ARAM-Swin: a hybrid architecture with an adaptive residual attention module and Swin Transformer for rolling bearing fault diagnosis
Authors:
- 27 March 2026
- journal article
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (12) , 126112
Abstract
Existing deep learning methods struggle to simultaneously capture global temporal dependencies and local transient impulses of rolling bearing fault signals, while static attention mechanisms often fail to adapt to complex industrial noise. To address these challenges, this paper proposes ARAM-Swin, a dual-branch hybrid diagnostic architecture. Firstly, a composite Gramian angular field encoding strategy is employed to fuse dynamic and static signal features into multi-view images. Secondly, a parallel extraction framework is constructed: a Swin Transformer branch models long-range dependencies, while a convolutional neural network branch embedded with an adaptive residual attention module (ARAM) extracts fine-grained fault textures. Notably, ARAM utilizes a learnable residual scaling factor to dynamically balance feature enhancement and information preservation. Experimental results on the Case Western Reserve University and XJTU-SY datasets demonstrate that ARAM-Swin delivers superior diagnostic efficacy under multi-condition, cross-domain, limited-sample, and strong-noise scenarios, achieving fault classification accuracies of 99.98% and 99.89%, respectively.Keywords
This publication has 34 references indexed in Scilit:
- Global–local feature learning for fine-grained food classification based on Swin TransformerEngineering Applications of Artificial Intelligence, 2024
- SSTrans-Net: Smart Swin Transformer Network for medical image segmentationBiomedical Signal Processing and Control, 2024
- Surface defect detection and classification of steel using an efficient Swin TransformerAdvanced Engineering Informatics, 2023
- Fault Diagnosis of Rolling Bearing Under Variable Working Conditions Based on CWT and T-ResNetJournal of Vibration Engineering & Technologies, 2022
- Research on fault diagnosis method of MS-CNN rolling bearing based on local central moment discrepancyAdvanced Engineering Informatics, 2022
- CST: Convolutional Swin Transformer for detecting the degree and types of plant diseasesComputers and Electronics in Agriculture, 2022
- Intelligent fault diagnosis of rolling bearing based on wavelet transform and improved ResNet under noisy labels and environmentEngineering Applications of Artificial Intelligence, 2022
- Bearing fault diagnosis base on multi-scale CNN and LSTM modelJournal of Intelligent Manufacturing, 2020
- A transfer convolutional neural network for fault diagnosis based on ResNet-50Neural Computing and Applications, 2019
- Application of empirical mode decomposition and artificial neural network for automatic bearing fault diagnosis based on vibration signalsApplied Acoustics, 2015