摘要
本文提出一种新的回归方程的鲁棒递推辨识方法。该方法通过Huber函数选择加权因子,使得参数估计值对由测量系统引起的大扰动或异常值具有鲁棒性。文中给出并证明了该算法对确定性系统的参数估计的收敛性与一致性定理。两个线性动态系统的计算机仿真实例显示出该方法对大扰动或异常值的良好鲁棒性以及参数估计的收敛性。
This paper presents a novel robust recursive identification method for regressive equations. The method is with robustness for great disturbances or outliers generated by measurement systems via choosing weighting factor based on huber function. The identification algorithm is discussed in detail. For deterministic regressive systems,a theorem about the convergence and consistence of parameter estimates is stated and proved strictly. Two computer simulation examples for linear dynamical systems show us the good robustness for the great disturbances or outliers,convergence of the method proposed in this paper.
关键词
匐棒性
最小二乘法
参数估计
control theory
parameter estimate
robustness
least squares method
