A black-box approach based on Artificial Neural Networks (ANNs) for modeling non-linearities in power electronic converters (EPCs) is investigated in this paper. By the proposed approach, a model based on the use of a nonlinear autoregressive exogenous NARX-ANN is implemented and used to replicate, within the same model, the behavior of a boost converter both in the discontinuous conduction mode (DCM) and in the continuous conduction mode (CCM). The effectiveness of the obtained models is evaluated in the time domain as well as in the frequency domain. Experimental tests verify the validity of the proposed approach.
