Identification of switched reluctance machine inductance using artificial neuronal network

This paper aims, to presents a new method for identified the parameters of switched reluctance machine (SRM) using neural network and Hammerstein model. This latter, is consists of a static nonlinear block followed by a dynamic linear block. Thus, the inherent magnetic nonlinearity of the SRM must be taken into account by appropriate identification of the machine parameters. The model of Hammerstein is verified and compared to neural networks and polynomial method.