Low-altitude penetration airway planning method based on improved particle swarm optimization
By improving the particle swarm optimization algorithm to construct a route planning model, the optimal trajectory is found and smoothed, which solves the problems of low search efficiency and local optima in existing algorithms in low-altitude penetration, and realizes efficient low-altitude penetration route planning.
Patent Information
- Application Number
- CN202512014422.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-29
- Publication Date
- 2026-02-17
AI Technical Summary
Existing route planning algorithms are inefficient and computationally intensive in three-dimensional space, and intelligent optimization algorithms are prone to getting stuck in local optima, making it difficult to generate a globally optimal solution.
An improved particle swarm optimization (PSO) algorithm is used to construct a route planning environment model. Combining topography, enemy radar and air defense fire distribution, the optimal waypoint is found through the improved PSO algorithm, and the optimal trajectory is obtained by smoothing with B-spline curves.
It generates optimal flight paths that can effectively avoid threats in low-altitude environments, improves the success rate of low-altitude penetration missions, reduces the probability of ground collisions and being killed, and enables rapid and covert mission execution.
Smart Images
Figure CN121540168A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The application belongs to the field of aircraft route planning, and particularly relates to a low-altitude penetration route planning method based on an improved particle swarm algorithm. BACKGROUND
[0002] The route planning technology is a key technology in the field of low-altitude penetration. Firstly, the planned path can effectively avoid the detection of the other party and the attack of the threat of the other party, and secondly, the path can avoid dangerous terrain, adverse environment and artificial obstacles that may affect flight, so as to ensure the maximum survivability of the aircraft.
[0003] Since the 1980s, the route planning of special task flight has been continuously developed, and a large amount of work has been done in this field. The current route planning algorithm includes traditional algorithms such as A* algorithm, RRT algorithm and artificial potential field method, and intelligent optimization algorithms such as ant colony algorithm, particle swarm algorithm and genetic algorithm. These algorithms first establish a reasonable optimization index, fully consider the topography of the task area, the distribution of the radar and air defense firepower of the other party, and combine a series of constraint conditions such as the performance parameters of the aircraft, so as to plan a feasible low-altitude penetration route for the aircraft from the starting point to the target point, so that the aircraft reaches the optimal or suboptimal under the specified performance index. However, the traditional algorithm has low search efficiency and large calculation amount in three-dimensional space, and the intelligent optimization algorithm shows certain superiority in convergence speed, but is prone to the problem of falling into local optimum and may not obtain the global optimal solution. Therefore, the application provides a low-altitude penetration route planning method based on an improved particle swarm algorithm, which effectively solves the problem of falling into local optimum in solving the optimization problem.
[0004] Therefore, there is an urgent need for a technical solution to overcome or alleviate at least one of the above-mentioned defects of the prior art. SUMMARY
[0005] The application aims to provide a low-altitude penetration route planning method based on an improved particle swarm algorithm to solve at least one problem existing in the prior art.
[0006] The technical scheme of the application is:
[0007] The first aspect of the application provides a low-altitude penetration route planning method based on an improved particle swarm algorithm, comprising:
[0008] Step S1, constructing a route planning environment model;
[0009] Step S2, finding an optimal track point by an improved particle swarm algorithm according to the route planning environment model;
[0010] Step S3, performing smoothing processing on the optimal track point to obtain an optimal trajectory.
[0011] In at least one embodiment of the present application, in step S1, the route planning environment model is constructed, comprising:
[0012] S1.1, obtaining route planning information, constructing a route planning environment model;
[0013] S1.2, determining the constraint conditions of the route planning environment model:
[0014] S1.3, constructing the cost function of the route planning environment model.
[0015] In at least one embodiment of the present application, in S1.1, the route planning information is obtained, and the route planning environment model is constructed, comprising:
[0016] Obtaining route planning information;
[0017] The mathematical description of constructing the route planning environment model is:
[0018] ;
[0019] Wherein, is the position of the waypoint at time t, is the center coordinate of the i th threat, R i is the threat radius of the i th threat;
[0020] The environment map is superimposed and fused with the radar model and the equipment model, and the expression of the terrain fusion is:
[0021] ;
[0022] Wherein, z1(x,y) is the height value of the reference terrain, z2(x,y) is the height value of the mountain peak, z radar (x,y) is the radar position, z antigun (x,y) is the equipment position.
