Robust Learning and Control of Time-Delay Nonlinear Systems With Deep Recurrent Koopman Operators
Minghao Han, Zhaojian Li, Xiang Yin, Xunyuan Yin
Abstract
In this work, we consider the problem of Koopman modeling and data-driven predictive control for a class of uncertain nonlinear systems subject to time delays. A robust deep learning-based approach–deep recurrent Koopman operator is proposed. Without requiring the knowledge of system uncertainties or information on the time delays, the proposed deep recurrent Koopman operator method is able to learn the dynamics of the nonlinear systems autonomously. A robust predictive control framework is established based on the deep Koopman operator. Conditions on the stability of the closed-loop system are presented. The proposed approach is applied to a chemical process example. The results confirm the superiority of the proposed framework as compared to baselines.