具有加性时变时滞神经网络的稳定性分析  

Stability analysis of neural networks with additive time-varying delay components

作　　者：李蓉[1] 张海洋[2] 王延萌 吴涛[1] 熊良林[1] 

机构地区：[1]云南民族大学数学与计算机科学学院,云南昆明650500 [2]南京理工大学理学院,江苏南京210094 [3]南京航空航天大学理学院,江苏南京210016

出　　处：《云南民族大学学报（自然科学版）》2017年第3期216-222,共7页Journal of Yunnan Minzu University:Natural Sciences Edition

基　　金：国家自然科学基金(11601474;11461082);云南民族大学研究生创新基金(2016YJCXS08)

摘　　要：讨论了具有加性时变时滞的神经网络模型的稳定性,得到了新的稳定性判据.在构造包含三重积分项的新Lyapunov泛函的基础上,利用新的不等式,采用时滞分割方法,并结合其他分析技巧,得到了保守性较低的线性矩阵不等式稳定性条件.最后,通过2个数值实例,验证了方法的有效性和结果的优越性.In this paper, the stability of neural networks with additive time -varying delay components is discussed and some new stability criteria are obtained. On the basis of constructing a new Lyapunov functional with three integral terms, using new inequalities, delay- partitioning technique, combined with other analytical techniques, the stability conditions of the linear matrix inequalities with a lower conservatism are obtained. Finally, two numerical examples are given to verify the effectiveness of the proposed method and the superiority of the results.

关 键 词：加性时变时滞 神经网络 全局渐近稳定性 LYAPUNOV泛函 

分 类 号：O178[理学—数学]