In this paper, we consider cyber physical systems security control problems under DoS attacks via the tracking-removed autoencoder. The DoS attack model is described by the switch signal, which occurs in the controller-actuator transmission channel. Then, the linear matrix inequality theory is used to solve the average dwell time of the attack mode that the system can tolerate. Moreover, when the attack dwell time exceeds the tolerance range, a tracking-removed autoencoder is chosen to train to get the control signal. And it can be proved that the closed-loop system with the controller based on the tracking-removed autoencoder is asymptotically stable with H∞ performance index. Finally, the correctness and advancement of the theory are proved by an example.
No takes yet. Share an insight, caveat, or question.
Yu et al. (2024) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: