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

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.