Adaptive integral sliding-mode control strategy of data-driven cyber-physical systems against a class of actuator attacks

This study is concerned with the reliable and optimal control problems of data-driven cyber-physical systems (CPSs) against a class of actuator attacks. Consider an unknown continuous-time linear physical system with the external disturbance, and it is assumed that control input signals transmitted via network layers are vulnerable to cyber attacks. By introducing a new integral sliding-mode function and utilising the available data acquired by an off-policy reinforcement learning algorithm, a novel data-based adaptive integral sliding-mode control strategy is presented. Different from the existing control policies, the novel one uses a data-driven sliding-mode compensator to eliminate the effect of the actuator attacks such that the stability and a nearly optimal performance of the CPSs can be guaranteed. Finally, the effectiveness of the proposed control strategy is verified by a numerical example.