基于目标函数的递推子空间辨识算法-控制理论与应用.PDFVIP

第xx 卷第x 期 控制 理 论 与 应 用 Vol. xx No. x xxxx 年x 月 Control Theory Applications Xxx. xxxx 文文文章章章编编编号号号:2010 基基基于于于目目目标标标函函函数数数的的的递递递推推推子子子空空空间间间辨辨辨识识识算算算法法法 王 佳, 王宏伟, 顾 宏 (大连理工大学控制科学与工程学院, 辽宁大连116024) 摘要: 针对实际工程中要求对系统参数进行在线估计的问题, 提出一种递推子空间辨识的新方法. 通过引入辅助 变量关系将递推子空间辨识问题转化为目标函数的迭代最小化求解问题. 采用递推最小二乘算法在线估计参数并 由传播方法得到更新的广义能观性矩阵, 进而求得子空间辨识模型系统参数. 该算法简单有效且对初值具有更高 的鲁棒性. 最后, 通过仿真实例验证算法的有效性. 关键词: 子空间辨识; 递推算法; 目标函数; 递推最小二乘法 中图分类号: TP273 文献标识码: A Recursive subspace identification algorithm based on the objective function WANG Jia, WANG Hong-wei, GU Hong (School of Control Science and Engineering, Dalian University of Technology, Liaoning Dalian 116024, China) Abstract: For the requirements of estimating the system parameters on-line in most practical engineering problems, a new recursive subspace identification algorithm is proposed in this paper. The recursive identification problem is converted to minimize the objective function by the introduction of the instrumental variable relation. The Recursive least square algorithm is employed to estimate the parameters, then the propagator method is developed to update the extended observ- ability matrix and finally the system matrices are computed. The proposed method is simple and effective and improves the robustness to the uncertainty in initial values. The efficiency of this method is illustrated with a simulation example. Key words: subspace identification; recursive algorithm; the objective function; recursive least square method(RLS) 1 引引引言言言(Introduction) 本文直接从过程模型的状态空间方程出发推导 子空间模型辨识(Subspace model identification,