Power Transformer Fault Diagnosis based on Dissolved Gas Analysis with Logistic Regression

Logistic regression (LR) approach for power transformer fault diagnosis, based on dissolved gas analysis (DGA) is presented in this paper. DGA methods proposed by actual standard IEC 60599, often identify wrong fault or cannot even recognize fault type. To overcome these problems, in recent years, several artificial intelligence (AI) approaches are proposed. In this paper LR is applied for the first time in multi-layer and multi class configuration models for transformer fault diagnosis. It is shown that the proposed approach gives a very good classification performance.

---

Przedstawiono metodę diagnostyki transformatora bazująca na analizie rozpuszczonego gazu metodą logistycznej regresji. Metoda ta umożliwia nie tylko wykrywanie uszkodzeń ale także ich klasyfikację.