[0023] In at least one embodiment of the present application, the route planning information comprises an environment map, a threat area, a starting point position of route planning, and a target position of route planning.
[0024] In at least one embodiment of the present application, in S1.2, the constraint conditions of the route planning environment model comprise:
[0025] Flight height limit:
[0026] ;
[0027] Wherein, z terrain (i) is the terrain height, z safe is the minimum flight safety height, z followThe maximum height above ground level to achieve the highest concealment when following the terrain for the aircraft;
[0028] The flight path inclination angle limit:
[0029] ;
[0030] wherein z i is the elevation value corresponding to the i-th waypoint, z i-1 is the elevation value corresponding to the i-1-th waypoint, and d is the horizontal distance between the two waypoints, is the maximum flight path inclination angle;
[0031] The maximum normal acceleration limit:
[0032] ;
[0033] wherein, is the trajectory curvature, is the normal acceleration, V is the flight speed, and g is the gravitational acceleration;
[0034] The flight speed limit:
[0035] ;
[0036] wherein V min is the minimum flight speed, and V max is the maximum flight speed.
[0037] In at least one embodiment of the present application, in S1.3, the cost function of the waypoint planning environment model is:
[0038] The total distance cost function:
[0039] ;
[0040] wherein f dis is the total distance cost, is the i-th waypoint position, is the i+1-th waypoint position;
[0041] The threat cost function:
[0042] ;
[0043] ;
[0044] wherein f threat is the threat cost, R threat is the threat radius, d threat is the threat distance, is the threat center coordinate.
[0045] In at least one embodiment of the present application, in step S2, the optimal path point is found by improving the particle swarm algorithm according to the path planning environment model, comprising:
[0046] S2.1, determining a search space according to the environment map, setting the number of particle populations, the maximum number of iterations, the inertia weight factor and the learning factor;
[0047] S2.2, randomly generating an initial particle population in the search space, initializing the initial position and initial speed of each particle;
[0048] S2.3, taking the cost function as the fitness function, calculating the initial fitness function value of each particle, updating the initial individual optimal solution and the global optimal solution according to the initial fitness function value, as the first generation individual historical optimal solution and the global optimal solution;
[0049] S2.4, updating the position and speed of each particle;
[0050] S2.5, judging whether the particle satisfies the constraint condition under the current number of iterations, if not, discarding the current iteration and returning to S2.3;
[0051] S2.6, calculating the fitness function value of each particle under the current number of iterations, and comparing it with the individual historical optimal value and the global optimal solution, updating the particle individual optimal position and the global optimal position of the particle swarm;
[0052] S2.7, judging whether the particle swarm algorithm reaches the maximum number of iterations, if yes, outputting the optimal solution as the optimal path point, if not, returning to S2.3.
[0053] In at least one embodiment of the present application, in S2.4,
[0054] The position of the i-th particle at the t+1 iteration is:
[0055] ;
[0056] The speed of the i-th particle at the t+1 iteration is:
[0057] ;
[0058] wherein, 、 is the particle position, 、 is the particle speed, is the contraction factor, w is the inertia weight factor, is the historical optimal solution, For global optimal solution, c1, c2 are learning factors, r1, r2 are random numbers between (0, 1).
[0059] In at least one embodiment of the present application, the optimal track is obtained by smoothing the optimal track point in step S3, comprising:
[0060] The optimal track is obtained by interpolating and smoothing the optimal track point by a B-spline curve.
[0061] The second aspect of the present application provides a low-altitude penetration flight path planning system based on an improved particle swarm algorithm, based on the low-altitude penetration flight path planning method based on the improved particle swarm algorithm as described above, comprising:
[0062] A model construction module is configured to construct a flight path planning environment model.
