School of Electronics and Information Engineering, Soochow University, Suzhou, PR China.
Neural Netw. 2010 Dec;23(10):1202-7. doi: 10.1016/j.neunet.2010.07.001. Epub 2010 Jul 27.
This paper is concerned with the state estimation problem for a class of static neural networks with time-varying delay. Here the time derivative of the time-varying delay is no longer required to be smaller than one. A delay partition approach is proposed to derive a delay-dependent condition under which the resulting error system is globally asymptotically stable. The design of a desired state estimator for such kinds of delayed neural networks can be accomplished by means of solving a linear matrix inequality. A simulation example is finally given to show the application of the developed approach.
本文研究了一类时变时滞静态神经网络的状态估计问题。这里，时变时滞的时间导数不再要求小于 1。提出了一种延迟分区方法，得到了一个时滞相关的条件，使得所得到的误差系统全局渐近稳定。通过求解线性矩阵不等式，可以完成此类时滞神经网络的期望状态估计器的设计。最后，给出了一个仿真示例，以展示所提出方法的应用。
