论文部分内容阅读
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．
In this paper, a non-parametric identification algorithm using GFRF model classes is proposed for a class of nonlinear dynamical systems described by polynomials. The salient feature of this algorithm is that it requires a small amount of computation and storage space, and identification accuracy is high. The simulation results show that this non-parametric model identification algorithm is effective, and the model obtained by the identification method generally has good generalization ability, so it is a practical method with important application prospect.