Method, system and electronic equipment for multi-objective constraint planning of drone airport site selection

Abstract

The present invention discloses a multi-objective constraint planning site selection method, system and electronic equipment for drone airports, wherein the planning site selection method comprises the following steps: S1, obtaining geographic information of the target site selection area; S2, determining the performance parameters of the drone, and obtaining the flight coverage of the drone in combination with the geographic information; S3, constructing a dynamic task point model, and determining the drone task point set through the dynamic task point model; S4, obtaining the optimization target of the airport site selection, establishing an objective function according to the optimization target, constructing a site selection optimization model through the objective function, and setting constraints for the site selection optimization model; S5, using a heuristic algorithm, performing multi-objective optimization calculations based on the site selection optimization model, and obtaining the target layout of the drone airport. The technical solution disclosed by the present invention can accurately plan the navigation path, realize accurate navigation of the drone in an environment where communication is limited or silence is required, and improve the reliability of navigation and the operation capability of the drone.

Description

Technical Field

[0001] The present invention relates to the technical field of drone airport layout management, and more specifically, to a drone airport multi-objective constraint planning site selection method, system and electronic equipment. Background Art

[0002] In recent years, with the rapid development of drone technology and its wide application in logistics, patrol monitoring, emergency rescue and other fields, drone airports, as important infrastructure for drone cluster management, have gradually become a hot spot for technical research and engineering deployment. Drone airports significantly improve the operating efficiency and mission coverage capabilities of drones by providing drones with functions such as parking, charging, and mission scheduling. However, with the increasing diversification and complexity of mission requirements, the reasonable planning of the location and number of drone airports has become a key technical problem.

[0003] In the existing technology, the solution of drone airport layout has made significant progress. For example, a drone airport system that focuses on fully automated take-off and landing and efficient operation of drones has been designed, which can realize remote scheduling of tasks through intelligent charging and cloud management, and a machine nest system that can focus on the continuous execution of multiple tasks of drones in high-intensity, unmanned scenarios has emerged. The core of these systems is to ensure the efficient operation of drones in a wide-area environment, and to form a multi-drone collaborative system based on networked scheduling with drone airports as nodes. However, the current UAV airport deployment scheme still faces many technical challenges in practical applications: First, the multi-objective trade-off problem: the layout of UAV airports needs to balance multiple objectives such as covering mission requirements, reducing operating costs and meeting priority mission completion rates. Traditional single-objective optimization methods are difficult to take into account multiple requirements; Second, the problem of complex scene constraints: there are obstacles and UAV flight radius restrictions in actual scenes, which put forward additional constraints on the layout and site selection of UAV airports; Third, the problem of insufficient resource optimization: the existing methods are mostly based on empirical rules or local optimization strategies, and fail to fully consider factors such as UAV performance differences and uneven distribution of mission points, resulting in low resource utilization and affecting task execution efficiency; Fourth, the problem of poor dynamic adaptability: the existing UAV airport site selection and planning methods are mostly static designs, which are difficult to dynamically respond to real-time mission demand changes or environmental factors. It can be seen that the existing UAV airport site selection methods still cannot meet the actual application needs of UAVs.

[0004] Therefore, how to provide a multi-objective constraint planning site selection method and system for drone airports, which can perform multi-objective trade-offs, balance coverage requirements, mission operation costs, and mission completion rates, and achieve efficient layout of drone airports, has become a technical problem that needs to be urgently solved by technical personnel in this field. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides a multi-objective constraint planning site selection method and system and electronic equipment for drone airports, which can perform multi-objective trade-offs, balance coverage requirements, mission operation costs and mission completion rates, and achieve efficient layout of drone airports.

[0006] The technical solution provided by the present invention is as follows:

[0007] The present invention provides a multi-objective constraint planning site selection method for an unmanned aerial vehicle airport, comprising the following steps: S1, obtaining geographic information of a target site selection area; S2, determining performance parameters of an unmanned aerial vehicle, and obtaining a flight coverage range of the unmanned aerial vehicle in combination with the geographic information; S3, constructing a dynamic task point model, and determining a set of unmanned aerial vehicle task points through the dynamic task point model; S4, obtaining an optimization target for airport site selection, establishing an objective function according to the optimization target, constructing a site selection optimization model through the objective function, and setting constraint conditions for the site selection optimization model; S5, using a heuristic algorithm, performing multi-objective optimization calculations based on the site selection optimization model, and obtaining a target layout of an unmanned aerial vehicle airport.

[0008] Furthermore, in a preferred embodiment of the present invention, in step S1, the step of obtaining geographic information of the target site selection area includes:

[0009] Determine the geographic boundary information of the target site selection area;

[0010] Obtaining obstacle information within the target site selection area through a collection terminal, including obstacle location coordinates and obstacle height data;

[0011] The geographic boundary information and obstacle information are stored as a two-dimensional grid or a three-dimensional geographic information model.

[0012] Furthermore, in a preferred embodiment of the present invention, step S3 specifically includes:

[0013] S301: Determine the location and number of initial task points in the target site selection area, recorded as a task point set ,in Indicates the task point, is the number of initial mission points;

[0014] S302, determine each task point Contains attribute information:

[0015] ;

[0016] in Represents the geographical coordinates of the mission point, Indicates the initial priority of the task point, ranging from , Indicates the status of the task point. Indicates the deadline of the task point;

[0017] S303, introducing a dynamic task point model, and updating the task point set in real time;

[0018] S304: Obtain the updated dynamic task point set and update the optimization input, and generate the final task point set based on the task point coverage and priority. :

[0019] ;

[0020] in, is a set of dynamic task points, is the distance between the mission point and the drone airport, Indicates the maximum flight radius of the drone.

