Subset selection in identification, and application to speed and parameter estimation for induction machines

A method to determine which parameters of a model are numerically identifiable is presented. With this method, parameters are separated into ill-conditioned and well-conditioned parameters. Prior information about ill-conditioned parameters can be incorporated into the estimation process resulting in sensitivity reduction and improved numerical performance of estimation algorithms. The method is an extension to nonlinear models of subset selection methods developed in linear regression. The results are illustrated by application to the case of speed and parameter estimation for induction machine. The insights provided by our parameter subset selection approach are of decisive value in this application