Estimation of a generic model for a fleet of machines

In this paper, we propose a method to identify a generic model for a machine which is a member of a fleet of identical machines. These latest may work in the same or in different operating conditions. Firstly, the method consists in estimating a linear model for each machine independently from other machines, based on the data collected on the machine itself. Secondly, the common part of the models is identified. For that purpose, a resemblance criterion is used to determine identical coefficients over all the models. New models are then generated under some equality constraints on these parameters. The last step of the method consists in validating the choice made about the common part and hence validating the new models. This is realized by a statistical test based on a comparison between new and old estimates. An academic example is finally presented to illustrate the results of the method.