基于模糊神经网络的无人动力伞控制  

FUZZY NEURAL NETWORK CONTROL FOR UNMANNED POWERED PARAFOIL

作　　者：周红新[1] 陈自力[1] 李建[1] 

机构地区：[1]军械工程学院光学与电子工程系,石家庄050003

出　　处：《动力学与控制学报》2012年第2期182-185,共4页Journal of Dynamics and Control

基　　金：十一.五装备预先研究项目<无人驾驶软翼飞行器控制技术研究>(9140A25010208JB3401)~~

摘　　要：针对无人动力伞在执行任务时常常在低空、城市上空等复杂气流环境飞行,无人动力伞的响应特性受到飞行速度、航向角和各种风的综合影响,具有的非线性和不确定性.导致事先设计的控制规则不再适合,对此基于PID的控制算法难以达到满意的控制效果.本文提出了一种模糊神经网络控制无人动力伞航向控制策略,利用RBF神经网络所特有的局部逼近能力,对模糊控制规则进行在线推理并获得连续输出,采用GA算法对神经网络参数进行调整来实现对模糊控制器规则库的优化和模糊规则的自动生成.使控制器能够进一步适应无人动力伞实时控制中的时变性和不确定性,保持良好的控制性能;仿真表明算法是可行的.In terms of Unmanned Powered Parafoil Aircraft （UPPA） always flight in the low level sky and on top of the city＇ s hight rise. It often gets hight frequency disturb by all kinds of wind. It＇ s velocity and course angle or wind all affect the response characteristic of UPPA gesture. Then it will induce controlled rules be unsuitable with switch parameters. The PID algorithms can not reach satisfactory controlled effect. A fuzzy controller for UPPA gesture based on RBF networks and genetic algorithms is designed. A new method is also proposed for the self- tuning of scaling factors and genetic algorithm is employed to optimize the parameters used in tuning process in or- der to keep good controlling performance in case of time varying and uncertainties. Finally, with the nonlinear UPPA model of a mariner level vessel, simulation tests are carried out and results are satisfactory.

关 键 词：无人动力伞 模糊控制 神经网络 

分 类 号：O231[理学—运筹学与控制论]