Regional stability conditions for recurrent neural network-based control systems

TL;DR

This paper introduces new stability analysis conditions for recurrent neural network control systems using linear matrix inequalities, enabling improved control design and optimization.

Contribution

It presents novel global and regional stability criteria based on LMIs, applicable to control design and H2 norm minimization for RNNs.

Findings

The proposed conditions are effective in stability analysis.

Numerical simulations validate the theoretical results.

The methods show advantages and limitations in practical scenarios.

Abstract

In this paper we propose novel global and regional stability analysis conditions based on linear matrix inequalities for a general class of recurrent neural networks. These conditions can be also used for state-feedback control design and a suitable optimization problem enforcing H2 norm minimization properties is defined. The theoretical results are corroborated by numerical simulations, showing the advantages and limitations of the methods presented herein.