کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
406688 678105 2014 10 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Less conservative stability criteria for neural networks with discrete and distributed delays using a delay-partitioning approach
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر هوش مصنوعی
پیش نمایش صفحه اول مقاله
Less conservative stability criteria for neural networks with discrete and distributed delays using a delay-partitioning approach
چکیده انگلیسی

This paper is focused on the stability analysis of neural networks (NNs) with discrete and distributed delays. The novelty of this paper lies in the consideration of a new integral inequality proved to be less conservative than the celebrated Jensen׳s inequality and takes fully the relationship between the terms in the Leibniz–Newton formula within the framework of linear matrix inequalities (LMIs) into account. Based on this new integral inequality approach (IIA), an appropriate Lyapunov–Krasovskii functional is constructed and showed to have a great potential efficience in practice. Besides, by employing a delay decomposition approach which gives enough thought to information of the delayed plant states, improved delay-dependent stability criteria in terms of linear matrix inequalities (LMIs) are derived. Four numerical examples are given to demonstrate the effectiveness and the advantage of the proposed method.

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Neurocomputing - Volume 140, 22 September 2014, Pages 273–282
نویسندگان
, , , , ,