.png){kind=icon}
.png){kind=icon}
Return
Robust unsupervised gearbox fault detection under variable-speed operating conditions
.png){kind=icon}
OA
AI
S
Y
J
F
DOI：10.1016/j.egyai.2026.100862.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Order-domain alignment removes speed-induced spectral shifts in gear vibration. • Physics-based simulation confirms kinematic validity of order-domain augmentation. • Speed-conditioned decoding with latent regularization decouples health from speed. • Only healthy data are required for unsupervised fault detection. • Robust fault detection is achieved across tested operating regimes.
Keywords:
Energy machinery
Wind turbine drivetrain
Unsupervised fault detection
Speed-invariant representation learning
Order domain augmentation
Autoencoder
Journal
IF:
9.6
Papers:
835
Citations:
3.1K