Work

Hierarchical Convolution-Transformer Framework for Gear Fault Diagnosis Under Severe Noise

Year: 2025

Type: article

Abstract: To address the limitations of convolutional neural networks in capturing global fault features, the high computational cost and overfitting risk of Transformer models in gear fault diagnosis, and the feature degradation under strong noise, this study proposes a novel convolution–Transformer–channel attention network. The proposed method achieves a dynamic balance between local and global features through the joint design of multi-scale convolution and sparse self-attention. Multi-scale convolution extracts local features, while the enhanced sparse multi-head self-attention models long-range dependencies via adaptive sequence compression to reduce computational complexity. In addition, a dual-stage squeeze-and-excitation mechanism recalibrates feature channels to suppress noise interference and enhance robustness. This method is well-suited for gear fault diagnosis under strong noise conditions, offering improved generalization capability and promising potential for industrial applications.

Source: IEEE Access

DOI: 10.1109/access.2025.3580424

Authors: Qiushi He, Bo Kang, Shanshan Fan, Xueyi Li

Institution: Northeast Forestry University

Language: English

Topic: Machine Fault Diagnosis Techniques

Subfield: Control and Systems Engineering

Field: Engineering

Domain: Physical Sciences

SDG: Industry, innovation and infrastructure

Open Access status: gold

Estimated APC paid: $2,075