Dissolved Gas Analysis of Insulating Oil for Power Transformer Fault Diagnosis with Bayesian Neural Network

Dissolved gas analysis is widely used for preventative maintenance techniques and fault diagnoses of oil-immersed power transformers. There are also various conventional methods dissolved insulating oil in transformers including Doernenburg ratios, Rogers ratios Duval’s triangle. The Bayesian have been developed over many years applied to a range different fields the problem training artificial neural networks. In particular, approach can solve over-fitting networks after being trained. framework be utilised compare rank architectures types This research aims at deploying detailed procedure with inference, known as networks, classify transformer faults based on ratios. this research, IEC TC 10 databases were form test data sets. results obtained from performance trained show that despite limitation available data, an appropriate number hidden units successfully accuracy rates greater than 80%.