Machine learning methods for detecting anomalies in a power transformer by monitoring its hot-spot temperature

C. Brighenti, M.A. Sanz-Bobi

4th International Conference on Power Engineering, Energy and Electrical Drives - POWERENG 2013, Estambul (Turquía). 13-17 mayo 2013

Resumen:

This paper analyzes and compares different machine learning methods such as decision trees, SOMs, MLPs and rough sets for the classification of the operation condition of a power transformer. The purpose is to construct a classification model able to estimate the hot-spot temperature as a function of other external input variables. The classifier would then be used to detect anomalous operation conditions of the transformer by comparing the observed and estimated hot-spot temperatures.

Palabras clave: Classification methods; anomaly detection; power transformer; decision trees; neural networks; rough sets

DOI: https://doi.org/10.1109/PowerEng.2013.6635664

Publicado en POWERENG 2013, pp: 528-533, ISBN: 978-1-4673-6392-1

Fecha de publicación: 2013-10-21.

Cita:
C. Brighenti, M.A. Sanz-Bobi, Machine learning methods for detecting anomalies in a power transformer by monitoring its hot-spot temperature, 4th International Conference on Power Engineering, Energy and Electrical Drives - POWERENG 2013, Estambul (Turquía). 13-17 mayo 2013. En: POWERENG 2013: Proceedings of the 4th International Conference on Power Engineering, Energy and Electrical Drives, e-ISBN: 978-1-4673-6392-1