This document presents a technique for classifying faults on overhead transmission lines using S-Transform and a Probabilistic Neural Network (PNN) classifier. Voltage signals are processed using S-Transform to extract energy features from each phase. These 3 features (1 per phase) are used as inputs to a PNN classifier to determine the type of fault (e.g. line-ground, line-line) and faulty phase. The method was tested on a simulated 3-phase transmission line model in MATLAB with different fault conditions. It produced accurate classification results, even when noise was added to the signals. The paper concludes the method provides fast and accurate fault classification.