Small sample fault diagnosis method of gearbox based on frequency band attention network

Objectives Deep learning-based fault diagnosis methods generally require a large number of fault samples. To achieve accurate gearbox fault diagnosis under small-sample scenarios, a novel diagnosis method based on frequency band attention network is proposed.

Methods Initially, through the reconstruction-encoding layer, the vibration signals are transformed into sub-band encoded signals that are easy to classify; Subsequently, the intrinsic band attention layer is constructed to fully mine the representative time-frequency features from sub-band encoded signals; Finally, the multiple feature fusion module is used to integrate the time-frequency feature information for fault recognition under small-sample conditions.

Results The validation results on a gearbox fault simulation test bench show that the proposed method achieves a fault diagnosis accuracy of 99.85% under small-sample conditions, outperforming the comparison models.

Conclusions The research results can provide a reference for the fault diagnosis of gearbox under small sample conditions.