A Probabilistic Classifier for Transformer Dissolved Gas Analysis With a Particle Swarm Optimizer

Abstract

This paper presents a Parzen-Windows (PW)-based classifier for transformer fault diagnosis, which is able to interpret transformer dissolved gas analysis (DGA) with a probabilistic scheme. A global optimizer, particle swarm optimizer (PSO), is employed to optimize the parameters of PW to improve fault classification accuracies. First, the essential concept of PW-based classification using PSO is introduced. This probabilistic classification approach is then extended from a simple PW method to classifying fault types on the evidence of various gas ratios. The proposed approach not only allows an intuitive interpretation of the transformer diagnosis, but also provides a DGA reviewer with quantified confidence to support decision making. It can be seen from the results that both the diagnosis accuracy and computational efficiency are improved compared with a number of fault classification techniques.