基于Volterra级数模型的非线性系统的鲁棒自适应辨识

研究了基于Volterra模型的非线性系统的鲁棒自适应辨识问题。针对Volterra系统辨识时输入输出观测数据均受噪声污染的情况，建立了基于Volterra模型的鲁棒Volterra总体均方最小自适应辨识算法。算法应用梯度下降原理，通过对梯度的修正，有效地提高了算法的鲁棒性。仿真结果表明，在低信噪比，或使用较大学习因子的情况下，该算法的收敛性能明显优于其他算法，便于实际应用。

Robust Adaptive Identification for Nonlinear System Based on Volterra Series Model

Adaptive identification for nonlin ea r Volterra system is researched.In allusion to the Volterra system identificati on in which the input and output signals are all corrupted by noise, a robust Vo l terra total least mean square adaptive identification algorithm is presented bas ed on Volterra series model. This algorithm is established according to the stee pest descent principle, and its robust performance is effectively improved by mo difying gradient. The simulation results show that the convergence perfo rmance of the presented algorithm is better than those of other algorithms when signal-noise-ratio (SNR) is lower, or a larger learning factor is used. This n ew algorithm could be used in actual application.