摘要
本文给出利用Householder变换对矩阵进行上三角化的按列递推公式。该公式用于差分、多项式、AR、ARMA、CARMA等模型的结构和参数辨识时,可大大减小计算量,提高算法的实用性。
A recursive Householder formula for transforming high rectangular matrices into upper triangular matrices column by column is proposed. The formula can be used to simultaneously estimate the orders and parameters of polynomial models, difference models, AR models, ARMA models, CARMA models and so on. Since the orders can be estimated in passing by our formula, the computation time for estimating both orders and parameters is only slightly more than that for just estimating the parameters of the model with known orders.
出处
《自动化学报》
EI
CSCD
北大核心
1990年第2期142-145,共4页
Acta Automatica Sinica
关键词
矩阵
三角化
系统辨识
建模
System identification
modeling
order estimation
Householder transformation.
