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

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