Intelligent Finite-Time Self-Triggered Control for Fuzzy UMV Systems With Hybrid Attacks
针对网络环境下遭受混合攻击的非线性无人艇系统，提出一种基于Q学习的智能自触发控制策略，在节省通信计算资源的同时保证系统有限时间有界性。
This work studies the finite-time self-triggered control of networked nonlinear unmanned marine vehicle (UMV) systems with hybrid attacks. A Takagi–Sugeno (T–S) fuzzy model is constructed to characterize the nonlinear UMV systems. To save limited communication and computing resources, an intelligent self-triggered mechanism is proposed, in which the threshold of self-triggered condition is adjusted intelligently by the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Q</i>-learning algorithm. Only the current states information and the last samples are adopted to calculate the interexecution interval for the next triggered instant, and then the controller signal is updated. In light of denial-of-service attacks and deception attacks under networked environment, two Bernoulli random variables are applied to describe the random occurrence of hybrid attacks. By using the Lyapunov function, sufficient conditions for finite-time boundedness of the closed-loop UMV systems are obtained. In addition, a collaborative design method for triggered parameter and controller gain is proposed. Finally, the benchmark UMV systems are simulated to demonstrate the effectiveness of the proposed strategy.