Closed-loop subspace identification of multivariable dynamic errors-in-variables models based on ORT
In terms of the model of errors-in-variables, this article analyses the causes of deviation based on the existing method of subspace identification in the closed-loop system; then, it puts forward another method of subspace identification with an auxiliary variable based on orthogonal decomposition. The auxiliary variables can be selected and improved by this method, improving the quality of system identification.
KeywordsSubspace identification Errors-in-variables Orthogonal projection Closed-loop identification Singular value decomposition
The authors are grateful to the associate editor and the referees for their scrupulous reading and for pointing out several errors in earlier versions of this manuscript. And we gratefully acknowledge the financial supported by the Science and Technology Research Program of Chongqing Municipal Education Commission (Grant No. KJ1729403).