Application of neural networks in the classification of incipient faults in power transformers: A study of case

The power transformer is one of the most important equipment in an electric power system. If this equipment is out of order in an unplanned way, the damage for both society and electric utilities are very significant. In this work, multi-layer perceptrons have been trained via Rprop algorithm to classify incipient faults in power transformers. The proposed procedure has been applied to real databases derived from chromatographic tests of power transformers. The results obtained here show that the proposed technique generates concordance rates between 75 and 90% most of the time. Neural classifiers can be seen as a key component in power transformer predictive maintenance.