[0063] An optimal track point acquisition module is configured to obtain an optimal track point by an improved particle swarm algorithm according to the flight path planning environment model.
[0064] A smoothing module is configured to smooth the optimal track point to obtain an optimal track.
[0065] The third aspect of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor implements the low-altitude penetration flight path planning method based on the improved particle swarm algorithm as described above when executing the computer program.
[0066] The fourth aspect of the present application provides a computer readable storage medium, which stores a computer program, wherein the computer program is executed by a processor to implement the low-altitude penetration flight path planning method based on the improved particle swarm algorithm as described above.
[0067] The present application has at least the following beneficial technical effects:
[0068] The low-altitude penetration flight path planning method based on the improved particle swarm algorithm of the present application can timely avoid low-altitude environmental threats, generate optimal tracks, and guide the aircraft to quickly and stealthily penetrate the target area to perform tasks. BRIEF DESCRIPTION OF DRAWINGS
[0069] Fig. 1 is a flow chart of the low-altitude penetration flight path planning method based on the improved particle swarm algorithm of one embodiment of the present application;
[0070] Fig. 2 is a schematic diagram of the flight path planning simulation result of one embodiment of the present application. DETAILED DESCRIPTION
[0071] For the purposes of making the purposes, technical solutions and advantages of the present application clearer, the technical solutions in the embodiments of the present application will be described in more detail below with reference to the drawings in the embodiments of the present application. In the drawings, identical or similar reference numerals represent identical or similar elements or elements having identical or similar functions throughout. The described embodiments are part of the embodiments of the present application, rather than all the embodiments. The embodiments described below with reference to the drawings are exemplary and are intended to explain the present application, and cannot be understood as limiting the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application. The embodiments of the present application will be described in detail below with reference to the drawings.
[0072] In the description of the present application, it should be understood that the terms "center", "longitudinal", "transverse", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship shown in the drawings, and are only for the purpose of facilitating the description of the present application and simplifying the description, and do not indicate or imply 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 scope of protection of the present application.
[0073] The embodiments of the present application will be described in detail below with reference to the drawings. Figs. 1-2 The present application will be described in further detail.
[0074] The first aspect of the present application provides a low-altitude penetration route planning method based on an improved particle swarm algorithm, comprising the following steps:
[0075] Step S1, constructing a route planning environment model;
[0076] Step S2, according to the route planning environment model, finding the optimal track point by the improved particle swarm algorithm;
[0077] Step S3, smoothing the optimal track point to obtain the optimal trajectory.
[0078] The low-altitude penetration route planning method based on the improved particle swarm algorithm of the present application, first, in step S1, a route planning environment model is constructed, including:
[0079] S1.1, obtaining route planning information to construct a route planning environment model;
[0080] Obtaining route planning information, the route planning information includes an environment map, a threat area, a starting point position of route planning, and a target position of route planning.
[0081] In one embodiment of the present application, a digital elevation map is acquired, the size of the task flight area is determined, and the threat area, the starting point and the end point in the current low-altitude penetration task are determined.
[0082] The threat range of radar detection, ground-to-air missile and high-powered gun in the task environment is simulated by using a hemisphere, and the mathematical description of the flight path planning environment model is constructed as follows:
[0083] ;
[0084] wherein, is the position of the waypoint at time t, is the center coordinate of the i-th threat, and R i is the threat radius of the i-th threat;
[0085] The environment map is superimposed and fused with the radar model and the equipment model, and the expression of the terrain fusion is as follows:
[0086] ;
[0087] wherein, z1(x, y) is the height value of the reference terrain, z2(x, y) is the height value of the mountain peak, and z radar (x, y) is the position of the radar, and z antigun (x, y) is the position of the equipment.
