Classification Method in Fault Diagnosis of Oil-Immersed Power Transformers by Considering Dissolved Gas Analysis

Rosmaliati (Department of Electrical Engineering, Institut Teknologi Sepuluh Nopember, Indonesia)
Bernandus Anggo Seno Aji (Department of Information Technology, Institut Teknologi Telkom, Surabaya, Indonesia)
Isa Hafidz (Department of Electrical Engineering, Institut Teknologi Telkom, Surabaya, Indonesia)
Ardyono Priyadi (Department of Electrical Engineering, Institut Teknologi Sepuluh Nopember, Indonesia)
Mauridhi Hery Purnomo (Department of Computer Engineering, Institut Teknologi Sepuluh Nopember, Indonesia)

EMITTER International Journal of Engineering Technology
Vol 10 No 2 (2022)

Fault detection in the incipient stage is necessary to avoid hazardous operating conditions and reduce outage rates in transformers. Fault-detected dissolved gas analysis is widely used to detect incipient faults in oil-immersed transformers. This paper proposes fault diagnosis transformers using an artificial neural network based on classification techniques. Data on the condition of transformer oil is assessed for dissolved gas analysis to measure the dissolved gas concentration in the transformer oil. This type of disturbance can affect the gas concentration in the transformer oil. Fault diagnosis is implemented, and fault reference is provided. The result of the NN method is more accurate than the Tree and Random Forest method, with CA and AUC values 0.800 and 0.913. This classification approach is expected to help fault diagnostics in power transformers.