Non-Invasive Detection of Rotor Inter-Turn Short Circuit in Large Hydrogenerators by Using Stray Flux Measurement Combined With Convolutional Variational Autoencoder Analysis (CVAE)

Salient Pole Synchronous Generators (SPSG) are known for their robustness and stability; However, internal faults like rotor interturn short circuits (ITSC) might still occur and lead to unscheduled machine shutdowns if not caught early. The literature focuses mainly on high-speed SPSGs and is short on studies covering the diagnosis of low-speed machines. To bridge this gap, this paper presents a non-invasive diagnosis method for low-speed SPSG used by Hydro-Québec. The proposed approach is based on real measurements of stray flux signals and faulty synthetic signals, obtained by FEM simulations. The Convolutional Variational AutoEncoder (CVAE) is used to cluster signals according to the fault severity, and to visualize them in 2D space. Furthermore, two studies were conducted to compare the performance and robustness of the CVAE against the
${\bm{RMS}}$
standard method. The results demonstrate that the CVAE is more sensitive and reliable in detecting ITSCs in large hydrogenerators. Finally, a case study was conducted to validate the proposed method using a real faulty dataset, confirming the obtained results.