertial monitoring points in the path, identify and mark the path segments that change continuously within the monitoring period, and establish the identification information of the path disturbance affected area. S4: Extract the affected path segment based on the identification information of the path disturbance affected area, analyze the angular relationship between the advance direction and the wind disturbance direction, determine whether the offset value exceeds the deviation range, and if the condition is met, make unified adjustments to the node positions in the path segment and establish a list of path point position adjustments after disturbance. The path segment density identification results include the change range of task point spacing, the path segment area exceeding the threshold, and the area label information. The patrol task allocation path set includes the independent screening task point set, the path connection structure, and the initial path division results. The path disturbance affected section identification information includes the location of abnormal change segments, the wind disturbance direction trend, and the summary information of disturbed path segments. The path point position adjustment list after disturbance includes the node position adjustment value, the key node position information, and the adjusted path node set.

2. The method for optimizing drone patrol paths in smart parks according to claim 1, characterized in that, The specific steps of S1 are as follows: S101: Obtain the three-dimensional coordinate information of the patrol task points, construct path segments and extract the three-dimensional coordinate values ​​between adjacent task points in sequence, calculate the distance between task points based on the three-dimensional coordinate values, and generate the path segment distance value between task points. S102: Call the path segment distance value between the task points, calculate the average distance value between the task points in the path segment, and make a difference judgment with the set distance threshold. Extract the path segment number and task point number that exceed the threshold to obtain the path segment distance exceeding the limit number value. S103: Based on the path segment spacing exceeding the limit number value, combine adjacent exceeding path segments, extract the start and end task point numbers, construct the path segment area boundary and mark it, and generate the path segment density identification result.

3. The method for optimizing drone patrol paths in smart parks according to claim 2, characterized in that, The specific steps of S2 are as follows: S201: Obtain the set of trajectory nodes in the path segment density recognition result, call the node coordinate values ​​to calculate the centroid position of the path segment in the set, and generate the centroid position coordinate set of the path segment; S202: Based on the set of coordinates of the centroid of the path segment, extract the spatial distance between the centroid and the boundary point of the task segment, determine whether the centroid is outside the boundary distance threshold range, and obtain a set of independent task path segments. S203: Based on the path connection relationship between the set of independent task path segments and the fence area and high-voltage line tower area, detect the connection structure between the path segments and the area nodes, establish a multi-path segment connection matrix, and generate a set of collaborative path segments for multiple UAVs.

4. The method for optimizing drone patrol paths in smart parks according to claim 3, characterized in that, The specific steps for S3 are as follows: S301: Obtain inertial monitoring point data from the set of collaborative path segments of the multiple UAVs, and combine the flight attitude information of each UAV to integrate and analyze the data of each monitoring point in the path segment to generate flight attitude data. S302: Based on the flight attitude data, abnormal fluctuations within the monitoring period are judged by setting a threshold, abnormal change segments in the path segment are identified, and abnormal change identifiers are generated. S303: Based on the abnormal change identifier, analyze the changing trend of the disturbed path segment and the direction of wind disturbance, mark the location and direction of the disturbed path segment, and generate the identification information of the path disturbance affected area.

5. The method for optimizing drone patrol paths in smart parks according to claim 4, characterized in that, The specific steps of S4 are as follows: S401: Obtain the identification information of the affected section of the path disturbance, extract the associated parameters of the affected path segment, calculate and record the offset of the path segment, determine whether the conditions are met, and generate the offset analysis result of the disturbed path segment. S402: Obtain the advancing direction and wind disturbance direction of the path segment, calculate the angle difference, determine whether it exceeds the preset deviation range, and generate the offset angle analysis value; S403: Based on the angle offset analysis results, filter out path segments with excessive offset, adjust the positions of key nodes, supplement the node position information in the high-rise backflow area, and generate a list of path point position adjustments after disturbance.

6. The method for optimizing drone patrol paths in smart parks according to claim 1, characterized in that, The method further includes: S5: Based on the path data in the list of path point locations after disturbance, extract the number of task points and path length of the path, determine the balance of task point distribution between paths, and if it does not meet the coordination standard, adjust the path segment structure and update the task point location index to establish an optimized path coordination distribution structure. The optimized path coordination distribution structure includes the task point quantity distribution, path length parameters, and collaborative configuration structure.

7. The method for optimizing drone patrol paths in smart parks according to claim 6, characterized in that, The specific steps of S5 are as follows: S501: Obtain the disturbed path point location data, extract the number of task points and the distance between task points for each path, obtain the number of task points and length parameters of the path, detect the distribution status of task points, and generate path task point distribution data. S502: Based on the task point distribution status data of the path, the distribution density of task points is compared with the preset balance standard to make a judgment, filter out paths with uneven task point distribution, calculate the offset of the path, and generate path balance deviation data. S503: Based on the path balance deviation data, adjust the unbalanced paths, reorganize the path segment structure and adjust the task point location index, output the optimized multi-machine collaborative configuration result, and obtain the optimized path coordination distribution structure.

8. A smart park drone patrol path optimization device, characterized in that, The smart park drone patrol path optimization device is used to execute the smart park drone patrol path optimization method according to any one of claims 1-7, and the smart park drone patrol path optimization device includes: The task point identification module is used to perform S1: acquire the three-dimensional coordinate information of task points in the patrol area, identify the distance change trend of path segments between task points, calculate the average distance between task points in the path segment, compare it with the preset distance threshold, filter out path segments that exceed the set threshold, and obtain the path segment density identification result. The path density analysis module is used to perform S2: based on the path segment density identification results, extract the task point set and calculate the centroid position of the set, determine the positional relationship between the set and the boundary points of the task segment, adjust the path connection structure, form a preliminary division of the collaborative path of multiple UAVs, and obtain the patrol task allocation path set; The flight path interference monitoring module is used to perform S3: extract the flight attitude data of the inertial monitoring points of the high-temperature zone path segment of the thermal pipeline in the plant area from the path set of the patrol task allocation, identify abnormal changes within the monitoring period, analyze the wind disturbance direction trend, identify the interference path segment and the disturbed direction, and generate path disturbance impact area identification information. The path adjustment and optimization module is used to execute S4: Based on the identification information of the path disturbance affected area, extract the affected path segment, analyze the angular relationship between the advance direction and the wind disturbance direction, determine whether the offset exceeds the deviation range, adjust the path node position, supplement key node information, and obtain the path point position adjustment list after the disturbance. The multi-machine collaborative path allocation module is used to execute S5: based on the path point position adjustment list after disturbance, extract the number and length parameters of the path task points, analyze the distribution status of task points, and if it is unbalanced, reorganize the path structure, adjust the task point position index, and obtain the optimized path coordination distribution structure.

9. A smart park drone patrol path optimization device, comprising a memory and a processor, characterized in that, The memory stores a computer program, and when the processor executes the computer program, it implements the smart park drone patrol path optimization method according to claim 1.

Images