Decentralized Guaranteed Cost Control for Discrete-Time Uncertain Large-Scale Systems Using Neural Networks
| Authors: | Mukaidani Hiroaki, Hiroshima University, Japan
Ishii Yasuhisa, Hiroshima University, Japan
Tsuji Toshio, Hiroshima University, Japan |
|---|
| Topic: | 2.5 Robust Control |
|---|
| Session: | Robust Controller Synthesis I |
|---|
| Keywords: | Large-scale systems, Discrete-time systems, Uncertain linear systems, Decentralized control, Robust control, Neural networks |
|---|
Abstract
This paper investigates an application of neural networks to the guaranteed cost control problem of decentralized robust control for a class of discrete-time uncertain large-scale systems. Based on the Linear Matrix Inequality (LMI) design approach, a class of decentralized local state feedback controllers with additive gain perturbations is established. The novel contribution of this paper is that to reduce the large cost caused by the LMI conditions Neural Networks (NNs) are substituted for the additive gain perturbations. Although the NNs are included in the uncertain large-scale systems, the closed-loop system is asymptotically stable. Furthermore, it is shown that the closed-loop cost function is not more than the specified upper bound for all admissible uncertainties.