[0021] Furthermore, in a preferred embodiment of the present invention, in step S303, the step of updating the task point set in real time includes:

[0022] S303.1. According to the task point status, remove the completed task points and obtain the task point set after removal:

[0023] ;

[0024] S303.2. Determine whether there is a new task point. If there is no new task point, update the task point set and output the task point set. , i.e., a set of dynamic task points;

[0025] S303.3, if it exists A new task point is added, first determine the new task point information, and obtain the new task point set ;

[0026] Then, the eliminated task point set is combined And the newly added task point set , get the dynamic task point set ;

[0027] Then, according to the deadline and urgency of the task points in the dynamic task point set, the priority of the task points is dynamically adjusted:

[0028] ;

[0029] in, is the current time, is the time threshold, is the priority adjustment coefficient, It is the highest priority for the task point;

[0030] Finally, the adjusted dynamic task point set is output .

[0031] Furthermore, in a preferred embodiment of the present invention, in step S4, the optimization target is determined based on the number of task points covered by the site selection, the task execution cost, and the completion ratio of the priority task points. The step of establishing the objective function according to the optimization target includes:

[0032] Firstly, according to the dynamic task point set, the number of task points required to be covered by the airport site selection is determined;

[0033] Then, the task execution cost of airport site selection and the completion ratio of priority task points are obtained;

[0034] Then, a weight coefficient of the optimization target is determined, and the weight coefficient is dynamically adjusted according to the scenario requirements;

[0035] Finally, the objective function of the optimization goal is established:

[0036] ;

[0037] in, , , is the weight parameter of the optimization objective, and its value range is ; The number of mission points covered for site selection; the cost of performing the task of selecting a site for an airport; It is the completion ratio of priority task points.

[0038] Furthermore, in a preferred embodiment of the present invention, the step of obtaining the task execution cost of airport site selection includes:

[0039] According to the distance of the task point and drone speed , get the mission flight time ;

[0040] Based on the performance parameters, a power consumption model of the UAV is constructed, combined with the mission flight time. , calculate the flight energy consumption of the mission execution , The power consumption of the drone;

[0041] Determine the construction and operation costs of drone airports;

[0042] The mission execution cost of airport site selection is obtained by combining the flight time, flight energy consumption and construction and operation costs.

[0043] Furthermore, in a preferred embodiment of the present invention, the weight coefficient adjustment strategy follows the principle that the sum is 1, that is, ; The step of dynamically adjusting the weight coefficient according to the scene requirements includes:

[0044] When the scenario requires covering more mission points, improve The weight of

[0045] When the scenario requirements are cost-sensitive, improve The weight of

[0046] When the scene requirements focus on priority tasks, improve The weight of .

[0047] Furthermore, in a preferred embodiment of the present invention, in step S4, the step of setting constraints for the site selection optimization model includes:

[0048] Get the distance between the mission point and the drone airport , and determine the maximum flight radius of the drone , constrain the maximum coverage radius of the task point: ;

[0049] Determine the unique coverage of the mission point and select an airport to cover each mission point:

[0050] ;

[0051] in, For drone airports, Gather for the mission point;

[0052] Check whether the mission path between the drone airport and the mission point passes through obstacles, and perform obstacle avoidance constraints on the mission path.

[0053] Furthermore, in a preferred embodiment of the present invention, in step S5, a non-dominated sorting genetic algorithm II is used to perform multi-objective optimization calculation to obtain the target layout of the drone airport, and the specific steps include:

[0054] S501, population initialization: generating an initial population through a greedy algorithm, and obtaining an initial solution of the initial population;

[0055] S502, objective function calculation: obtaining the objective function value of each individual in the initial population through the objective function, and performing multi-objective evaluation;

[0056] S503, non-dominated sorting: Sort the individuals according to the objective function value to determine the Pareto optimal solution; then divide the non-dominated solutions into different levels and retain the better solutions;

[0057] S504, calculate crowding distance: calculate the crowding degree of each individual in the population, and give priority to selecting individuals with large crowding degrees as high-quality individuals;

[0058] S505, selection, crossover and mutation: first, select the high-quality individuals to enter the next generation population; then perform a crossover operation on the selected individuals to generate new solutions; finally, perform a mutation operation on some individuals to explore the solution space;

[0059] S506, iterative update: repeatedly perform the above operations until the maximum iteration data is reached or the target converges, stop updating and output the target layout of the drone airport.

[0060] Furthermore, in a preferred embodiment of the present invention, in step S501, the step of obtaining an initial solution of the initial population includes:

[0061] S501.1. First, sort the task points from high to low according to the task priority;

[0062] S501.2. Then, the airport site is selected. The first drone airport is placed in the area with the highest density of mission points. The next airport is placed in the location with the most mission points within the coverage radius, and so on.

[0063] S501.3, then assign the mission points to the nearest drone airport in order of priority;

[0064] S501.4. Finally, an initial solution is generated based on the airport layout and mission point allocation scheme obtained by the greedy algorithm.

