Fuel cells are electrochemical devices that convert the chemical energy of a reaction directly into dc electrical energy. Proton Exchange Membrane (PEM) fuel cell is a suitable alternative for both electrical transportation and stationary applications. In this article, an Artificial Neural Network (ANN) modelling approach of a PEM fuel cell is developed. This model describes the behaviour of PEM fuel cell voltage under both steady-state and transient conditions. Moreover, the prediction of the operating temperature of a PEM fuel cell based only on its measured voltage and current is proposed and tested. Indeed, experimental data from a 1.2 kW Nexa Ballard PEM fuel cell is used to validate the proposed method.