Filtering-based recursive least-squares identification algorithm for controlled autoregressive moving average systems using the maximum likelihood principle
Filtering-based recursive least-squares identification algorithm for controlled autoregressive moving average systems using the maximum likelihood principle
复制标题
使用最大似然原理的受控自回归移动平均系统的基于滤波的递归最小二乘辨识算法
DOI：
10.1177/1077546314523634
复制
发表时间：
2015-11-01
影响因子：
2.8
通讯作者：
Ding, Feng
中科院分区：
文献类型：
--
作者：
Li, Junhong;Ding, Feng
研究受控自回归滑动平均系统的参数估计问题。其基本思想是利用噪声多项式对输入输出数据进行滤波，得到受控滑动平均辨识模型和噪声模型。利用递阶辨识原理，分别采用最大似然递推最小二乘算法和递推最小二乘算法交互估计两个辨识模型的参数。数值算例验证了算法的有效性。
This paper considers the parameter estimation problem of controlled autoregressive moving average systems. The basic idea is to use the noise polynomial to filter the input-output data, then a controlled moving average identification model and a noise model are obtained. A maximum likelihood recursive least squares algorithm and a recursive least squares algorithm are used to interactively estimate the parameters of the two identification models by using the hierarchical identification principle. A numerical example is provided to show the effectiveness of the proposed algorithms.