As one of the essential equipment of Gas Insulated Switchgear (GIS), the abnormal mechanical condition of the disconnector will directly lead to the interruption of its opening and closing operation and the delay of the power outage and transmission. To effectively and efficiently recognize the mechanical condition of GIS disconnector, this paper presents a mechanical fault diagnosis method consisting of synchrosqueezing wavelet transform (SWT) and stacked autoencoder (SAE) based on the vibration signal originating from the opening and closing operation of GIS disconnector. The time-frequency representation (TFR) of vibration signal is calculated and the deep-learning framework based on the SAE is built. The analysis results of a three-phased GIS disconnector under the normal and typical mechanical fault conditions show that the proposed fault diagnosis method can identify the different mechanical conditions with high accuracy.

暂无