广义输出误差模的两阶段最小二乘递推辨识.PDFVIP

31 2 Vol. 31 No. 2 2014 2 Control Theory Applications Feb. 2014 DOI: 10.7641/CTA.2014.30035 , , , , (1. , 330063; 2. , 214122) : , (OEARMA), . , , . , , , . , . : ; ; ; : TP273 : A Two-stage least squares recursive identification for generalized output error models JIA Jie , CHEN Chen , CAO Jiao , LUO Xiao-na , DING Feng (1. School of Information Engineering, Nanchang Hangkong University, Nanchang Jiangxi 330063, China; 2. School of Internet of Things Engineering, Jiangnan University, Wuxi Jiangsu 214122, China) Abstract: A class of the colored noise interference systems is with the generalized output error model (OEARMA). This paper presents a two-stage recursive least squares algorithm for their parameter identifications. The basic idea is to combine the auxiliary model identification idea and the decomposition technique to decompose a system into two subsystems, each of which contains one parameter vector. When applying the auxiliary model-based recursive extended least squares theory, we employ the auxiliary model output to replace the unknown intermediate variables in the identified model information vector, and use the estimated residuals to replace the immeasurable noise terms in the information vector. This makes it possible to apply the recursive identification idea to estimate all the parameters of the system with a high computational efficiency. The simulation examples validate the effectiveness of the proposed algorithm. Key words: stochastic system; least squares; two-stage recursion; auxi