Fault detection and isolation of asynchronous machine based on the probabilistic neural network

Abstract

In this paper, we propose three neural networks based methods for fault detection and isolation of asynchronous machine: a probabilistic neural network (PNN), multi-layer perceptron (MLP), and generalised regression neural network (GRNN). To perform efficient diagnostic results the cross-validation procedure input data is partitioned into three sets: a training set, a validation set and a test set. The stator RMS values of three-phase voltages and currents are used as model inputs to identify the different types of faults and the normal operating mode. Efficiency of these three neural based methods is compared using a test set of 100 data.