Regional stability conditions for recurrent neural network-based control systems

2024/09/24 by Alessio La Bella, Marcello Farina, La Bella, Alessio +5 · 4 citations
Computer Science · Engineering · #Adaptive Control of Nonlinear Systems #FOS: Electrical engineering #Neural Networks and Applications #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2409.15792

openalex publication_date 2024/09/24 · openalex created_date 2024/10/26 · openalex updated_date 2026/07/28

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.

Cited by

• Development of a velocity form for a class of RNNs, with application to offset-free nonlinear MPC design
• Learning stabilising policies for constrained nonlinear systems
• Recurrent neural network-based robust control systems with closed-loop regional incremental ISS and application to MPC design
• Aperiodic-sampled neural network controllers with closed-loop stability verifications (extended version)

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