Improved Swin Transformer Integrated with GADF Method for Bearing Fault Detection
Authors:
- 6 August 2025
- journal article
- Published by IOP Publishing in Engineering Research Express
- Vol. 7 (3)
Abstract
Detecting bearing faults is of crucial importance for ensuring the reliability and performance of modern industrial equipment. In this research, a method integrating the Gramian Angular Difference Field (GADF), an improved Swin Transformer, and a Convolutional Neural Network with Global Attention Module (CNN-GAM) is proposed. The proposed approach utilizes GADF to convert one-dimensional vibration signals into two-dimensional images, which not only preserves the time-varying characteristics of the signals but also enhances the feature representation. The improved Swin Transformer efficiently extracts multi-scale and multi-level features, reducing computational complexity and broadening the receptive field of the model. The CNN-GAM module then optimizes the feature representation, with the convolutional neural network capturing local features and the global attention module assigning precise attention weights to accentuate crucial information, thereby significantly enhancing the accuracy of the model. This method has been validated using the bearing dataset from Case Western Reserve University (CWRU). After comprehensive data cleaning and processing, the model exhibited remarkable performance. In the first round of training, the accuracy reached 88%, and within 25 iterations, the validation accuracy was stably maximized at 99%, while the training loss was as low as 0.01. Compared with existing models, this approach demonstrates greater robustness, requires fewer training rounds, and maintains excellent stability. Even under simulated complex working conditions, it can accurately classify a wider range of fault types with minimal misclassifications. It achieves high precision and high reliability, and thus holds significant theoretical value as well as promising potential for industrial applications.Keywords
Funding Information
- Science and Technology Innovation Plan Projects of Tianjin (23YDTPJC00290)
This publication has 17 references indexed in Scilit:
- A comprehensive review of non-destructive methods for bearing lubricating oil film thickness measurementIndustrial Lubrication and Tribology, 2024
- Research on a System Noise Simulation and Filtering Method in Tunable Diode Laser Absorption Spectroscopy TechnologyJournal of Applied Spectroscopy, 2023
- A Comprehensive Review on Advancement in Deep Learning Techniques for Automatic Detection of Tuberculosis from Chest X-ray ImagesArchives of Computational Methods in Engineering, 2023
- A Gene Correlation Measurement Method for Spatial Transcriptome Data Based on Partitioning and DistributionJournal of Computational Biology, 2023
- Fault Diagnosis of Variable Speed Bearing Based on EMDOS-DCCNN ModelJournal of Vibration Engineering & Technologies, 2023
- A Novel Small Samples Fault Diagnosis Method Based on the Self-attention Wasserstein Generative Adversarial NetworkNeural Processing Letters, 2023
- Application of deep learning in brain tumor segmentationScience & Technology Development Journal - Engineering and Technology, 2022
- Correlated SVD and Its Application in Bearing Fault DiagnosisIEEE Transactions on Neural Networks and Learning Systems, 2021
- A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working loadMechanical Systems and Signal Processing, 2018
- A bearing fault diagnosis method based on the low-dimensional compressed vibration signalAdvances in Mechanical Engineering, 2015