具有随机切换非线性的时滞神经网络的非脆弱状态估计

Non-fragile State Estimation for Delayed Neural Networks with Stochastic Switching Nonlinearities

探讨了带有随机切换非线性和混合时滞的不确定神经网络的非脆弱状态估计问题.首先,给出了所研究神经网络的数学模型;其次,基于有效信息设计非脆弱状态估计器,采用范数有界不确定性刻画了状态估计器增益矩阵的摄动现象;再次,基于Lyapunov稳定性定理给出了新的线性矩阵不等式描述的稳定性条件;最后,给出了仿真实验验证所提出的状态估计算法的可行性.

In this paper, the non-fragile state estimation problem is discussed for uncertain neural networks with stochastic switched nonlinear and mixed delays. Firstly, the mathematical model of the neural network studied is given. Secondly, the non-fragile state estimator is designed based on available information. The perturbation phenomenon of state estimator gain matrix is characterized by the norm bounded uncertainty. Thirdly, the stability condition in terms of the new linear matrix inequality description is given based on the Lyapunov stability theorem. Finally, the simulation experiment is given to illustrate the feasibility of the proposed state estimation algorithm.