High-Voltage GIS Devices Fault Diagnosis Leveraging Sequence-to-Sequence Modeling

The real-time fault diagnosis of High Voltage Gas Insulated Switches (HV-GIS) is critical for maintaining the safety and operational reliability of electrical grids. Conventional diagnostic techniques mainly depend on statistical feature extraction followed by machine learning-based classification. However, these methods often face challenges in effectively handling the complexities introduced by varying aging processes and diverse operating conditions. In order to address the issues, we introduce a general fault diagnosis framework for HV-GIS that leverages sequence-to-sequence (seq2seq) modeling. Our framework transforms sensing data into sequences and treats the diagnosis task as a seq2seq problem, leveraging this modeling approach to achieve a generalized fault diagnosis. Experimental results indicate that the diagnosis model trained with our framework outperforms baseline models, offering a more effective and generalized solution for HV-GIS fault diagnosis.