Full Information Control for Switched Neural Networks Subject to Fault and Disturbance

• Published in: IEEE transaction on neural networks and learning systems Vol. 34; no. 2; pp. 703 - 714
• Main Authors: Sun, Jiayue, Zhang, Huaguang, Xu, Shun, Liu, Yang
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.02.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Availability; Biological neural networks; Control systems; Disturbance; Dwell time; fault; Fault tolerance; full information control; Fuzzy control; Fuzzy neural networks; Liapunov functions; Linear matrix inequalities; Mathematical analysis; Neural networks; Stability analysis; State feedback; switched; Switches; Tracking errors
• ISSN: 2162-237X; 2162-2388; 2162-2388
• DOI: 10.1109/TNNLS.2021.3100143

The article investigates full information control problem for switched neural networks subject to fault and disturbance. First, the main objective is realizing interval stability and zero tracking error under condition that neither of the neuron states' vectors including the plant and reference models is available. Second, the desired full information controller and neural networks' observer are designed to ensure observer-based dynamic error system mean-square exponentially stable with sufficient condition of strict weight <inline-formula> <tex-math notation="LaTeX">\mathcal {H}_{\infty } /\mathcal {H}_{-} </tex-math></inline-formula> performance levels. Finally, we concentrate on stability analyses and fault tolerance for switched neural networks with fault accompanied by disturbance through linear matrix inequalities (LMIs), Lyapunov function, and average dwell time, discussing it according to different values of fault. Finally, simulation examples are listed to account for the availability and effectiveness of the research methodology.