Fault diagnosis of power transformer using random forest based combined classifier

Abstract

In the power system, transformers are crucial electrical equipment that require an insulator or dielectric material, such as paper immersed in insulating oil, to prevent electrical contact between components. The dissolved gas analysis (DGA) test is important for diagnosing and determining the maintenance recommendations for transformers. The duval triangle method (DTM) is commonly used to identify faults in transformers. The data used in this article are from DGA test of power transformers in East Java and Bali transmission main unit (UIT JBM). The DGA data were analyzed based on the IEEE C57.104-2019 standards, and by using the developed random forest (RF) classifier-based DTM for easier software implementation and better accuracy. The results of fault identification in 6 transformers case study showed a low-thermal fault (T1)<300 °C in transformer 1, where methane gas increased, stray gassing (S) in transformer 5 due to escalating hydrogen gas production, overheating (O)≤250 °C indicated in transformers 2 and 6 due to rising ethane gas production. Transformers 3 and 4 were found in normal condition. This fault identification is done to enhance the accuracy of maintenance recommendation action based on DGA.