Fuzzy learning vector quantization networks for power transformer condition assessment

To improve the assessment capability of power transformers, this paper prop oses a new intelligent decision support system based on fuzzy learning vect or quantization (FLVQ) networks. In constructing the system, a fuzzy-based classifier is designed to divide the historical data for dissolved gas anal ysis (DGA) into various categories with different levels of gas attributes. For each category of gas attributes, a learning vector quantization (LVQ) network is trained to be responsible for the classification of the potentia l faults due to insulation deterioration. The assessment approach has been tested on the DGA data from Taiwan Power Company (TPC) and compared with th e previous fuzzy diagnosis system and the existing multi-layered backpropag ation based artificial neural networks (BPANN) methods. Remarkable classifi cation accuracy and far less training efforts of the proposed approach are achieved in this paper.