Design of Fixed-Time Neural Controller for Uncertain Nonstrict-Feedback Systems with Smooth Switching Functions

作     者：YANG Jinzi LI Yuanxin TONG Shaocheng YANG Jinzi;LI Yuanxin;TONG Shaocheng

作者机构：State Key Laboratory of Synthetical Automation for Process IndustriesNortheastern UniversityShenyang110819China College of ScienceLiaoning University of TechnologyJinzhou121001China 

出 版 物：《Journal of Systems Science & Complexity》 (系统科学与复杂性学报（英文版）)

年 卷 期：2023年第36卷第6期

页      面：2344-2363页

核心收录：

学科分类：08[工学] 0802[工学-机械工程] 0701[理学-数学] 080201[工学-机械制造及其自动化] 

基　　金：supported in part by the National Science of China under Grant Nos.62373176,61973146 in part by the Applied Basic Research Program in Liaoning Province under Grant No.2022JH2/101300276 in part by the Key Project of the Educational Department of Liaoning Province under Grant No.JYTZD2023084 in part by Taishan Scholar Project of Shandong Province of China under Grant No.tsqn201909097。 

主　　题：Backstepping technique fixed-time control neural networks switching function 

摘      要：The tracking problem of uncertain nonstrict-feedback nonlinear systems(UNFNS)is examined to develop a novel adaptive neural control scheme to ensure fixed-time convergence.In particular,the challenge associated with the unknown nonlinear function can be overcome through neural network(NN)based estimation.Therefore,an NN-based adaptive fixed-time control scheme is established with only one parameter,using the property of the basis function vector to address the algebraic loop problem.Furthermore,the singularity problem can be solved by incorporating a smooth switching function.A rigorous theoretical analysis is performed to demonstrate that the output signal can track the reference signal within a fixed time and that the signals in the control systems are bounded.Finally,numerical simulations are performed to validate the feasibility of the proposed methodology.