BP神经网络PID控制器在无人机编队飞行中的应用  

Application of BP Neural Network PID Controller in UAV Formation Flight

作　　者：牧彬[1] 米征[1] 盛凯[1] 高利娃 

机构地区：[1]中国飞机强度研究所,陕西西安710065

出　　处：《测控技术》2017年第4期66-69,共4页Measurement & Control Technology

摘　　要：无人机编队飞行可以大幅提高作战效率,因而受到了越来越多的关注。从近距离编队出发,采用长机-僚机编队结构,设计一种基于BP神经网络参数整定的PID控制器,并以双机菱形编队为基础,对其进行仿真验证。仿真结果表明,该控制器能够实现双机近距离队形保持及重构,与常规PID控制器相比,省去PID参数整定时间,并且具有更快的响应速度、更小的超调量及更好的鲁棒性。The formation flight of multi-unmanned aerial vehicles（UAVs） can greatly improve the effieienty of battle mission,thus more and more attention has been received.Starting from the short-range formation,based on the leader-follower structure,a PID controller adjusted by neural networks is designed,the controller based on double formation is verified by simulation.Simulation results show that this controller can achieve the goal of formation keeping and reconfiguration.Compared with the traditional PID controller,formation can faster recover with smaller overshoot,and has better robustness.

关 键 词：无人机编队 编队保持与变换 BP神经网络 

分 类 号：V297[航空宇航科学技术]