[0065] The present invention also provides a multi-objective constraint planning and site selection system for drone airports, including:

[0066] An input module is used to receive geographic data of the target site selection area, UAV performance parameters, and mission point information;

[0067] An optimization module for calculating the target layout of drone airports based on the site selection optimization model and constraints;

[0068] Output module, used to generate site selection results, including drone airport layout and optimization parameters;

[0069] The output module includes a visualization unit and a data export unit. The visualization unit is used to display the drone airport layout and site optimization process in real time, including the coverage of mission points and the optimization index curve; the data export unit is used to export the site optimization results in multiple formats.

[0070] In addition, the present invention also provides an electronic device, including a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the multi-objective constraint planning and site selection method for the UAV airport.

[0071] The invention provides a multi-objective constraint planning site selection method, system and electronic device for drone airports, wherein the planning site selection method comprises the following steps: S1, obtaining geographic information of the target site selection area; S2, determining the performance parameters of the drone, and obtaining the flight coverage of the drone in combination with the geographic information; S3, constructing a dynamic task point model, and determining the drone task point set through the dynamic task point model; S4, obtaining the optimization target of the airport site selection, establishing an objective function according to the optimization target, constructing a site selection optimization model through the objective function, and setting constraints for the site selection optimization model; S5, using a heuristic algorithm, performing multi-objective optimization calculations based on the site selection optimization model, and obtaining the target layout of the drone airport. The multi-objective constraint planning site selection method for drone airports provided by the invention constructs a site selection optimization model based on multi-objective constraints by integrating artificial intelligence optimization algorithms and geographic information processing technology, which can not only realize the reasonable layout of drone airports, but also effectively improve the operating efficiency and task execution capabilities of drone networks. In the multi-objective constraint planning site selection method for the UAV airport, after determining the target site selection area, it is first necessary to obtain the geographic information of the site selection area, including geographic boundary information and obstacle information in the area; then, by combining the performance parameters of the UAV, the flight coverage of the UAV is determined in the target site selection area; then, it is necessary to consider determining the UAV mission points in the target site selection area, which include completed mission points, to-be-completed mission points and newly added mission points. For this purpose, the dynamic mission point model is constructed, and the mission points are summarized and counted to obtain the mission point set; then, the optimization target is determined based on the coverage mission requirements, mission execution costs and priority mission completion rates, and the airport optimization layout is obtained as the result to establish the objective function. After determining the constraints, combined with the objective function, a site selection optimization model based on multi-objective constraints is constructed, so that the airport site selection can balance between multiple objectives and take into account multiple needs; finally, a heuristic algorithm is used to calculate the target layout of the UAV airport, realize the efficient deployment of the UAV airport, optimize resource allocation, and improve the coverage efficiency and operating cost-effectiveness of the UAV network. Therefore, compared with the prior art, the technical solution involved in the present invention can perform multi-objective trade-offs, balance coverage requirements, mission operation costs, and mission completion rates, and achieve efficient layout of drone airports. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0073] Figure 1 A flowchart of the steps of the multi-objective constraint planning site selection method for the drone airport involved in an embodiment of the present invention;

[0074] Figure 2 A flowchart of the steps of using the non-dominated sorting genetic algorithm II to perform multi-objective optimization calculations and obtain a target layout of a drone airport in an embodiment of the present invention;

[0075] Figure 3 A flowchart of the steps of obtaining an initial solution of an initial population according to an embodiment of the present invention;

[0076] Figure 4 This is a schematic block diagram of the structure of the planning and site selection system for multi-objective constraints on drone airports involved in an embodiment of the present invention. DETAILED DESCRIPTION

[0077] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present invention.

[0078] It should be noted that when an element is referred to as being "fixed on" or "set on" another element, it can be directly on the other element or indirectly set on the other element; when an element is referred to as being "connected to" another element, it can be directly connected to the other element or indirectly connected to the other element.

[0079] It should be understood that the terms "length", "width", "up", "down", "front", "back", "first", "second", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship are based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0080] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "multiple" and "several" is two or more, unless otherwise clearly and specifically defined.

[0081] It should be noted that the structures, proportions, sizes, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification so as to facilitate understanding and reading by persons familiar with this technology. They are not used to limit the conditions under which the present invention can be implemented, and therefore have no substantive technical significance. Any structural modification, change in proportion or adjustment of size, without affecting the effects and purposes that can be achieved by the present invention, should still fall within the scope of the technical contents disclosed by the present invention.

[0082] Please Figures 1 to 4 As shown, the present invention provides a multi-objective constraint planning site selection method, system and electronic device for drone airports. By combining regional geographic information, drone performance parameters and task point priorities, a heuristic optimization algorithm is used to calculate the target layout of drone airports. It is suitable for complex environments with multiple scenarios and multiple requirements, effectively solves the site selection planning problem of drone airports in the prior art, and can significantly improve the resource allocation efficiency and task completion ability of drone cluster systems. It can be applied to drone logistics distribution, monitoring inspection, emergency rescue and other scenes. Among them, the multi-objective constraint planning site selection method for drone airports includes the following steps: S1, obtaining geographic information of the target site selection area; S2, determining the performance parameters of the drone, and obtaining the flight coverage of the drone in combination with the geographic information; S3, constructing a dynamic task point model, and determining the drone task point set through the dynamic task point model; S4, obtaining the optimization target of airport site selection, establishing an objective function according to the optimization target, constructing a site selection optimization model through the objective function, and setting constraints for the site selection optimization model; S5, using a heuristic algorithm, performing multi-objective optimization calculation based on the site selection optimization model, and obtaining the target layout of the drone airport. The technical solution involved in the present invention can perform multi-objective trade-offs, balance coverage requirements, mission operation costs, and mission completion rates, and achieve efficient layout of drone airports.

