A fast method for online closed-loop system identification

In the modern control schemes broadly applied presently in the servo drive system of machine tools, the sampling frequency has been growing larger and larger becomes higher and higher, so it is important to keep up-to-date with the variance of the actual system parameters. As a solution to the problem, a novel method developed from the recursive extended least squares (RELS) algorithm in terms of the computation of functions, operates in such a way that the parameters of the system model are revised only when several proper new groups of data are obtained. The simulation and experimentation of online direct closed-loop system identification indicate that, by selecting the updating step, this method is able to effectively cut down the identifying cost time while obtaining satisfactory accuracy of estimation.