A temporal-spatial multi-order weighted graph convolution network with refined feature topology graph for imbalance fault diagnosis of rotating machinery

• Published in: Reliability engineering & system safety Vol. 257; p. 110830
• Main Authors: Jiang, Zhichao, Liu, Dongdong, Cui, Lingli
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.05.2025
• Subjects: Dynamically adjusted label smoothing regularization; Imbalance fault diagnosis; Multi-order weighted graph convolution layer; Refined feature topology graph; Rotating machinery; Rotating machinery; Dynamically adjusted label smoothing regularization; Refined feature topology graph; Multi-order weighted graph convolution layer; Imbalance fault diagnosis

In the actual operation, rotating machinery mostly works under normal condition. The collected monitoring data often exhibit serious distribution imbalance with far more normal label samples than fault label samples, leading to poor recognition performance of standard intelligent diagnosis models. B...