期刊
NEURAL NETWORKS
卷 95, 期 -, 页码 134-142出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.neunet.2017.08.005
关键词
Adaptive control; Backstepping; Learning control; Mismatched uncertainty; Neural network; Parameter convergence
资金
- National Natural Science Foundation of China [61703295, 61503158]
- Defense Innovative Research Programme, MINDEF of Singapore [MINDEF-NUSDIRP/2012/02]
In existing neural network (NN) learning control methods, the trajectory of NN inputs must be recurrent to satisfy a stringent condition termed persistent excitation (PE) so that NN parameter convergence is obtainable. This paper focuses on command-filtered backstepping adaptive control for a class of strict-feedback nonlinear systems with functional uncertainties, where an NN composite learning technique is proposed to guarantee convergence of NN weights to their ideal values without the PE condition. In the NN composite learning, spatially localized NN approximation is employed to handle functional uncertainties, online historical data together with instantaneous data are exploited to generate prediction errors, and both tracking errors and prediction errors are employed to update NN weights. The influence of NN approximation errors on the control performance is also clearly shown. The distinctive feature of the proposed NN composite learning is that NN parameter convergence is guaranteed without the requirement of the trajectory of NN inputs being recurrent. Illustrative results have verified effectiveness and superiority of the proposed method compared with existing NN learning control methods. (C) 2017 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据