Event-driven NN adaptive fixed-time control for nonlinear systems with guaranteed performance

• Published in: Journal of the Franklin Institute Vol. 359; no. 9; pp. 4138 - 4159
• Main Authors: Song, Xiaona, Sun, Peng, Song, Shuai, Stojanovic, Vladimir
• Format: Journal Article
• Language: English
• Published: Elmsford Elsevier Ltd 01.06.2022; Elsevier Science Ltd
• Subjects: Adaptive control; Algorithms; Closed loop systems; Control systems design; Control theory; Controllers; Feedback control; Neural networks; Nonlinear control; Nonlinear systems; Radial basis function; Simulation; Tracking control; Tracking errors
• ISSN: 0016-0032; 1879-2693; 0016-0032
• DOI: 10.1016/j.jfranklin.2022.04.003

This article investigates the adaptive neural network fixed-time tracking control issue for a class of strict-feedback nonlinear systems with prescribed performance demands, in which the radial basis function neural networks (RBFNNs) are utilized to approximate the unknown items. First, an modified fractional-order command filtered backstepping (FOCFB) control technique is incorporated to address the issue of the iterative derivation and remove the impact of filtering errors, where a fractional-order filter is adopted to improve the filter performance. Furthermore, an event-driven-based fixed-time adaptive controller is constructed to reduce the communication burden while excluding the Zeno-behavior. Stability results prove that the designed controller not only guarantees all the signals of the closed-loop system (CLS) are practically fixed-time bounded, but also the tracking error can be regulated to the predefined boundary. Finally, the feasibility and superiority of the proposed control algorithm are verified by two simulation examples.