Open access
Aug 2026
A lightweight mechanical fault diagnosis framework based on dynamic separable convolution and broadcast self-attention
A lightweight fault diagnosis framework that effectively balances diagnostic accuracy, model lightweighting, and noise resistance, offering an efficient solution for real-time fault diagnosis in industrial settings.
Pei-Chen Yang, Yizhe Song, Tian-Tong Zhang
· Journal of Vibroengineering · 0 citations