Fault Prediction of Transformer Using Machine Learning and DGA

D. Saravanan, Ahmad Fariz Hasan, Ajit Singh, Hannan Mansoor, Rabindra Nath Shaw

20202020 IEEE International Conference on Computing, Power and Communication Technologies (GUCON)41 citationsDOI

Abstract

The Power Transformer are the most Crucial part of power System and its failure may result in not only interrupted power supply but also great economic loss. So, it is important to monitor transformer health on daily bases. Many diagnostic techniques are available for this purpose out of which DGA have been an important technique. Although DGA (Dissolved Gas Analysis) is good technique but it depends mostly on the expertise on human. Hence it is not the fastest faults diagnostic tool. This paper uses the Multilayer Artificial Neural Network Model and Support Vector Machine Classifier Model in order to predict the Fault condition of transformer using DGA (Dissolved Gas Analysis) Data. The Support Vector Machine Classifier has shown better results around 81.4% then the Multilayer Artificial Neural Network which give prediction result accuracy around 76 %.

Topics & Concepts

Dissolved gas analysisArtificial neural networkSupport vector machineTransformerClassifier (UML)Machine learningComputer scienceArtificial intelligenceCondition monitoringEngineeringReliability engineeringTransformer oilElectrical engineeringVoltagePower Transformer Diagnostics and InsulationHigh voltage insulation and dielectric phenomenaMachine Fault Diagnosis Techniques