非线性动态调节模型的滤波式递推辨识算法  

Recursive Identification Algorithm Based on Data Filtering for Hammerstein-CARAR Models

作　　者：岳娜[1] 肖永松[1] 

机构地区：[1]江南大学通信与控制工程学院,无锡214122

出　　处：《科技通报》2010年第5期704-707,共4页Bulletin of Science and Technology

基　　金：国家自然科学基金项目(编号:60973043)

摘　　要：针对Hammerstein非线性动态调节模型提出一种基于数据滤波的递推广义最小二乘算法,方法的主要思想是:通过数据滤波,将辨识模型分解成系统模型和噪声模型,然后分别辨识。最后给出两种方法的仿真实例,通过与递推广义最小二乘算法参数估计精度和收敛速度的比较,来说明滤波式递推广义最小二乘算法的有效性。A new approach is developed for Hammerstein-CARAR models,that is the data filtering based recursive generalized least squares algorithms （F-RGLS）. Through the data filtering,we obtain two identification models,one including the parameters of the system model,and the other including the parameters of the noise model. Thus,the recursive least squares method can be used to estimate the parameters of these two identification models,respectively,by replacing un- measurable noise terms in the information vectors with their estimates. The simulation example shows that the proposed F-RGLS algorithm has high computational efficiency.

关 键 词：递推辨识 非线性系统 HAMMERSTEIN模型 最小二乘算法 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]