带加性时变时滞的不确定神经网络鲁棒散耗性研究

Research on robust dissipation of uncertain neural networks with additive time-varying delays

针对加性时变时滞不确定神经网络的时滞相关鲁棒耗散性问题,提出了一种更一般化的激活函数。与以往研究不同,充分考虑了关于神经元激活函数和加性时变时滞的充分信息,通过使用一些新的积分项构造合适的Lyapunov-Krasovskii泛函(LKF),并利用新生成的单积分不等式来计算其导数,包括延森不等式和维特林积分不等式的特殊情形。利用线性矩阵不等式(LMI)技术建立了一个新的时滞相关的不守恒全局渐近稳定性和耗散准则。最终通过计算和数值仿真验证了所提理论的有效性。

Aim at the problem of the delay dependent robust dissipative problem of uncertain neural networks with additive time-varying delays,this paper studied a generalized activation functions.Different from previous studies,it considered some sufficient information on neuron activation function and additive time-varying delays.It constructed a suitable LKF with some new integral terms,and estimated their derivative by using newly developed single integral inequality that included Jensen’s inequality and Wirtinger-based integral inequality as a special case.It established a new delay-dependent less conservative global asymptotic stability and dissipative criteria in the form of linear matrix inequalities(LMI)technique.Finally,this paper verified the validity of the proposed theory by calculation and numerical simulation.