一种基于粒子群算法的小型无人直升机自适应控制  

A small-scale unmanned helicopter adaptive control method based on particle swarm algorithm

作　　者：周健[1] 王敏[1] 洪良[1] ZHOU Jian;WANG Min;HONG Liang(School of Electronics and Information,Xi’an Polytechnic University,Xi’an 710048,China)

机构地区：[1]西安工程大学电子信息学院,陕西西安710048

出　　处：《现代电子技术》2018年第18期117-121,共5页Modern Electronics Technique

基　　金：陕西省教育厅自然科学基金(17JK0345);西安工程大学博士科研启动基金(BS1415);陕西省自然科学基础研究计划面上项目(2018JM6089)~~

摘　　要：针对小型无人直升机飞行时模型的非线性和参数不确定的特点,提出一种自适应控制方法。小型无人直升机模型不确定部分由小脑模型关节控制器(CMAC)神经网络在线补偿,控制律及神经网络参数自适应律由反步法回馈递推得到,并且利用粒子群算法优化控制器固定参数来改善系统动态性能。仿真结果表明,在较大的模型气动参数不确定的情况下,所设计的控制律仍能理想地跟踪飞行指令,同时具有快速的收敛性和良好的鲁棒性。In allusion to the characteristics of non-linearity and parameter uncertainty of the small-scale unmanned helicop-ter model during its flight,an adaptive control method is proposed.The uncertainty part of the small-scale unmanned helicopter model is compensated online by the cerebellar model articulation controller(CMAC)neural network.The control law and the adaptive law of the neural network parameter are obtained by means of recursion and feedback of the backstepping method.The particle swarm algorithm is used to optimize fixed parameters of the controller,so as to improve dynamic performance of the sys-tem.The simulation results show that the designed control law can still ideally track flight instructions,and has rapid conver-gence performance and good robustness when big uncertainties exist in pneumatic parameters of the model.

关 键 词：小型无人直升机 自适应控制 反步法 小脑模型关节控制器 在线补偿 粒子群算法 

分 类 号：TN876-34[电子电信—信息与通信工程] TP273[自动化与计算机技术—检测技术与自动化装置]