[0088] S1.2, determine the constraint conditions of the flight path planning environment model:
[0089] The constraint conditions include:
[0090] Flight height limit:
[0091] ;
[0092] wherein, z terrain (i) is the terrain height, z safe is the minimum flight safety height, and z follow is the maximum height from the ground when the aircraft realizes terrain following to achieve concealment;
[0093] Flight path inclination angle limit:
[0094] ;
[0095] wherein, z i is the elevation value corresponding to the i-th waypoint, z i-1 is the elevation value corresponding to the i-1-th waypoint, d is the horizontal distance between the two waypoints, is the maximum flight path inclination angle;
[0096] Maximum normal overload limit:
[0097] ;
[0098] in, For trajectory curvature, For normal overload, V is the flight speed, and g is the acceleration due to gravity;
[0099] Flight speed limit:
[0100] ;
[0101] Among them, V min For the minimum flight speed, V max This is the maximum flight speed.
[0102] S1.3, Cost function for constructing the route planning environment model.
[0103] For the construction of the cost function, stealth and security are used as the indicators of penetration capability. The objective function is designed to minimize the total penetration cost and the cost of the threat received.
[0104] In this embodiment, the cost function of the route planning environment model is:
[0105] Total range cost function:
[0106] ;
[0107] Among them, f dis For the cost of the total voyage, Let i be the location of the i-th waypoint. This represents the position of the (i+1)th waypoint.
[0108] Threat cost function:
[0109] ;
[0110] ;
[0111] Among them, f threat As a threat, R threat For the threat radius, d threat For threat distance, Coordinates of the threat center.
[0112] The low-altitude penetration route planning method based on an improved particle swarm optimization (PSO) algorithm in this application, in step S2, finds the optimal waypoint using the improved PSO algorithm based on the route planning environment model. Compared to the traditional PSO algorithm, the improved PSO algorithm adjusts the learning factor to address the local optima problem in finding the optimal waypoint. For example... Fig. 2 As shown, the specific process includes:
[0113] S2.1, determine the search space according to the environment map, set the number of particle population n_pop, the maximum number of iterations Max_Iteration, the inertia weight factor w and the learning factor c1, c2; the maximum number of iterations is the algorithm termination condition;
[0114] S2.2, randomly generate an initial particle population in the search space, and initialize the initial position and initial speed of each particle;
[0115] S2.3, take the cost function as the fitness function, calculate the initial fitness function value of each particle, and update the initial individual optimal solution and the global optimal solution as the first generation individual historical optimal solution Pbest and the global optimal solution Gbest according to the initial fitness function value; the fitness function value is the cost function value constructed;
[0116] S2.4, update the position and speed of each particle;
[0117] The position of the i-th particle at the t+1th iteration is:
[0118] ;
[0119] The velocity of the i-th particle at the t+1th iteration is:
[0120] ;
[0121] Wherein, , is the particle position, , is the particle velocity, is the contraction factor, w is the inertia weight factor, is the historical optimal solution, is the global optimal solution, c1, c2 is the learning factor, r1, r2 is a random number between (0, 1).
[0122] The contraction factor is defined as:
[0123] ;
[0124] If the particle speed is too high, it may miss the global optimal solution; on the contrary, the speed of the particle is too small, which cannot search enough, resulting in falling into local optimum. The contraction factor effectively controls the speed of the particle by selecting appropriate parameters, so that the algorithm reaches an effective balance between the global optimal solution and the local optimal solution.
[0125] S2.5, judge whether the particle satisfies the constraint condition under the current number of iterations, if not, discard the current iteration and return to S2.3;
[0126] determine whether the updated particle meets the flight height limit, the flight path inclination angle limit, the maximum normal overload limit, and the flight speed limit, and if not, the current update is invalid;
[0127] S2.6, calculate the fitness function value of each particle at the current iteration number, and compare it with the individual historical optimal value and the global optimal solution, update the particle individual optimal position and the global optimal position of the particle group;
[0128] Update the fitness function value, if the current particle fitness is better than the historical best fitness, update the current particle best fitness and best position; if the current particle best fitness is better than the global historical best fitness, update the historical best individual Pbest, and update Gbest with the current group best individual.
[0129] S2.7, determine whether the particle swarm algorithm reaches the maximum iteration number, if yes, output the optimal solution as the optimal track point, if not, return to S2.3.