[0083] The following is a specific description of the multi-objective constraint planning site selection method for a drone airport disclosed in the present invention in combination with a specific embodiment. The multi-objective constraint planning site selection method for a drone airport specifically includes the following steps:

[0084] S1. Obtain geographic information of the target site selection area.

[0085] Specifically, in a specific embodiment of the present invention, in step S1, the step of obtaining geographic information of the target site selection area includes: determining the geographic boundary information of the target site selection area; obtaining obstacle information in the target site selection area through a collection terminal, including obstacle position coordinates and obstacle height data; combining the geographic boundary information and obstacle information to form geographic data, performing data preprocessing on the geographic data, and then storing it as a two-dimensional grid or a three-dimensional geographic information model.

[0086] Among them, in an embodiment of the present invention, step S1 is used to collect geographic information of the target site selection area after determining the target site selection area of ​​the drone; the geographic information is mainly composed of geographic boundary information and obstacle information, and the geographic boundary information is used to determine the flight coverage of the drone, and the obstacle information is used to plan the unmanned path of the drone.

[0087] Specifically, in a specific embodiment of the present invention, the step of data preprocessing includes: identifying the geographic data, determining the missing data value, locating the data missing range in the target site selection area according to the missing value, re-collecting the missing data and performing a filling operation; classifying the geographic data according to the data type, establishing data sets based on the data classification type, performing statistical analysis on the data sets, screening and removing outliers; setting a unique identifier for each individual data in the data set, constructing a comparison model and setting a preset similarity threshold in the model, inputting the individual data into the comparison model for similarity comparison with other data of the same type, traversing all individual data in the data set, determining duplicate data and performing a removal operation; finally, according to a predetermined format, unifying and converting the data for output or storage.

[0088] S2. Determine the performance parameters of the UAV and obtain the flight coverage of the UAV in combination with the geographic information.

[0089] In this embodiment, the performance parameters of the UAV include a maximum flight radius, a maximum load capacity, and a mission execution capability; wherein the mission execution capability includes the UAV endurance time and the mission completion efficiency; in step S2, the flight coverage of the UAV is obtained through the performance parameters of the UAV and combined with geographic information, and stored as mapping data; then, combined with a two-dimensional grid or a three-dimensional geographic information model, the maximum flight radius of the UAV can be determined within the target site selection area. .

[0090] S3. Construct a dynamic mission point model, and determine the drone mission point set through the dynamic mission point model.

[0091] Specifically, in the embodiment of the present invention, step S3 is used to determine the mission points that the drone needs to perform in the target site selection area. Since the site selection and planning of traditional drone airports are mostly static designs, it is difficult to dynamically respond to changes in real-time mission requirements or environmental factors, such as new mission points and changes in obstacles. Therefore, in step S3, the dynamic mission point model is used to dynamically respond to changes in mission points and scenarios, thereby enhancing the robustness and applicability of the drone airport layout plan.

[0092] Specifically, in a specific embodiment of the present invention, the step S3 specifically includes: S301, determining the location and number of initial task points in the target site selection area, recorded as a task point set ,in Indicates the task point, is the number of initial task points; S302, determine each task point Contains attribute information: ;in Represents the geographical coordinates of the mission point, Indicates the initial priority of the task point, ranging from , Indicates the status of the task point. Indicates the deadline of the task point; S303, introduces a dynamic task point model, and updates the task point set in real time; S304, obtains the updated dynamic task point set and updates the optimization input, and generates the final task point set based on the task point coverage and priority :

[0093] ;

[0094] in, is a set of dynamic task points, is the distance between the mission point and the drone airport, Indicates the maximum flight radius of the drone.

[0095] Among them, in this embodiment, the step S3 of determining the set of drone task points is specifically divided into four steps. First, according to the geographic information of the target site selection area and the actual application requirements of the drone, the number of initial task points is obtained, and the corresponding positions of each of the initial task points in the target site selection area are determined to generate a task point set; then, attribute information is set for the task points in the set, including geographic coordinates, initial priority, task point status, and deadline; then, according to the task point requirements and scene changes, a dynamic task point model is constructed, the task point set is updated, and a dynamic task point set is generated; finally, the updated dynamic task point set is obtained and the optimization input is updated, and the task point set is generated through the coverage and priority setting of the updated task points in the target site selection area. .

[0096] Specifically, in a specific embodiment of the present invention, in step S303, the step of updating the task point set in real time includes: S303.1, according to the task point status, eliminating the completed task points, and obtaining the task point set after elimination:

[0097] ;

[0098] S303.2. Determine whether there is a new task point. If there is no new task point, update the task point set and output the task point set. , that is, the dynamic task point set; S303.3, if there is A new task point is added, first determine the new task point information, and obtain the new task point set ; Then combine the removed task point set And the newly added task point set , get the dynamic task point set ; Then, dynamically adjust the priority of the task points according to the deadline and urgency of the task points in the dynamic task point set:

[0099] ;

[0100] in, is the current time, is the time threshold, is the priority adjustment coefficient, It is the highest priority for the task point;

[0101] Finally, the adjusted dynamic task point set is output .

