Chebyshev Neural Network Observer Based RBF Neural Network Terminal Sliding Mode Controller for a Class of Nonlinear System
作者单位：Department of AutomationShanghai Jiao Tong University School of Mechatronic Engineering and AutomationShanghai University
会议名称：《第30届中国控制与决策会议》
会议日期：2018年
学科分类：08[工学] 0835[工学-软件工程] 0802[工学-机械工程] 080201[工学-机械制造及其自动化]
基 金：partially supported by the National Science Foundation of China under Grants 61473183 and U1509211
关 键 词：MLP Neural Network RBF Neural Network Terminal Sliding Mode Sliding Surface State Estimation Observer
摘 要：This paper focuses on an observer-based controller for a class of nonlinear *** order to solve the problem of unknown dynamic in practical systems,two different Neural Networks（NNs） for observer and controller parts are *** the observer part,a Multi-Layer Perceptron（MLP） neural network based on error back propagation algorithm is applied to update the weights of neural network that will be used to estimate the system *** the controller part,Radial Basis Function Neural Network（RBFNN） with terminal sliding mode controller,based on a new sliding surface,is combined to achieve a finite time stability and fast convergence *** update law in the controller part is related to the proposed sliding *** stability of the closed loop system is analyzed by Lyapunov stability *** simulation,the proposed technique is applied to a chaotic system to obtain the effectiveness of the proposed approach.