一类非线性动态系统的非参数GFRF模型辨识

本文对一类用多项式描述的非线性动态系统提出使用ＧＦＲＦ模型类的非参数辨识算法，这种算法的显著特点是需要很小的计算量和存储空间，而且辨识精度较高，仿真结果表明这种非参数模型辨识算法是有效的，而且由辨识方法获得的模型一般具有很好的泛化能力，因而是一种具有重要应用前景的实用方法 。

Identification of Nonparametric GFRF Modelfor a Class of Nonlinear Dynamic Systems*

This paper presents the nonparametric identification algorithm of GFRF models for a class of nonlinear dynamic systems with polynomial form.The distinguishing feature of the algorithm is to desire a limited calculating quantity and store space,and the identification accuracy is high.The simulation results show that the identification algorithm is very effective,and the obtained model is of excellent generalization ability in general.So,it's an approach with important prospect for application.