The Application And Research Of UAV Mission Planning Algorithm

UAV mission planning is to plan a series of missions such as mission scheduling,allocation of target order,and the establishment of flight path for the UAVs that perform the missions.As the demand for energy collection increases year by year,the number and scope of newly developed oil wells are increasing,and the ability of manual inspection has been unable to meet the needs of oil well inspection.Therefore,it is of great significance to study the decision-making of UAV inspection control in the planning of oil well inspection missions,so as to effectively solve the problem of inspection target allocation and UAV path planning.The UAV mission planning algorithm is the core of the UAV mission system and is used to solve the problem of reasonable target allocation and flight path planning mission model between UAVs.The Particle Swarm Optimization Algorithm is a representative algorithm.It is widely used in UAV mission planning research applications because of its simple operation and excellent optimization performance.However,due to the different requirements of the mission and the different focus of the mission,the standard particle swarm algorithm has inevitable shortcomings.Therefore,the reasonable improvement of the algorithm can not only meet the actual requirements and objectives of the UAV mission,but also improve the efficiency and success rate of the UAV mission planning.This paper takes UAV mission planning analysis design and application as an example,and studies the improvement of standard Particle Swarm Optimization Algorithm and its application in oil well inspection.The main contents are as follows:First of all,the composition of the constraints and the principle of constructing the model in the target assignment mission of the UAV are studied.Combined with the mission constraints and the constraints of the UAV,the previous global UAV target assignment mission model is determined.Particle swarm optimization is selected as the basic algorithm of mission planning,and it is improved according to the requirements of different periods of missions.In the global mission assignment in the early stage of the mission,quantum behavior is introduced based on the particle swarm algorithm to expand the search range and improve the global search performance of the algorithm.Secondly,based on the processing method of inertia weight of Particle Swarm Optimization Algorithm,a linear differential decrement strategy is introduced into the shrinkage-expansion coefficient of Quantum Particle Swarm Optimization Algorithm to jump out the local optimal value and improve the convergence speed.Then,the Gaussian learning strategy is introduced to improve the accuracy of the results.Finally,the improved algorithm is tested by multimodal function,compared with other algorithms,and simulated by examples.Secondly,the mission constraints and model construction of UAV path planning are studied,and the local UAV path planning mission model in the later stage is determined by combining the relevant constraints.Based on the idea of complementary advantages,the improved algorithm in the early stage of the mission and the search algorithm of the BeetleAntennae Search Algorithm are combined and improved.In the early stage of the algorithm,the improved Particle Swarm Optimization Algorithm is used to search the optimal value globally.Then,in the later stage of the algorithm,the Beetle Antennae Search Algorithm is used to carry out further accurate search near the optimal value.Finally,the improved algorithm is tested by multimodal function,compared with other algorithms,and simulated by examples.Eventually,the application of the improved algorithm in oil field patrol is studied.According to the idea of hierarchical progressive planning,the research and analysis of the overall steps of the UAV oil well inspection mission planning.Aiming at the global distribution mission model in the early stage of oil well inspection,the Gaussian linear differential decreasing Quantum Particle Swarm Optimization Algorithm is used to obtain the initial distribution set,so that the distribution result can satisfy the maximum return and meet the full allocation requirement in a short time.Aiming at the later local three-dimensional path planning model,the Gaussian Beetle Antennae Quantum Particle Swarm Optimization Algorithm is used to determine the shortest path to complete the specified allocation area,so that the generated path satisfies the requirements of the distribution area traversal and the shortest flight path.According to the characteristics of UAV in actual flight,the initial reference path is smoothed to make the processed path meet the requirements of flight feasibility.Through the analysis of the experimental results,the effectiveness of the improved mission planning algorithm in the inspection of the UAV oil wells is verified.