A comparative study of neural network efficiency in power transformers diagnosis using dissolved gas analysis

TLDR

The study compares neural network efficiency for detecting early faults in power transformers. Neural networks were trained on five dissolved‑gas‑analysis criteria (Doernenburg, modified Rogers, Rogers, IEC, CSUS), then tested on new DGA data and compared with inspection results. Diagnosis success rates varied by criterion, ranging from 87 % to 100 %.

Abstract

This paper presents a comparative study of neural network (NN) efficiency for the detection of incipient faults in power transformers. The NN was trained according to five diagnosis criteria commonly used for dissolved gas analysis (DGA) in transformer insulating oil. These criteria are Doernenburg, modified Rogers, Rogers, IEC and CSUS. Once trained, the neural network was tested by using a new set of DGA results. Finally, NN diagnosis results were compared with those obtained by inspection and an analysis. The study shows that NN rate of successful diagnosis is dependant on the criterion under consideration, with values in the range of 87-100%.