Enhancing Data Preprocessing Layer for Power Transformer Fault Diagnosis Using DGA Combining Fuzzy Logic and Duval Triangle 1

The Duval Triangle 1 method, when combined with fuzzy logic, has been widely utilized in the diagnostics of power transformer faults due to its straightforwardness and interpretability. Nevertheless, the conventional approach is fundamentally constrained by its dependence on only three gas components—methane $\left(\text{CH}_{4}\right)$, acetylene $\left(\mathrm{C}_{2} \mathrm{H}_{2}\right)$, and ethylene ($\mathrm{C}_{2} \mathrm{H}_{4}$)—which limits its diagnostic capability in situations where other gases such as hydrogen ($\mathrm{H}_{2}$) and ethane ($\mathrm{C}_{2} \mathrm{H}_{6}$) are crucial. To overcome these limitations, this study introduces two significant enhancements. Firstly, a refined fuzzy logic framework is developed to address zone boundary ambiguities within the Duval Triangle, thereby enhancing classification precision and achieving a diagnostic accuracy of 90%. Secondly, a data preprocessing layer is incorporated, facilitating the analysis of a more comprehensive set of input gases ($\% \text{CH}_{4}, \% \mathrm{C}_{2} \mathrm{H}_{2}, \% \mathrm{C}_{2} \mathrm{H}_{4}, \% \mathrm{H}_{2}$, and $\% \mathrm{C}_{2} \mathrm{H}_{6}$). This layer performs normalization, outlier detection, and dimensionality adjustment, further elevating diagnostic performance to 97.1%. The proposed improvements are validated using real-world datasets, demonstrating substantial gains in both accuracy and robustness. The results underscore the synergistic advantage of integrating fuzzy logic inference with intelligent data preprocessing, offering a scalable and reliable solution for contemporary transformer condition monitoring.