Modelling of an electromagnetic levitation system using a neural network

Systems which involve electromagnetic interactions are very difficult to model. Often, when developing controllers for such systems the model which is used is affected by uncertainties or is linearized. Even if these models can be used for the controller design process, they are not well suited for accurate simulations. In this paper, an electromagnetic levitation system is modeled. Based on the observed behavior of the system, a neural network is used to approximate a non-linear parameter in the model of the plant, which otherwise would have been very difficult to model.