stability conditions for fuzzy neural networks模糊神经网络的稳定性条件.pdfVIP

Hindawi Publishing Corporation Advances in Fuzzy Systems Volume 2012, Article ID 281821, 4 pages doi:10.1155/2012/281821 Research Article H∞ Stability Conditions for Fuzzy Neural Networks Choon Ki Ahn Department of Automotive Engineering, Seoul National University of Science Technology, 172 Gongneung 2-dong, Nowon-gu, Seoul 139-743, Republic of Korea Correspondence should be addressed to Choon Ki Ahn, hironaka@snut.ac.kr Received 29 August 2011; Accepted 1 December 2011 Academic Editor: Kemal Kilic Copyright © 2012 Choon Ki Ahn. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. This paper presents a novel approach to assess the stability of fuzzy neural networks. First, we propose a new condition for the H∞ stability of fuzzy neural networks. Second, a new H∞ stability condition based on linear matrix inequality (LMI) is presented for fuzzy neural networks. These conditions also ensure asymptotic stability without external input. 1. Introduction the normalized weight of each IF-THEN rule, and it satisfies h (ω) ≥ 0, r h (ω) = 1. The T-S fuzzy models have i i=1 i In this paper, we consider the following Takagi-Sugeno (T-S) been of great importance in academic research and industrial fuzzy Hopfield neural network: applications. Essentially, these models are based on the use of