Rolling Bearing Fault Diagnosis Method Based on SWT and Improved Vision Transformer

To address the challenge of low diagnostic accuracy in rolling bearing fault diagnosis under varying operating conditions, this paper proposes a novel method integrating the synchronized wavelet transform (SWT) with an enhanced Vision Transformer architecture, referred to as ResCAA-ViT. The SWT is f...

Full description

Saved in:
Bibliographic Details
Main Authors: Saihao Ren, Xiaoping Lou
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/7/2090
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849730351300083712
author Saihao Ren
Xiaoping Lou
author_facet Saihao Ren
Xiaoping Lou
author_sort Saihao Ren
collection DOAJ
description To address the challenge of low diagnostic accuracy in rolling bearing fault diagnosis under varying operating conditions, this paper proposes a novel method integrating the synchronized wavelet transform (SWT) with an enhanced Vision Transformer architecture, referred to as ResCAA-ViT. The SWT is first applied to process raw vibration signals, generating high-resolution time–frequency maps as input for the network model. By compressing and reordering wavelet transform coefficients in the frequency domain, the SWT enhances time–frequency resolution, enabling the clear capture of instantaneous changes and local features in the signals. Transfer learning further leverages pre-trained ResNet50 parameters to initialize the convolutional and residual layers of the ResCAA-ViT model, facilitating efficient feature extraction. The extracted features are processed by a dual-branch architecture: the left branch employs a residual network module with a CAA attention mechanism, improving sensitivity to critical fault characteristics through strip convolution and adaptive channel weighting. The right branch utilizes a Vision Transformer to capture global features via the self-attention mechanism. The outputs of both branches are fused through addition, and the diagnostic results are obtained using a Softmax classifier. This hybrid architecture combines the strengths of convolutional neural networks and Transformers while leveraging the CAA attention mechanism to enhance feature representation, resulting in robust fault diagnosis. To further enhance generalization, the model combines cross-entropy and mean squared error loss functions. The experimental results show that the proposed method achieves average accuracy rates of 99.96% and 96.51% under constant and varying load conditions, respectively, on the Case Western Reserve University bearing fault dataset, outperforming other methods. Additionally, it achieves an average diagnostic accuracy of 99.25% on a real-world dataset of generator non-drive end bearings in wind turbines, surpassing competing approaches. These findings highlight the effectiveness of the SWT and ResCAA-ViT-based approach in addressing complex variations in operating conditions, demonstrating its significant practical applicability.
format Article
id doaj-art-aef5c03934b54c05a56ef6fa15d0f8f6
institution DOAJ
issn 1424-8220
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-aef5c03934b54c05a56ef6fa15d0f8f62025-08-20T03:08:54ZengMDPI AGSensors1424-82202025-03-01257209010.3390/s25072090Rolling Bearing Fault Diagnosis Method Based on SWT and Improved Vision TransformerSaihao Ren0Xiaoping Lou1Key Laboratory of the Ministry of Education for Optoelectronic Measurement Technology and Instrument, Beijing Information Science and Technology University, Beijing 100192, ChinaKey Laboratory of the Ministry of Education for Optoelectronic Measurement Technology and Instrument, Beijing Information Science and Technology University, Beijing 100192, ChinaTo address the challenge of low diagnostic accuracy in rolling bearing fault diagnosis under varying operating conditions, this paper proposes a novel method integrating the synchronized wavelet transform (SWT) with an enhanced Vision Transformer architecture, referred to as ResCAA-ViT. The SWT is first applied to process raw vibration signals, generating high-resolution time–frequency maps as input for the network model. By compressing and reordering wavelet transform coefficients in the frequency domain, the SWT enhances time–frequency resolution, enabling the clear capture of instantaneous changes and local features in the signals. Transfer learning further leverages pre-trained ResNet50 parameters to initialize the convolutional and residual layers of the ResCAA-ViT model, facilitating efficient feature extraction. The extracted features are processed by a dual-branch architecture: the left branch employs a residual network module with a CAA attention mechanism, improving sensitivity to critical fault characteristics through strip convolution and adaptive channel weighting. The right branch utilizes a Vision Transformer to capture global features via the self-attention mechanism. The outputs of both branches are fused through addition, and the diagnostic results are obtained using a Softmax classifier. This hybrid architecture combines the strengths of convolutional neural networks and Transformers while leveraging the CAA attention mechanism to enhance feature representation, resulting in robust fault diagnosis. To further enhance generalization, the model combines cross-entropy and mean squared error loss functions. The experimental results show that the proposed method achieves average accuracy rates of 99.96% and 96.51% under constant and varying load conditions, respectively, on the Case Western Reserve University bearing fault dataset, outperforming other methods. Additionally, it achieves an average diagnostic accuracy of 99.25% on a real-world dataset of generator non-drive end bearings in wind turbines, surpassing competing approaches. These findings highlight the effectiveness of the SWT and ResCAA-ViT-based approach in addressing complex variations in operating conditions, demonstrating its significant practical applicability.https://www.mdpi.com/1424-8220/25/7/2090rolling bearingsfault diagnosisvariable operating conditionssynchronized wavelet transform (SWT)CAA attention mechanismVision Transformer
spellingShingle Saihao Ren
Xiaoping Lou
Rolling Bearing Fault Diagnosis Method Based on SWT and Improved Vision Transformer
Sensors
rolling bearings
fault diagnosis
variable operating conditions
synchronized wavelet transform (SWT)
CAA attention mechanism
Vision Transformer
title Rolling Bearing Fault Diagnosis Method Based on SWT and Improved Vision Transformer
title_full Rolling Bearing Fault Diagnosis Method Based on SWT and Improved Vision Transformer
title_fullStr Rolling Bearing Fault Diagnosis Method Based on SWT and Improved Vision Transformer
title_full_unstemmed Rolling Bearing Fault Diagnosis Method Based on SWT and Improved Vision Transformer
title_short Rolling Bearing Fault Diagnosis Method Based on SWT and Improved Vision Transformer
title_sort rolling bearing fault diagnosis method based on swt and improved vision transformer
topic rolling bearings
fault diagnosis
variable operating conditions
synchronized wavelet transform (SWT)
CAA attention mechanism
Vision Transformer
url https://www.mdpi.com/1424-8220/25/7/2090
work_keys_str_mv AT saihaoren rollingbearingfaultdiagnosismethodbasedonswtandimprovedvisiontransformer
AT xiaopinglou rollingbearingfaultdiagnosismethodbasedonswtandimprovedvisiontransformer