摘要详情

ID / 提交时间

283 / 2024-09-14 19:53:47

标题

Research on Fault Diagnosis of High Voltage Circuit Breakers Based on Improved FCN

关键字

high voltage circuit breakers; fault Diagnosis; self-attention; full convolutional networks

主题及专题

1)Emerging HV Switching Technologies

状态

终稿

作者

Yifan Fu / Dalian University of Technology

Xiongying Duan / Dalian University of Technology

Lubin Wu / Dalian University of Technology

Zhenqi Jiang / Dalian University of Technology

Minfu Liao / Dalian University of Technology

摘要

With the development of intelligent power system in recent years, the diagnosis of high voltage circuit breakers (HVCBs) has become one of the research hotspots. In order to find a better diagnosis method, an experimental platform was established to simulate different typical faults. Several parameters extracted from opening coil current and vibration signal under different situations were compared to select the most representative characteristic parameters. Combining self-attention mechanism and full convolutional networks (FCN), the Improved FCN model was set up. The data were imported to the Improved diagnostic models, it was found that the accuracy of new method can be 95.7%, which higher than other control diagnostic models. The research results provide a reference for fault diagnosis of HVCBs.