Adaptive Neural Sliding-Mode Control for Fuzzy Singularly Perturbed Systems: Sojourn-Probability-Based Stochastic Communication Protocol.

Abstract

This article addresses an adaptive neural network (NN) sliding-mode control (SMC) strategy for fuzzy singularly perturbed systems against unrestricted deception attacks and stochastic communication protocol (SCP). Instead of relying on the traditional transition probability, a sojourn-probability-based SCP is efficiently established to characterize the stochastic nature more precisely. In response to unrestricted deception attacks, an NN-based technique is deployed to estimate and counteract their detrimental impacts on system performance. Moreover, the design of the sliding-mode controller integrates the singular perturbation parameter and fuzzy rules, addressing the challenge of imperfect premise matching. The proposed controller guarantees exponential ultimate boundedness in the mean square sense and ensures the reachability of the specified sliding surface for the closed-loop system. Finally, the efficacy of the proposed theoretical framework is validated through two illustrative examples, confirming its practical applicability and robustness.