RESEARCH PAPER
A Multi-Scale Depth-wise Separable Convolution Swin Transformer for Fault Diagnosis of In-Wheel Motor Bearings
1
Jiangsu University, China
2
Mie University, Japan
Submission date: 2026-01-08
Final revision date: 2026-03-23
Acceptance date: 2026-03-31
Online publication date: 2026-04-25
KEYWORDS
Fault diagnosisSignal processingAttention mechanismIn-wheel motorSwin transformerDepth-wise separable convolution
TOPICS
ABSTRACT
Fault diagnosis of in-wheel motor bearings is challenging due to weak fault features and non-stationary vibration signals under complex operating conditions. To address the limitations of conventional models in transient impact modeling and feature representation, this study proposes an enhanced Swin Transformer–based fault diagnosis framework. The proposed method integrates a multi-scale convolutional feature-enhanced feed-forward network (MSCF-EFFN) to improve shallow cross-scale representation, a unified deformable shifted window multi-head self-attention (DSW-MSA) framework to adaptively capture irregular transient impact features, and a depth-wise convolution attention module (DWCAM) to refine deep feature selection. The model is validated on a self-built dynamic test bench covering nine bearing health states and 28 operating conditions, achieving an average accuracy of 98.7% and a peak accuracy of 99.12%. Comparative and ablation studies demonstrate superior accuracy, robustness, and convergence performance over existing models.
REFERENCES (46)
1.
Zhao Z, Taghavifar H, Du H, Qin Y, Dong M and Gu L. In-Wheel Motor Vibration Control for Distributed-Driven Electric Vehicles: A Review. IEEE Transactions on Transportation Electrification 2021; 7(4): 2864–2880. https://doi.org/10.1109/TTE.20....
2.
Yan K, Hu Z, Hu J, Li J, Zhang B, Song J, Li J, Chen L, Li H and Xu L. A critical review of radial field in-wheel motors: technical progress and future trends. eTransportation 2024; 22: 100353. https://doi.org/10.1016/j.etra....
3.
Wei J, Zhao Z, Lu E, Liu S, Hu X, Zhou Q, Xu C. Adaptive backstepping tracking control for differential drive vehicles under longitudinal slipping conditions. Biosystems Engineering 2026; 261: 104339. https://doi.org/10.1016/j.bios....
4.
Xue H, Wu M, Zhang Z, Wang H. Intelligent diagnosis of mechanical faults of in-wheel motor based on improved artificial hydrocarbon networks. ISA Transactions 2022; 120: 360–371. https://doi.org/10.1016/j.isat....
5.
Hussain F. Model predictive control system based on direct yaw moment control for 4WID self-steering agriculture vehicle. International Journal of Agricultural and Biological Engineering 2021; 14(2): 175–181. https://doi.org/10.25165/j.ija....
6.
Lei Y, Yang B, Jiang X, Jia F, Li N, Nandi A K. Applications of machine learning to machine fault diagnosis: A review and roadmap. Mechanical Systems and Signal Processing 2020; 138: 106587. https://doi.org/10.1016/j.ymss....
7.
Yu Z, Li Y, Du X, Liu Y. Threshing cylinder unbalance detection using a signal extraction method based on parameter-adaptive variational mode decomposition. Biosystems Engineering 2024; 244: 26–41. https://doi.org/10.1016/j.bios....
8.
Pang J, Li Y, Ji J, Xu L. Vibration excitation identification and control of the cutter of a combine harvester using triaxial accelerometers and partial coherence sorting. Biosystems Engineering 2019; 185: 25–34. https://doi.org/10.1016/j.bios....
9.
Castilla-Gutierrez J, Fortes Garrido J C, Davila Martin J M and Grande Gil J A. Evaluation procedure for blowing machine monitoring and predicting bearing SKFNU6322 failure by power spectral density. Eksploatacja i Niezawodnosc–Maintenance and Reliability 2021; 23(3): 522-529. https://doi.org/10.17531/ein.2....
