Artificial intelligence model for transformer fault diagnosis using a constructed database

Dynamic Incipient Fault Forecasting for Power Transformers Using an LSTM Model

“…3) Four AI models (SVM, KNN, decision tree, and ANN) are trained with the DGA datasets extracted from a constructed fault database [31]. Eight transformer health conditions can be detected by the model, which are: low-energy discharge (D1); high-energy discharge (D2); a combination fault discharge fault and thermal fault; partial discharge (PD); low temperature fault (T1); medium temperature fault (T2); high temperature fault (T3); and normal state (NS).…”

“…The fault rate for the seven future weeks and true health state are tabulated in Table X. To clarify, actual faults were assessed by a hybrid method combining the Roger's ratio and Duval triangle method to construct a fault database, which was proposed in our previous work [18] [31]. In most cases, the transformer condition was healthy; only rare cases with DT faults and some cases with thermal faults, particularly for T3 occurred, which matched the actual fault type distribution.…”