[0130] The low-altitude penetration route planning method based on the improved particle swarm algorithm of the application, in step S3, the optimal track point is smoothed to obtain the optimal trajectory, which comprises:
[0131] The optimal trajectory is obtained by interpolating and smoothing the optimal track point by a B-spline curve.
[0132] For track smoothing, the optimal track point is found by the improved particle swarm algorithm , and the optimal track obtained therefrom is composed of multiple straight line segments, which will produce more inflection points, which is limited by the aircraft maneuvering performance, and the track is difficult to adapt to the flight requirements. Therefore, the track point is interpolated and smoothed by a uniform B-spline curve to obtain an optimal smooth trajectory, as shown in Fig. 2 .
[0133] The low-altitude penetration route planning method based on the improved particle swarm algorithm of the application realizes low-altitude penetration route planning through the improved particle swarm algorithm. The particle swarm algorithm has the advantages of fast convergence speed and strong robustness, and considers the terrain constraints, enemy threats, flight speed limits, and flight path inclination angle limits in the low-altitude environment to plan the optimal trajectory, so that the aircraft can well follow the terrain, avoid the terrain and threats, reduce the probability of crashing and being killed, thereby improving the mission success rate of the aircraft in low-altitude penetration, improving the ability of the aircraft in low-altitude penetration, and enabling the long-range aircraft to well complete the task requirements in low-altitude penetration. In the improved particle swarm algorithm, a contraction factor is introduced into the particle speed update formula, which avoids falling into a local optimal solution to a certain extent.
[0134] The second aspect of the present application provides a low-altitude penetration route planning system based on an improved particle swarm algorithm, based on the low-altitude penetration route planning method based on the improved particle swarm algorithm, comprising:
[0135] a model construction module, configured to construct a route planning environment model;
[0136] an optimal track point acquisition module, configured to acquire an optimal track point by using the improved particle swarm algorithm according to the route planning environment model;
[0137] a smoothing processing module, configured to perform smoothing processing on the optimal track point to obtain an optimal trajectory.
[0138] The third aspect of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and the processor implements the low-altitude penetration route planning method based on the improved particle swarm algorithm when executing the computer program.
[0139] The fourth aspect of the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the low-altitude penetration route planning method based on the improved particle swarm algorithm.
[0140] The above is merely a specific implementation of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of changes or replacements within the technical range disclosed in the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.
Claims
1. A low-altitude penetration route planning method based on an improved particle swarm algorithm, characterized in that, The method comprises the following steps: Step S1, constructing a route planning environment model; Step S2, finding an optimal track point by using an improved particle swarm algorithm according to the route planning environment model; Step S3, performing smoothing processing on the optimal track point to obtain an optimal trajectory.
2. The low-altitude penetration route planning method based on the improved particle swarm algorithm according to claim 1, characterized in that, In step S1, the route planning environment model is constructed, comprising: S1.1, acquiring route planning information and constructing a route planning environment model; S1.2, determining constraint conditions of the route planning environment model; S1.3, constructing a cost function of the route planning environment model.
3. The low-altitude penetration route planning method based on the improved particle swarm algorithm according to claim 2, characterized in that, In S1.1, the route planning information is acquired and the route planning environment model is constructed, comprising: The route planning information is acquired. The mathematical description of the route planning environment model is constructed as follows: ； wherein, is the position of the waypoint at time t, is the center coordinate of the ith threat, R i is the threat radius of the ith threat; The environment map is superimposed and fused with a radar model and an equipment model, and the expression of the terrain fusion is obtained as follows: ； wherein z1(x, y) is the height value of the reference terrain, z2(x, y) is the height value of the mountain peak, z radar (x, y) is the radar position, z antigun (x, y) is the equipment position.
4. The low-altitude penetration route planning method based on the improved particle swarm algorithm according to claim 3, characterized in that, The route planning information comprises an environment map, a threat area, a starting point position of route planning and a target position of route planning.
