损失数据线性参数系统的递推最小二乘辨识方法  

Recursive least squares identification algorithms for linear-in-parameter systems with missing data

作　　者：丁锋[1] 汪菲菲[1] 

机构地区：[1]江南大学物联网工程学院,江苏无锡214122

出　　处：《控制与决策》2016年第12期2261-2266,共6页Control and Decision

基　　金：国家自然科学基金项目(61273194)

摘　　要：针对损失数据线性参数系统的参数辨识问题,借助辅助模型辨识思想推导出其变递推间隔辅助模型递推最小二乘算法.为了提高该算法的计算效率,利用分解技术得到变递推间隔分解递推最小二乘算法估计系统参数.此外,在变递推间隔分解递推最小二乘算法中引入遗忘因子,从而提高参数估计精度和收敛速度.仿真结果表明,所提出的算法能有效估计系统参数.An interval-varying auxiliary model based recursive least squares（AM-RLS） algorithm is derived for linear-inparameter systems with missing data by means of the auxiliary model identification idea. In order to improve the computation efficiency, an interval-varying decomposition AM-RLS algorithm is proposed for estimating the system parameters. The introduction of the forgetting factors can improve the parameter estimation accuracy and accelerate the convergence rates of the interval-varying decomposition based AM-RLS algorithm. The simulation results show that the proposed algorithms can effectively estimate the parameters of the system.

关 键 词：参数估计 辅助模型 分解技术 损失数据 线性参数系统 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]