Research On UAV Path Planning Method And Its Application In Oilfield Patrol

As a new technology,UAV inspection technology has been widely used in many fields,such as environmental protection,communication,electric power,meteorology and so on.UAV path planning is the key problem of UAV inspection.With the continuous improvement of oil field production and scale,the traditional manual inspection method is not enough to meet the needs of oilfield management.Therefore,it is of great significance to study the path planning method of oil field inspection UAV based on the characteristics of oil field.UAV path planning is to plan the flight path from the starting point to the target point,which meets the constraint conditions.It is one of the important contents of UAV mission planning.In this paper,the path planning method of UAV is studied under the practical background of oil field,the main contents of this paper are as follows:Firstly,the UAV path planning problem and environmental modeling are studied.Based on the flight environment and mission requirements of UAV,the path expression and constraint conditions of UAV are determined.According to the UAV flying at a constant height,the three-dimensional flight environment is abstracted into two-dimensional space,which is intercepted by a virtual plane.Oil wells are expressed as the characteristic points of the plane coordinate,and the obstacles are expressed as the plane polygon by means of geometric description.The longitude and latitude coordinates of the oil well are processed by means of Gauss transform,and the environmental model is established.Secondly,the UAV path planning algorithm is chosen and improved.Based on the comparison and analysis of Genetic algorithm,Ant Colony algorithm and Particle Swarm Optimization(PSO)algorithm,PSO algorithm is selected as the UAV path planning algorithm.Aiming to overcome the shortcomings of PSO algorithm,SFLA-DPSO algorithm is proposed then.In the early stage of the algorithm,the initial populations are grouped by the grouping strategy of hybrid leapfrog algorithm,sub optimal individuals are optimized by local deep search,and individual at all levels are extracted as the new populations,which ensure the search efficiency is improved.In the later stage of the algorithm,the three crossover operation is performed on the optimal individual,and the mutation operation based on the density is introduced.The sparse points are changed by a large probability and the particle diversity is enhanced.The performance of the improved algorithm is compared with other algorithms by datas of TSPLIB.Thirdly,the obstacle avoidance problem is studied.For known obstacles,an obstacle detection method based on computational geometry is designed,and the obstacle detection results are introduced into the evaluation function of path planning algorithm by the barrier factor,which guaranteed that the generated path meets the requirements of obstacle avoidance.The Artificial Potential Field method is used to plan the local obstacle avoidance path for emergent obstacles.Finally,taking Daqing oilfield patrol as an example,the path of UAV is designed.According to the inspection wells model,the initial optimal reference path is planned by the SFLA-DPSO algorithm and the obstacle avoidance method based on computational geometry.Then the path is smoothed,which meets the requirements of the shortest path,obstacle avoidance and traversal requirements.The Artificial Potential Field method is used to generate the local dynamic path,which can avoid emergency obstacle threat.The basic steps of path planning for UAV are given,and the path planning results of method of this paper are compared with those of other algorithms.