Accurate models of Overcurrent (OC) with inverse time relay characteristics play an important role for coordination of power system protection schemes. This paper proposes a new method for modelling OC relays curves. The model is based on artificial neural networks. The cascade correlation neural network is used to calculate operating times of OC relays for various Time Dial Settings (TDS) or Time Multiplier Settings (TMS). The new model is more accurate than traditional models. The model is validated by comparing the results obtained from the new method with nonlinear analytical, perceptron and backpropagation neural networks models as applied for various types of overcurrent relays.