[0102] Specifically, in the embodiment of the present invention, step S503 is used to update the initial task point set to achieve dynamic adjustment of the task points. When applied in post-disaster emergency scenarios, by dynamically adjusting the task points and the layout of the drone airport, it is possible to ensure rapid allocation of resources and priority satisfaction of emergency needs. In this embodiment, updating the initial task point set means removing completed task points according to the task point completion progress, and adding new task points according to task requirements; in the step of updating the initial task point set, first, according to the task point status, the completed task points are obtained, that is, the task points in The task points in the state are removed from the initial task point set to obtain the task point set. ; Then determine whether there is a new task point, that is, determine whether there is a Task points in the state, if there is no new task point, then output the task point set , at this time the task point set That is, the dynamic task point set. If there are new task points, the new task point set and the removed task point set are combined. Merge and obtain a dynamic task point set Then, based on the urgency and deadline of the task points in the set, the priority of the task points is readjusted to complete the update operation of the task point set and output the dynamic task point set. .

[0103] S4. Obtaining the optimization goal of airport site selection, establishing an objective function according to the optimization goal, constructing a site selection optimization model through the objective function, and setting constraints for the site selection optimization model.

[0104] Specifically, in a specific embodiment of the present invention, in step S4, the optimization target is determined by the number of task points covered by the site selection, the task execution cost, and the completion ratio of the priority task points. The step of establishing the objective function according to the optimization target includes: first, determining the number of task points required to be covered by the airport site selection according to the dynamic task point set; then obtaining the task execution cost of the airport site selection and the completion ratio of the priority task points; then determining the weight coefficient of the optimization target, and dynamically adjusting the weight coefficient according to the scenario requirements; and finally establishing the objective function of the optimization target:

[0105] ;

[0106] in, , , is the weight parameter of the optimization objective, and its value range is ; The number of mission points covered for site selection; the cost of performing the task of selecting a site for an airport; It is the completion ratio of priority task points.

[0107] Among them, in step S4, by constructing a comprehensive objective function, balancing the task coverage, operating cost and task completion rate, the efficient layout of the drone airport is realized, so that the layout of the drone airport can balance multiple objectives such as covering task requirements, reducing operating costs and meeting priority task completion rates. Based on this functional characteristic, the multi-objective constraint planning site selection method of the drone airport can be applied to logistics distribution, and the target site selection area of ​​the drone airport covers multiple distribution points. The method is used to determine the target layout of the drone airport to ensure that high-priority distribution points such as medical supplies are given priority distribution, while optimizing the energy consumption and flight time of the drone, taking into account multiple needs. In the construction step of the objective function, after obtaining the number of covered task points, the task execution cost and the completion ratio of the priority task points, it is more critical to determine the weight coefficients of the three. In this method, the weight coefficients can be adjusted according to the scene requirements, dynamically responding to the real-time task point requirements and environmental factors. Changes, finally, based on the optimization target and the weight coefficient of the optimization target, the objective function is established, and the site selection optimization model is constructed.

[0108] Specifically, in a specific embodiment of the present invention, the step of obtaining the task execution cost of airport site selection includes: according to the distance of the task point and drone speed , get the mission flight time ; Based on the performance parameters, a power consumption model of the drone is constructed, combined with the mission flight time , calculate the flight energy consumption of the mission execution , The power consumption of the UAV is calculated; the construction and operation cost of the UAV airport is determined; and the mission execution cost of the airport site selection is obtained by combining the flight time, flight energy consumption and construction and operation cost.

[0109] Specifically, in a specific embodiment of the present invention, the adjustment strategy of the weight coefficient follows the principle that the sum is 1, that is, ; The step of dynamically adjusting the weight coefficient according to the scene requirements includes: when the scene requirements cover more task points, increase When the scenario requirements are cost-sensitive, increase When the scenario requirements focus on priority task points, increase The weight of .

[0110] Among them, in the embodiment of the present invention, the task execution cost in the objective function The parameter comprehensively considers the drone energy consumption, flight time and airport deployment cost, and combines the three; and the function weight coefficient can be adjusted according to different application scenarios. When the scenario needs to cover more mission points, is cost-sensitive or focuses on priority mission points, it can be increased respectively. , , Through cost control and combined with weight adjustment of different application scenarios, the best balance between goals is achieved to ensure that the system achieves the best compromise between efficiency and cost, thereby improving the efficiency of resource use and the overall performance of the system.

[0111] Specifically, in a specific embodiment of the present invention, in step S4, the step of setting constraints for the site selection optimization model includes: obtaining the distance between the mission point and the drone airport , and determine the maximum flight radius of the drone , constrain the maximum coverage radius of the task point: ; Determine the unique coverage of the mission point and select an airport to cover each mission point:

[0112] ;

[0113] in, For drone airports, Gather for the mission point;

[0114] Check whether the mission path between the drone airport and the mission point passes through obstacles, and perform obstacle avoidance constraints on the mission path.

