This paper presents the application of Hilbert-Huang Transform (HHT) and artificial neural network (ANN) for fault detection on transformers. The combined procedure, Emprical mode decomposition (EMD) and Hilbert transform, is called the Hilbert-Huang Transform (HHT). The ANN is designed and trained using feed forward propagation algorithm. The input features of the ANN are extracted from the frequency and aplitude of IMFs by applying the Hilbert transform. Simulation results of the proposed method for fault detection on tranformers proveto be effective.