In this paper, we propose a deep unfolding-based framework for the outputfeedback control of systems with input saturation . The data-driven framework we propose in this paper is based on a deep-learning technique called Neural Ordinary Differential Equations . The proposed framework can significantly outperform a conventional design methodology based on linear matrix inequalities. Our numerical simulation shows that the proposedframework can significantly outperform a traditional design methodology by using a linear matrix algorithm based on linear matrix algorithms based instructions and testing by the existing theoretical results already established in the literature, thereby avoiding the computational challenge in the conventional design methodologies as well as theoretically guaranteeing the system’s performance of the system .

Author(s) : Koki Kobayashi, Masaki Ogura, Taisuke Kobayashi, Kenji Sugimoto

Links : PDF - Abstract

Code :

https://github.com/narock/machine_learning


Coursera

Keywords : based - linear - design - deep - framework -

Leave a Reply

Your email address will not be published. Required fields are marked *