[0115] Among them, in step S4, the site selection optimization model needs to be conditionally constrained according to the operation scene to improve the applicability of the method to complex scenes. In the actual scene of drone operation, there are obstacles (such as mountains, high buildings, etc.) and drone flight radius restrictions, which put forward additional constraints on the layout and site selection of drone airports. Therefore, conditional constraints are required in the site selection optimization model. In this embodiment, the constraints include maximum coverage radius, unique coverage of task points, and obstacle avoidance constraints. Specifically, the distance between the task point and the drone airport is Constrain it to the maximum flight radius of the drone Second, according to the operation requirements, a unique airport is set to cover the mission points in the set to ensure the smooth progress of the UAV operation. Third, obstacle avoidance constraints are performed based on the geographic information of the target site selection area.

[0116] Specifically, in a specific embodiment of the present invention, the obstacle avoidance constraint step includes: obtaining the geographic coordinates of the drone airport and the mission point, and determining the drone mission execution area according to the geographic coordinates; then obtaining the obstacle information in the target site selection area, and determining the obstacle data in the mission execution area based on the obstacle information; then the drone constructs a preliminary mission path according to the geographic coordinates and obstacle data; the drone takes off at the airport according to the preliminary mission path, collects environmental information during flight in real time, including meteorological information and obstacle information, and obtains the real-time position coordinates of the drone; constructs a dynamic path optimization model, uses the environmental information, the geographic coordinates of the mission point and the real-time position coordinates of the drone as optimization features, and inputs them into the dynamic path optimization model, performs obstacle avoidance constraints and meteorological constraints on the drone, and obtains a real-time updated mission path.

[0117] S5. Using a heuristic algorithm, perform multi-objective optimization calculations based on the site selection optimization model to obtain the target layout of the drone airport.

[0118] Specifically, in a specific embodiment of the present invention, the heuristic algorithm includes a genetic algorithm and a simulated annealing algorithm.

[0119] Specifically, in a specific embodiment of the present invention, in step S5, a non-dominated sorting genetic algorithm II is used to perform multi-objective optimization calculations to obtain the target layout of the drone airport, and the specific steps include: S501, population initialization: generating an initial population through a greedy algorithm, and obtaining an initial solution of the initial population; S502, objective function calculation: obtaining the objective function value of each individual in the initial population through the objective function, and performing multi-objective evaluation; S503, non-dominated sorting: sorting the individuals according to the objective function value to determine the Pareto optimal solution, that is, the non-dominated Solution; then divide the non-dominated solutions into different levels, and retain the better solutions; S504, calculate the crowding distance: calculate the crowding degree of each individual in the population, and give priority to individuals with large crowding degrees as high-quality individuals; S505, selection, crossover and mutation: first select the high-quality individuals to enter the next generation population; then perform a crossover operation on the selected individuals to generate new solutions; finally, perform mutation operations on some individuals to explore the solution space; S506, iterative update: repeatedly perform the above operations until the maximum iteration data is reached or the target converges, stop updating and output the target layout of the drone airport.

[0120] Among them, in the embodiment of the present invention, a non-dominated sorting genetic algorithm II (NSGA-II) is used to perform multi-objective optimization calculations to obtain the optimal drone airport layout. In step S5, the steps of the multi-objective optimization calculation specifically include population initialization, objective function calculation, non-dominated sorting, calculation of congestion distance, selection, crossover and mutation, and iterative update. First, based on the site selection optimization model, a greedy algorithm is used to initialize the population of the drone airport layout plan, and an initial population is randomly generated. Each individual in the initial population represents a drone airport site selection plan, including layout locations and covered mission points; then, the objective function value of each individual is calculated based on the individual information in the population and combined with the objective function. , and perform multi-objective evaluation; next, sort the individuals according to the objective function value, or more precisely, sort the site selection and layout schemes represented by the individuals, determine the Pareto optimal solution set by sorting the order, and hierarchically divide the non-dominated solutions in the optimal solution set, and find and retain the better solutions; then calculate the crowding distance of the population individuals. In multi-objective optimization, the crowding distance can measure the distribution density of individuals in the target space. By selecting individuals with a larger crowding distance for crossover and mutation operations, premature convergence can be avoided and the algorithm can be ensured to explore a wider solution space; then select high-quality individuals for crossover and mutation operations to increase population diversity, which helps the genetic algorithm to explore in the search space and find a better solution; finally, according to the maximum number of iterations or target convergence, repeatedly perform multi-objective optimization calculation operations until the stop condition is reached, and output the target layout of the drone airport.

[0121] Specifically, in a specific embodiment of the present invention, in step S501, the step of obtaining an initial solution of the initial population includes: S501.1, firstly sorting the task points from high to low according to the task priority; S501.2, then selecting the airport site, placing the first drone airport in the task point area with the highest density, selecting the location with the most task points within the coverage radius to place the next airport, and so on; S501.3, then allocating the task points to the nearest drone airport in order of priority; S501.4, finally generating an initial solution based on the airport layout and task point allocation plan obtained by the greedy algorithm.

[0122] Among them, in step S501, the initial solution of the initial population is obtained by a greedy algorithm; the purpose of calculating the initial solution of the initial population is to provide a reasonable starting point for multi-objective optimization, and to ensure that the optimal solution can be effectively explored by the algorithm later; in this embodiment, step S501 generates an initial solution according to the airport layout plan and the task point allocation plan, and the airport layout and task point allocation plan are calculated and obtained by a greedy algorithm: among them, firstly, the airport site is selected, and the drone airport is placed in the target site selection area based on the task density, that is, the first drone airport is placed in the task point area with the highest density, and then the location with the most task points within the coverage radius is selected to place the next airport, and so on to obtain the drone site selection layout plan; secondly, the task point allocation plan is determined, firstly the task points are sorted according to the priority, and then the task points are allocated to the nearest drone airport in order according to the priority, so as to obtain the task point allocation plan. Finally, based on the two schemes of airport layout and task point allocation, the initial solution is obtained.

