Application of model selection methods for the identification of a dynamic boost pressure model

摘要

Modeling a technical system requires a lot of effort. Especially, when used for simulation, there are high demands on the models regarding approximation accuracy and computational complexity. As building a model based on physical laws is highly time-consuming, system identification is used increasingly. A key problem in system identification is to select an appropriate model, especially when no a priori information of the considered process is available. This paper treats the application of model selection approaches known from linear regression analysis to the identification of a dynamic boost pressure model for the use in a simulation.