水下机器人自适应输出反馈控制设计

来源期刊:中南大学学报(自然科学版)2011年第z1期

论文作者:张利军 齐雪 庞永杰 贾鹤鸣

文章页码:464 - 468

关键词:水下机器人;自适应控制;输出反馈;动态递归模糊神经网络

Key words:autonomous underwater vehicle; adaptive control; output feedback; dynamic recurrent fuzzy neural network

摘    要:研究水下机器人轨迹跟踪控制问题。在充分考虑不确定水动力系数的结构特征的基础上,提出基于动态递归模糊神经网络的自适应输出反馈控制策略。控制器由3部分组成:基于动态补偿器的输出反馈控制项、神经网络自适应控制项和鲁棒控制项。神经网络所需的自适应学习信号由线性观测器提供。利用Lyapunov稳定理论证明控制系统的稳定性。最后将所设计的控制方法应用于球形水下机器人ODIN,对其纵向、横向和艏向运动轨迹的跟踪问题进行了仿真实验,实验结果验证了控制方法的有效性。

Abstract: The tracking control problem for autonomous underwater vehicles (AUV) was addressed. The structure of uncertain hydrodynamic coefficients was deeply analyzed, and an adaptive output feedback controller based on dynamic recurrent fuzzy neural network (DRFNN) was proposed. The controller was composed of three parts, i.e. the output feedback control based on dynamic compensator, neural network and robust control item. An observer was designed to provide the adaptive learning signal for neural network. The stability of the controller by Lyapunov theory was analysed. The method provided was used for an Omni-Direction Intelligent Navigator (ODIN). Validity of the theory was proved by simulation of the trajectory tracking of the surge, sway and heading angle.

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号