A novel intelligent learning control scheme for discrete-time nonlinear uncertain systems in multiple environments
Date of Original Version
In this paper, we propose a novel intelligent control scheme for a class of discrete-time nonlinear uncertain systems operating under multiple environments/control situations. First, based on the deterministic learning theory, artificial neural networks (NNs) are employed to accurately learn/identify the uncertain system dynamics under each individual environment. The learned knowledge is then utilized to: (i) achieve improved control performance by developing a family of experience-based controllers (EBCs), each of which is tailored to an individual environment; and (ii) determine real-time activation of the EBCs by developing a pattern recognition mechanism for online identifying the active control situation. In addition, a robust quasi-sliding mode controller is further designed and embedded in the overall control scheme to guarantee system stability during the transition process among multiple environments. The novelty of the proposed control scheme lies in its intelligent capabilities of knowledge acquisition and re-utilization in real-time control, enabling self-adaption to uncertain changing control environments. A simulation example is included to verify the effectiveness of the proposed results.
ASME 2020 Dynamic Systems and Control Conference, DSCC 2020
Zhang, Jingting, Chengzhi Yuan, and Paolo Stegagno. "A novel intelligent learning control scheme for discrete-time nonlinear uncertain systems in multiple environments." ASME 2020 Dynamic Systems and Control Conference, DSCC 2020 1, (2020). doi:10.1115/DSCC2020-3112.