An Improved Data-Driven Iterative Learning Secure Control for Intelligent Marine Vehicles With DoS Attacks
Huiying Liu, Li‐Ying Hao
Abstract
In this article, the problem of trajectory tracking for intelligent marine vehicles (IMVs) under disturbances, actuator faults and denial-of-service (DoS) attacks is researched. In order to improve the computational efficiency, we propose an improved data-driven iterative learning strategy within the iterative domain. Compared to previous results, our proposed learning strategy has demonstrated improved performance in terms of trajectory tracking through the partial form dynamic linearization technique, significantly increasing the speed of iterations. This research recognizes the effect of DoS attacks on the iterative learning data-driven model for IMVs. The proposed compensation mechanism mitigates the effects of DoS attacks by utilizing the data from previous iterations. Additionally, an improved data-driven iterative learning secure controller is designed to ensure convergence of trajectory tracking error. Finally, we demonstrate the efficacy and superiority of the proposed control scheme in the simulations.