作者：
Torben KnudsenAalborg University
Department of Control Engineering Institute of Electronic Systems Fredrik Bajers Vej 7 DK-9220 Aalborg Ø Denmark. Phone: +*** Fax: +***
If a model has a predictor with poles close to the unit circle, then the one step predictor can have large transients. In parameter estimation this initialization problem is often ignored with severe impact on estimat...
详细信息
If a model has a predictor with poles close to the unit circle, then the one step predictor can have large transients. In parameter estimation this initialization problem is often ignored with severe impact on estimator properties as a result. A method for proper initialization of the predictor is therefore developed. The method is based on the principle of backforecasting used on ARMAX models. A simulation example shows that the new method is superior to the standard prediction error methods.
Symmetrical behaviour of the covariance matrix and the positive-definite criterion are used to simplify identification of single-input/single-output systems using recursive least squares. Simulation results are obtain...
详细信息
Symmetrical behaviour of the covariance matrix and the positive-definite criterion are used to simplify identification of single-input/single-output systems using recursive least squares. Simulation results are obtained and these are compared with ordinary recursive least squares. The adaptive nature of the identifier is verified by varying the system parameters on convergence.
暂无评论