Performance-Guaranteed Adaptive Fuzzy Wavelet Neural Fixed-Time Control for Unmanned Surface Vehicle Under Switching Event-Triggered Communication
Xiaona Song, Chenglin Wu, Shuai Song, Xiaohui Zhang, Inés Tejado
Abstract
This article investigates the performance-guaranteed adaptive fuzzy wavelet neural fixed-time control design with singularity-avoidance for the unmanned surface vehicle (USV) under switching event-triggered communication. First, by resorting to the convergence of the fixed-time performance function, the tracking error is driven into the anticipated steady-state interval with the specified evolving behavior. Moreover, the unknown dynamics of the controlled vehicle are modeled approximately by the fuzzy wavelet neural networks, while a compensation function is designed to overcome the composite perturbation comprising the external disturbances and estimation errors. In addition, a switching event-triggered mechanism-based adaptive fixed-time control design is proposed, which not only achieves non-periodic updating of the control signal but also effectively eliminates control singularity and computational complexity present in traditional recursive control frameworks. Stability analysis confirms the practical fixed-time stability of the closed-loop system. Finally, illustrative results are provided to validate the effectiveness and feasibility of the developed scheme.