New delay‐dependent H∞ state estimator for static neural networks with bounded and unbounded time delays
An H∞ estimation issue for static neural networks (SNNs) is discussed by the research, and the SNN model is improved from the following two aspects: (1) The SNNs contains both bounded and unbounded delays. (2) The nonlinear activation function is bounded and belongs to an interval. Through the const...
Gespeichert in:
Veröffentlicht in: | Asian journal of control 2022-05, Vol.24 (3), p.1378-1390 |
---|---|
Hauptverfasser: | , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | An H∞ estimation issue for static neural networks (SNNs) is discussed by the research, and the SNN model is improved from the following two aspects: (1) The SNNs contains both bounded and unbounded delays. (2) The nonlinear activation function is bounded and belongs to an interval. Through the construction of the novel Lyapunov–Krasovskii functional (LKF), the state estimator is established. It is also pointed that a gain matrix is acquired by the linear matrix inequality (LMI). Numerical experiments indicate that the method put forward in this study is valid. In addition, the obtained results are characterized by effectiveness and correctness. |
---|---|
ISSN: | 1561-8625 1934-6093 |
DOI: | 10.1002/asjc.2724 |