[0123] Specifically, in the specific embodiment of the present invention, step S503 is specifically as follows: S503.1. Preset For individuals in the population, , is the number of individuals in the population; S503.2, sorting the individuals in the population according to the objective function value; S503.3, setting , then all Individual , and Compare the dominant and non-dominant relationships; S503.4, if no individual Better than , then mark the individual at this time For non-dominant individuals; S503.5, then , repeat steps S503.3 and S503.4 until all non-dominated individuals, i.e., non-dominated solutions, are found; S503.6, a non-dominated individual set is established based on the non-dominated individuals, and it is set as the first non-dominated layer; S503.7, then steps S503.3, S503.3 and S503.4 are repeated in sequence for the individuals in the non-dominated individual set to obtain the second non-dominated layer, and the hierarchical division is performed in this way, and the individuals of the population with a low level are selected as the better solution and retained.

[0124] Specifically, the present invention also provides a planning and site selection system for multi-objective constraints of a drone airport, including: an input module for receiving geographic data of a target site selection area, drone performance parameters and mission point information; an optimization module for calculating the target layout of the drone airport based on a site selection optimization model and constraint conditions; an output module for generating site selection results, including the drone airport layout and optimization parameters; the output module includes a visualization unit and a data export unit, the visualization unit is used to display the drone airport layout and site selection optimization process in real time, including the coverage of mission points and optimization index curves; the data export unit is used to export the site selection optimization results in multiple formats.

[0125] In addition, an embodiment of the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the multi-objective constraint planning and site selection method for the UAV airport.

[0126] In summary, the multi-objective constraint planning and site selection method and system for drone airports involved in the embodiments of the present invention can be widely used in drone logistics distribution, monitoring inspection, emergency rescue and other scenarios. The planning and site selection method constructs a site selection optimization model by combining regional geographic information, drone performance parameters and task point requirements, and uses a heuristic algorithm to calculate the target layout of the drone airport, aiming to achieve efficient deployment of drone airports, optimize resource allocation, and improve the coverage efficiency and operating cost-effectiveness of drone networks. In the multi-objective constraint planning and site selection method for drone airports, the steps first determine the optimization target based on coverage task requirements, task execution costs and priority task completion rates, obtain the airport optimization layout as a result to establish an objective function, and construct a site selection optimization model based on multi-objective constraints in combination with the objective function, so that the airport site selection can achieve a flexible balance between multiple targets, especially between coverage, operating costs and task completion rates, and can adjust weights for different application scenarios to achieve the best balance between targets, ensuring that the system achieves the best compromise between efficiency and cost, thereby improving the resource utilization efficiency and the overall performance of the system. Secondly, in this method, the site selection optimization model can support a variety of complex constraints, such as obstacle avoidance, flight radius restriction, task priority distribution, etc., especially in the process of UAV mission execution, it can identify and avoid obstacles in real time to ensure flight safety; at the same time, by dynamically adjusting the flight radius and task priority of the UAV, it ensures that various tasks are completed efficiently in order of priority, further improving the task completion rate and system stability. Finally, the heuristic algorithm is used to calculate the target layout of the UAV airport, and in the face of changes in task points or environmental conditions, this method constructs a dynamic task point model, dynamically updates the task point set, and adjusts the UAV airport layout and flight strategy in real time according to environmental factors and task point changes. It flexibly responds to environmental changes, such as weather changes, new obstacles, sudden tasks, etc., and makes adjustments quickly. Through intelligent scheduling and path planning, the flexibility, robustness and real-time response capabilities of the system are effectively improved, ensuring that it can still maintain efficient and stable operation in a complex dynamic environment. It can be seen that compared with the prior art, the technical solution involved in the present invention has multi-objective trade-off capabilities and dynamic adjustment capabilities. It adopts heuristic algorithms and multi-objective optimization technologies, can efficiently calculate the optimal layout of drone airports, and supports complex scene constraints such as obstacle avoidance and flight radius restrictions. It can be applied to airport site selection in complex scenes.

[0127] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. The multi-objective constraint planning method for the location selection of UAV airports is characterized by: The following steps are involved: S1. Obtaining geographic information of the target site selection area; S2. Determine the performance parameters of the UAV and obtain the flight coverage of the UAV in combination with the geographic information; S3, constructing a dynamic mission point model, and determining a set of UAV mission points through the dynamic mission point model; S4, obtaining an optimization target for airport site selection, establishing an objective function according to the optimization target, constructing a site selection optimization model through the objective function, and setting constraints for the site selection optimization model; S5. Using a heuristic algorithm, perform multi-objective optimization calculation based on the site selection optimization model to obtain the target layout of the drone airport; The step S3 specifically includes: S301: Determine the location and number of initial task points in the target site selection area, recorded as a task point set ,in Indicates the task point, is the number of initial mission points; S302, determine each task point Contains attribute information: ； in Represents the geographical coordinates of the mission point, Indicates the initial priority of the task point, ranging from , Indicates the status of the task point. Indicates the deadline of the task point; Indicates unassigned task points; Indicates the task point in progress; Indicates the completed task points; S303, introducing a dynamic task point model, and updating the task point set in real time; S304: Obtain the updated dynamic task point set and update the optimization input, and generate the final task point set based on the task point coverage and priority. : ； in, is a set of dynamic task points, is the distance between the mission point and the drone airport, Indicates the maximum flight radius of the drone.

