A hybrid approach combining deep learning and signal processing for bearing fault diagnosis under imbalanced samples and multiple operating conditions

Abstract To enhance bearing fault diagnosis performance under various operating conditions, this paper proposes a hybrid approach based on generative adversarial networks (GANs), transfer learning, wavelet transform time-frequency representations, asymmetric convolutional networks, and the multi-hea...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Benjie Zhang, Wei Wang, Yan He
Formato:	Artigo
Idioma:	Inglês
Publicado em:	Nature Portfolio 2025-04-01
coleção:	Scientific Reports
Assuntos:	Improved asymmetric convolutional networks Sample imbalance issue Different operating conditions Multi-head attention mechanism Rolling bearing Fault diagnosis
Acesso em linha:	https://doi.org/10.1038/s41598-025-98138-1
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!