Research on transformer fault diagnosis and early warning technology based on digital twins

Power transformers are critical equipment in power systems, and their operational reliability directly affects the safety and stability of grid operation. Conventional transformer operation and maintenance methods are often limited by fixed alarm rules and insufficient integration of monitoring information, making it difficult to achieve intelligent fault diagnosis and timely warning support. To address these issues, this paper proposes a digital twin-assisted framework for transformer fault diagnosis and early warning by integrating transformer digital modeling, online monitoring information, and dissolved gas analysis (DGA)-based intelligent diagnosis. A three-dimensional transformer digital model is constructed using laser point cloud reconstruction and parametric modeling to support equipment state representation and information mapping. Meanwhile, a Snake Optimization-Random Forest (SO-RF) model is developed for multi-class transformer fault diagnosis using five characteristic dissolved gas features. The proposed model is trained and tested using dissolved gas data from a power company's transformer fault case library and compared with Support Vector Machine (SVM) and Random Forest (RF) models. Experimental results show that the proposed SO-RF model achieves an overall diagnostic accuracy of 93.80%, which is higher than those of RF and SVM, with accuracies of 89.98% and 86.39%, respectively. The proposed framework provides a feasible technical route for combining data-driven transformer fault diagnosis with digital twin-assisted state visualization and warning support for intelligent transformer operation and maintenance.