Abstract
This study presents a Variational Autoencoder (VAE)-based framework for the unsupervised mechanical fault diagnosis of high-voltage isolation switches. By analyzing voltage and current signals to compute instantaneous power sequences, the method detects anomalies through reconstruction errors. Experimental results from both laboratory and real-world datasets demonstrate that the VAE model outperforms traditional methods, offering high diagnostic accuracy and robustness without the need for labeled data or manual feature extraction. This approach provides an effective solution for the real-time monitoring and predictive maintenance of high-voltage switchgear.