Abstract—This paper is concerned the problem of H
∞ control for artificial neural networks with mixed time-varying delays which comprising different interval and distributed time-varying delays via hybrid feedback control. The interval and distributed time-varying delays are not necessary to be differentiable. The main purpose of this research is to estimate exponential stability of artificial neural network with H
∞ performance attenuation level
γ. The key features of the approach include the introduction of a new Lyapunov- Krasovskii functional with triple integral terms, the employment of a tighter bounding technique, some slack matrices and newly introduced convex combination condition in the calculation, improved delay-dependent sufficient conditions for the H
∞ control with exponential stability of the system are obtained in terms of linear matrix inequalities (LMIs). The results of this paper complement the previously known ones. Finally, a numerical example is presented to show the effectiveness of the proposed methods.
Index Terms—Artificial neural networks, exponential stability, H
∞ control, hybrid feedback control.
C. Chantawat and T. Botmart are with Khon Kaen University, Department of Mathematics, Khon Kaen 40002, Thailand (e-mail: charuwat_c@ kkumail.com, thongbo@kku.ac.th).
W. Weera is with University of Pha yao, Department of Mathematics, Phayao 56000, Thailand (e-mail: wajaree.we@up.ac.th).
[PDF]
Cite:C. Chantawat, T. Botmart, and W. Weera, "New Analysis on H∞Control for Exponential Stability of Artificial Neural Network with Mixed Time-Varying Delays via Hybrid Feedback Control," International Journal of Information and Electronics Engineering vol. 8, no. 3, pp. 23-29, 2018.