The fault diagnosis of power transformer using clustering and Radial Basis Function neural network

• Published in: 2009 International Conference on Machine Learning and Cybernetics Vol. 3; pp. 1257 - 1260
• Main Author: Li Chao
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.07.2009
• Subjects: Artificial neural networks; Clustering algorithm; Clustering algorithms; Dissolved gas analysis; Fault diagnosis; Least mean square; Machine learning; Machine learning algorithms; Neural networks; Oil insulation; Power transformer; Power transformers; Radial basis function networks; RBF neural network
• DOI: 10.1109/ICMLC.2009.5212287
• ISBN: 9781424437023; 1424437024
• ISSN: 2160-133X

In paper, a fault diagnosis method of power transformer based on the radial basis function (RBF) neural network and clustering is discussed. It uses the clustering algorithm to decide centers of the radial basis function, and then uses least mean square (LMS) to calculate the output weights between the hidden layer and output layer. After decided the architecture of the artificial neural network, uses the history data of power transformer to test the proposed diagnosis system. From the testing result, it can be concluded that the proposed method is efficient in transformer fault diagnosis.