2. The multi-objective constraint planning site selection method for drone airports according to claim 1 is characterized in that: In step S303, the step of updating the task point set in real time includes: S303.

1. According to the task point status, remove the completed task points and obtain the task point set after removal: ； S303.

2. Determine whether there is a new task point. If there is no new task point, update the task point set and output the task point set. , i.e., a set of dynamic task points; S303.3, if it exists A new task point is added, first determine the new task point information, and obtain the new task point set ; Then, the eliminated task point set is combined And the newly added task point set , get the dynamic task point set ; Then, according to the deadline and urgency of the task points in the dynamic task point set, the priority of the task points is dynamically adjusted: ； in, is the current time, is the time threshold, is the priority adjustment coefficient, It is the highest priority for the task point; Finally, the adjusted dynamic task point set is output ; in, Indicates the emergency situation of the mission point.

3. The multi-objective constraint planning site selection method for drone airport according to claim 1 is characterized in that: In step S4, the optimization target is determined based on the number of task points covered by the site selection, the task execution cost, and the completion ratio of the priority task points. The steps of establishing the objective function according to the optimization target include: Firstly, according to the dynamic task point set, the number of task points required to be covered by the airport site selection is determined; Then, the task execution cost of airport site selection and the completion ratio of priority task points are obtained; Then, a weight coefficient of the optimization target is determined, and the weight coefficient is dynamically adjusted according to the scenario requirements; Finally, the objective function of the optimization goal is established: ； in, , , is the weight parameter of the optimization objective, and its value range is ; The number of mission points covered for site selection; the cost of performing the task of selecting a site for an airport; It is the completion ratio of priority task points.

4. The multi-objective constraint planning site selection method for drone airport according to claim 3 is characterized in that: The steps to obtain the task execution cost of airport site selection include: According to the distance of the task point and drone speed , get the mission flight time ; Based on the performance parameters, a power consumption model of the UAV is constructed, combined with the mission flight time. , calculate the flight energy consumption of the mission execution , The power consumption of the drone; Determine the construction and operation costs of drone airports; The mission execution cost of airport site selection is obtained by combining the flight time, flight energy consumption and construction and operation costs.

5. The multi-objective constraint planning site selection method for drone airport according to claim 3 is characterized in that: The adjustment strategy of the weight coefficient follows the principle that the sum is 1, that is, ; The step of dynamically adjusting the weight coefficient according to scenario requirements includes: When the scenario requires covering more mission points, improve The weight of When the scenario requirements are cost-sensitive, improve The weight of When the scene requirements focus on priority tasks, improve The weight of .

6. The multi-objective constraint planning site selection method for drone airport according to claim 1 is characterized in that: In step S4, the step of setting constraints for the site selection optimization model includes: Get the distance between the mission point and the drone airport , and determine the maximum flight radius of the drone , constrain the maximum coverage radius of the task point: ; Determine the unique coverage of the mission point and select an airport to cover each mission point: ； in, For drone airports, Gather for the mission point; Check whether the mission path between the drone airport and the mission point passes through obstacles, and perform obstacle avoidance constraints on the mission path.

7. The multi-objective constraint planning site selection method for drone airport according to claim 1 is characterized in that: In step S5, a non-dominated sorting genetic algorithm II is used to perform multi-objective optimization calculation to obtain the target layout of the drone airport. The specific steps include: S501, population initialization: generating an initial population through a greedy algorithm, and obtaining an initial solution of the initial population; S502, objective function calculation: obtaining the objective function value of each individual in the initial population through the objective function, and performing multi-objective evaluation; S503, non-dominated sorting: Sort the individuals according to the objective function value to determine the Pareto optimal solution; then divide the non-dominated solutions into different levels and retain the better solutions; S504, calculate crowding distance: calculate the crowding degree of each individual in the population, and give priority to selecting individuals with large crowding degrees as high-quality individuals; S505, selection, crossover and mutation: first, select the high-quality individuals to enter the next generation population; then perform a crossover operation on the selected individuals to generate new solutions; finally, perform a mutation operation on some individuals to explore the solution space; S506, iterative update: repeatedly perform the above operations until the maximum iteration data is reached or the target converges, stop updating and output the target layout of the drone airport.

8. A multi-objective constrained planning and site selection system for drone airports, the system being used to execute the multi-objective constrained planning and site selection method for drone airports as described in any one of claims 1 to 7, characterized in that: include: An input module is used to receive geographic data of the target site selection area, UAV performance parameters, and mission point information; An optimization module for calculating the target layout of drone airports based on the site selection optimization model and constraints; Output module, used to generate site selection results, including drone airport layout and optimization parameters; The output module includes a visualization unit and a data export unit. The visualization unit is used to display the drone airport layout and site optimization process in real time, including the coverage of mission points and the optimization index curve; the data export unit is used to export the site optimization results in multiple formats.

9. An electronic device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the multi-objective constraint planning site selection method for the drone airport as described in any one of claims 1 to 7.

Images