Regional stability conditions for recurrent neural network-based control systems

2025/01/24 by Alessio La Bella, Marcello Farina, William D’Amico +1 · 1 citation
Engineering · Computer Science · #Adaptive Control of Nonlinear Systems #Neural Networks and Applications #Neural Networks Stability and Synchronization

paper · doi:10.1016/j.automatica.2025.112127

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 H 2 norm minimization properties is defined. The theoretical results are corroborated by numerical simulations, showing the advantages and limitations of the methods presented herein.

Cited by

• Gated recurrent units: From local to global stability properties

Related

• Regional stability conditions for recurrent neural network-based control systems
• An incremental input-to-state stability condition for a generic class of recurrent neural networks
• Recurrent neural network-based robust control systems with closed-loop regional incremental ISS and application to MPC design
• Improved Sum-of-Squares Stability Verification of Neural-Network-Based Controllers
• Stability analysis of discrete-time recurrent neural networks