时变时滞神经网络地时滞相关鲁棒稳定性和耗散性分析.PDF

第32 卷 第6 期 控 制 与 决 策 Vol.32 No.6 2017 年 6 月 Control and Decision Jun. 2017 文章编号: 1001-0920(2017)06-1084-07 DOI: 10.13195/j.kzyjc.2016.0892 时变时滞神经网络的时滞相关鲁棒稳定性和耗散性分析 肖伸平, 练红海, 陈 刚, 冯 磊 (1. 湖南工业大学电气与信息工程学院，湖南株洲412007 ； 2. 电传动控制与智能装备湖南省重点实验室，湖南株洲412007) 摘 要: 研究时变时滞神经网络的鲁棒稳定性和耗散性问题. 充分利用积分项的时滞信息和激励函数条件构造 一个合适的增广LK 泛函; 利用自由矩阵积分不等式处理LK 泛函的导数, 得到一个低保守性的时滞相关稳定判 据; 将所获得的结论延伸至神经网络的耗散性分析, 并推导出一个确保神经网络严格 --耗散的充分条 件. 最后通过3 个数值算例验证了所提出方法的可行性和优越性. 关键词: 神经网络；稳定性；耗散性；自由矩阵积分不等式；时变时滞 中图分类号: TP273 文献标志码: A Delay-dependent robust stability and dissipativity analysis of neural networks with time-varying delays XIAO Shen-ping , LIAN Hong-hai, CHEN Gang, FENG Lei (1. School of Electrical and Information Engineering，Hu’nan University of Technology ，Zhuzhou 412007 ，China ； 2. Key Laboratory for Electric Drive Control and Intelligent Equipment of Hu’nan Province，Zhuzhou 412007 ，China) Abstract: The problems of robust delay-dependent stability and dissipativity for neural networks(NNs) with time-varying delay is investigated. A proper augmented Lyapunov-Krasovskii functional(LKF) is constructed, which fully utilizes the information of time-delay in integral term and the neuron activation function conditions. Then, by employing the free- matrix-based integral inequality to handle the derivative of the LKF, a less conservative delay-dependent stability criteria is obtained. The acquired conclusion is extended to the analysis of dissipativity for delayed NNs, and a suficient condition is derived to guarantee the NNs strictly --dissipative. The superiority and feasibility of presented approaches