Intelligent Control for Switched Systems with Time Delay via Deep Reinforcement Learning

The problem of intelligent control for switched systems with time delay is investigated in this paper. Firstly, the state feedback controller is proposed for switched systems with time delay by robust control theory and non-fragile control. Multiple Lyapunov-Krasovskii functional method and average...

Full description

Saved in:
Bibliographic Details
Main Authors: Song, Ruijia, Wang, Bolan, Cheng, Haoyu, Huang, Hanqiao, Yan, Jie
Format: Conference Proceeding
Language:English
Subjects:
Deep Reinforcement Learning
Delay effects
Non-fragile Control
Reinforcement learning
Robust control
Stability analysis
Sufficient conditions
Switched Delay Systems
Switched systems
Switches
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The problem of intelligent control for switched systems with time delay is investigated in this paper. Firstly, the state feedback controller is proposed for switched systems with time delay by robust control theory and non-fragile control. Multiple Lyapunov-Krasovskii functional method and average dwell time (ADT) approach are combined to analyze the stability of closed-loop system. Sufficient conditions to guarantee the stability and prescribed performance are given in the form of linear matrix inequalities (LMIs). In order to achieve better performance, the deep deterministic policy gradient (DDPG) approach is proposed to optimize the controller parameters in the neighborhood of parameters obtained by robust control. Numerical example is given in the end to illustrate the effectiveness and superiority of proposed method.
ISSN:1948-9447
DOI:10.1109/CCDC52312.2021.9602486