Oil-filled current transformers are crucial in high-voltage substations, directly affecting grid safety and reliability. Traditional defect diagnosis methods often show low accuracy and limited monitoring coverage, failing to meet operation and maintenance requirements. This paper proposes an AI-empowered digital twin-based defect diagnosis method that addresses typical issues like oil leakage, insulation damage, and moisture ingress by extracting relevant characteristic parameters to create an evaluation index system. A digital twin model integrates winding, core, and thermal flow characteristics, enabling real-time acquisition of operation parameters and precise mapping between physical and virtual transformers. A dual-model AI framework using Extreme Gradient Boosting (XGBoost) and Support Vector Machine (SVM) is introduced for intelligent defect identification and early defect prediction through multi-source data fusion. Finally, a corresponding diagnostic system is developed and verified using actual operation data from a 220 kV substation in Liaoning Province. The results show that the proposed method enables the online monitoring of multiple operating parameters, and the dual-model framework exhibits higher diagnostic accuracy and faster computation speed compared with Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN), providing effective support for intelligent condition-based maintenance of current transformers.
Zhong et al. (Wed,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: