时变时滞神经网络系统的时滞依赖的鲁棒稳定性准则

基于Lyapunov稳定性理论和线性矩阵不等式技术,针对一类带有范数有界不确定性的时变时滞神经网络系统,给出时滞依赖的鲁棒稳定性准则.系统稳定的充分条件是在激励函数满足一类更为通用的条件下得到的,即激励函数不必是单调可微的,并且消除对时变时滞导数的限制.所给的准则可用Matlab中的线性矩阵不等式控制工具箱进行验证.仿真结果进一步证明结论的有效性.

Delay-dependent Robust Stability Criterion of Neural Networks with Time-varying Delays

Based on Lyapunov stability theory and linear matrix inequality, delay- dependent robust stability is derived for a class of neural networks with time - varying delays and norm - bounded uncertainties. The result is obtained under mild conditions, assuming neither differentiability nor monotonicity for activation function. And the restriction of the derivative of the time - varying delay is removed. The proposed stability criterion can be checked by the LMI Control Toolbox in Matlab. Finally, the effectiveness of the result is demonstrated by a example.