5. The low-altitude penetration route planning method based on the improved particle swarm algorithm according to claim 4, characterized in that, In S1.2, the constraint conditions of the route planning environment model comprise: Flight height limitation; ； where z terrain (i) is the terrain height, z safe is the minimum flight safety height, z follow is the maximum height above ground reached by the aircraft to achieve concealment while following the terrain Track inclination angle limitation; ； wherein z i is the elevation value corresponding to the i-th waypoint, z i-1 is the elevation value corresponding to the i-1-th waypoint, d is the horizontal distance between the two waypoints, is the maximum track angle. Maximum normal overload limitation; ； wherein is the trajectory curvature, is the normal overload, V is the flight velocity, and g is the gravitational acceleration; Flight speed limitation; ； where V min is the minimum flight speed, V max is the maximum flight speed.
6. The low-altitude penetration route planning method based on the improved particle swarm algorithm according to claim 5, characterized in that, In S1.3, the cost function of the route planning environment model is as follows: Total distance cost function: ； wherein f dis is the total path cost, is the position of the i-th waypoint, is the position of the i+1-th waypoint; Threat cost function: ； ； where f threat is the threat cost, R threat is the threat radius, d threat is the threat distance, is the threat center coordinates.
7. The low-altitude penetration route planning method based on the improved particle swarm algorithm according to claim 6, characterized in that, In step S2, the optimal track point is found by using the improved particle swarm algorithm according to the route planning environment model, comprising: S2.1, determining a search space according to the environment map, setting the number of particle populations, the maximum number of iterations, the inertia weight factor and the learning factor; S2.2, randomly generating an initialized particle population in the search space, initializing the initial position and the initial speed of each particle; S2.3, taking the cost function as a fitness function, calculating the initial fitness function value of each particle, updating the initial individual optimal solution and the global optimal solution as the first generation individual historical optimal solution and the global optimal solution; S2.4, updating the position and the speed of each particle; S2.5, judging whether the particle in the current iteration number satisfies the constraint condition, if not, discarding the current iteration and returning to S2.3; S2.6, calculating the fitness function value of each particle in the current iteration number, comparing the fitness function value with the individual historical optimal value and the global optimal solution, and updating the particle individual optimal position and the particle group global optimal position; S2.7, judging whether the particle swarm algorithm reaches the maximum number of iterations, if yes, outputting the optimal solution as the optimal track point, if not, returning to S2.
3.
8. The low-altitude penetration route planning method based on the improved particle swarm algorithm according to claim 7, characterized in that, In S2.4, The position of the i-th particle in the t+1-th iteration is as follows: ； The speed of the i-th particle in the t+1-th iteration is as follows: ； wherein, , is the particle position, , is the particle velocity, is the shrinkage factor, w is the inertia weight factor, is the historical best solution, is the global best solution, c1, c2 are the learning factors, and r1, r2 are random numbers between (0, 1).
9. The low-altitude penetration route planning method based on the improved particle swarm algorithm according to claim 8, characterized in that, In step S3, the optimal trajectory is obtained by performing smoothing processing on the optimal track point, comprising: The optimal trajectory is obtained by performing interpolation smoothing processing on the optimal track point through a B-spline curve.
10. A low altitude penetration route planning system based on improved particle swarm optimization algorithm, the low altitude penetration route planning method based on improved particle swarm optimization algorithm according to any one of claims 1 to 9, characterized in that, The method comprises the following steps: A model construction module is configured to construct a route planning environment model; An optimal track point acquisition module is configured to find an optimal track point by using an improved particle swarm algorithm according to the route planning environment model; A smoothing processing module is configured to perform smoothing processing on the optimal track point to obtain an optimal trajectory.
11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that, The processor implements the low-altitude penetration flight path planning method based on the improved particle swarm algorithm as claimed in any one of claims 1 or 9 when executing the computer program.
12. A computer-readable storage medium, the computer-readable storage medium storing a computer program, characterized in that, The computer program can implement the low-altitude penetration flight path planning method based on the improved particle swarm algorithm as claimed in any one of claims 1 or 9 when executed by the processor.