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.
Phân tích khí hòa tan (DGA) là một phương pháp chẩn đoán quan trọng trong việc xác định lỗi tiềm ẩn bên trong máy biến áp (MBA) dầu. Trong số các phương pháp DGA truyền thống, phương pháp tỉ lệ IEC và Roger được áp dụng rộng rãi tại các Trung tâm thí nghiệm của ngành điện. Tuy nhiên, độ chính xác của các phương pháp này bị hạn chế bởi sự mơ hồ trong các ngưỡng tỉ lệ khí và quy tắc phân loại lỗi. Nghiên cứu này đề xuất một cách tiếp cận mới trong chẩn đoán lỗi của MBA bằng cách tích hợp logic mờ cải tiến với bộ quy tắc quyết định của phương pháp IEC và Roger. Khác với FL truyền thống, phương pháp cải tiến này giúp nâng cao đáng kể độ chính xác và khả năng thích nghi với tập dữ liệu DGA đầu vào. Các đánh giá thực nghiệm trên bộ dữ liệu DGA thực tế cho thấy phương pháp dựa trên logic mờ cải tiến vượt trội hơn các kỹ thuật truyền thống về độ chính xác, tính nhất quán và độ tin cậy.
Reliable transformer fault diagnosis is essential for maintaining power system stability. The IEEE Key Gas Method (KGM), a widely utilized approach in Dissolved Gas Analysis (DGA), exhibits limitations in addressing ambiguous data and ensuring high diagnostic accuracy. This study presents An enhanced model combining Fuzzy Logic with the IEEE Key Gas Method (FL-KGM) that introduces refined membership functions, optimized fuzzy rule sets, and a novel separation of CO and CO2 to eliminate diagnostic inconsistencies. By leveraging multidimensional gas ratio analysis and an adaptive classification framework, FL-KGM delivers superior fault identification and classification. Experimental validation utilizing real-world datasets demonstrates that FL-KGM achieves up to 98.6% accuracy, significantly outperforming KGM and other FL-based approaches. These findings elucidate the potential of FL-KGM in advancing transformer monitoring, enabling intelligent fault detection, and enhancing predictive maintenance strategies in modern power systems.
Reliable cement crack inspection is essential for structural health monitoring, particularly under challenging illumination conditions such as nighttime and low-light environments. Existing detection-based methods often require extensive bounding-box annotations, high computational resources, and show limited robustness in poor visibility conditions. This paper presents a lightweight RGB-thermal framework that integrates a MobileNetV4 classifier with a Convolutional Block Attention Module (CBAM) and an Enhanced Scale-Invariant Feature Transform (SIFT) localization algorithm for day–night crack inspection. Unlike conventional object detection approaches, the proposed method enables crack classification and localization without manual bounding-box annotation. The framework is evaluated using RGB and thermal images from three datasets, including the GYU-DET benchmark and two newly developed thermal crack datasets. On GYU-DET, the proposed classifier achieves a weighted F1-score of 83.16% using only region-of-interest-level labels, in contrast to the bounding-box-supervised YOLOv11n baseline on the same benchmark (mAP@0.5 = 0.568). Because the two approaches solve different sub-problems–joint detection-and-localization versus region-level classification–their results are reported as a capability comparison rather than a numerical improvement. Notably, crack, one of the two most difficult categories for the bounding-box detector, becomes one of the most reliably recognized categories once localization ambiguity is removed by the proposed decoupled design. For thermal morphology recognition, the original ROI-level evaluation yields weighted F1-scores of 92.25% and 92.69% on Datasets 2 and 3, respectively, within the collected crack set. A five-run crack-disjoint evaluation on Dataset 2, restricted to six morphology classes with sufficient numbers of independent physical cracks, yields an accuracy of % and a macro-F1 of %. End-to-end localization and classification from raw thermograms yields micro-F1 scores of 78.62% and 75.24% on Datasets 2 and 3, respectively. The Enhanced SIFT localization method, which requires no training, achieves F1-scores of 0.888 and 0.867 under passive and active thermal conditions, respectively, while operating within a 200 MB memory footprint on an entry-level 4 GB GPU. The lightweight and illumination-robust design enables reliable nighttime crack inspection and supports UAV-assisted and edge-based structural health monitoring applications.