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

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<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">%</sup>, which higher than other control diagnostic models. The research results provide a reference for fault diagnosis of HVCBs.