Fault Diagnosis of Power Transformers Using Computational Intelligence: A Review

This study reviews computational intelligence (CI) approaches for oil-immersed power transformer maintenance by discussing historical developments and by presenting state-of-the-art fault diagnosis methods. The CI-based approaches have emerged as rapidly evolving but highly effective approaches for using dissolved gas analysis (DGA) data for diagnosing power transformer faults. This study reviews the various CI-based methods reported in international journals, including fuzzy logic, neural networks, and evolutionary optimization-based approaches. (C) 2011 Published by Elsevier Ltd. Selection and/or peer-review under responsibility of organizing committee of 2nd International Conference on Advances in Energy Engineering (ICAEE).