10.
Tao Y, Ge C, Feng H, Xue H, Yao M, Tang H, Liao Z, Chen P. A novel approach for adaptively separating and extracting compound fault features of the in-wheel motor bearing. ISA Transactions 2025; 159: 337–351. https://doi.org/10.1016/j.isat....
11.
Ma C, Zhang W, Meng L, Yang M, Zhang K, Xu Y. A dual-objective optimized reweighted overlapping group sparse framework integrating frequency slice function for robust bearing fault diagnosis. Mechanical Systems and Signal Processing 2026; 242: 113678. https://doi.org/10.1016/j.ymss....
12.
Guo J, He Q, Zhen D, Gu F. Morphological convolution undecimated wavelet: A novel frequency demodulation analysis method for bearing fault diagnosis. IEEE Transactions on Instrumentation and Measurement 2025; 74: 3522008. https://doi.org/10.1109/TIM.20....
13.
Li H, Wang T, Zhang F, Chu F. AutoVMDPgram: An effective method for fault diagnosis of rolling bearing. IEEE Transactions on Neural Networks and Learning Systems 2024; 36(8): 15233–15243. https://doi.org/10.1109/TNLS.2....
14.
Wang B, Xiong Y, Tan L. A high-precision aeroengine bearing fault diagnosis based on spatial enhancement convolution and vision transformer. IEEE Transactions on Instrumentation and Measurement 2025; 74: 1–15. https://doi.org/10.1109/TIM.20....
15.
Wang J, Zheng J, Pan H, Tong J, Liu Q. Refined composite multiscale slope entropy and its application in rolling bearing fault diagnosis. ISA Transactions 2024; 152: 371–384. https://doi.org/10.1016/j.isat....
16.
Li J, Luo W, Bai M, Song M. Fault diagnosis of high-speed rolling bearing in the whole life cycle based on improved grey wolf optimizer–least squares support vector machines. Digital Signal Processing 2024; 145: 104345. https://doi.org/10.1016/j.dsp.....
17.
Chiang H S, Shih D H, Lin B, Shih M H. An APN model for arrhythmic beat classification. Bioinformatics 2014; 30(12): 1785–1786. https://doi.org/10.1093/bioinf....
18.
Borlea I D, Precup R E, Dragan F, Borlea A B. Centroid update approach to K-means clustering. Advances in Electrical and Computer Engineering 2017; 17(4): 3–10. https://doi.org/10.4316/AECE.2....
19.
Jing N. Neural network-based pattern recognition in the framework of edge computing. Romanian Journal of Information Science and Technology 2024; 27(1): 106–119. https://doi.org/10.59277/ROMJI....
20.
Andonovski G, Leite D, Precup R E, Gomide F, Pratama M, Škrjanc I. Advancements in data-driven evolving fuzzy and neuro-fuzzy control: A comprehensive survey. Applied Soft Computing 2025; 186: 114058. https://doi.org/10.1016/j.asoc....
21.
Zhang Q, Deng L. An intelligent fault diagnosis method of rolling bearings based on short-time Fourier transform and convolutional neural network. Journal of Failure Analysis and Prevention 2023; 23(2): 795–811. https://doi.org/10.1007/s11668....
22.
Yan R, Shang Z, Xu H, Wen J, Zhao Z, Chen X, Gao R X. Wavelet transform for rotary machine fault diagnosis: 10 years revisited. Mechanical Systems and Signal Processing 2023; 200: 110545. https://doi.org/10.1016/j.ymss....
23.
Li J, Liu Y, Wu X, Kong X, Cai B. Fault diagnosis in open circuit of inverters on electrical discharge milling machines using adaptive Gaussian wavelet convolutional network. Measurement 2025; 248: 116856. https://doi.org/10.1016/j.meas....
24.
Jiang G, Wang J, Wang L, Xie P, Li Y, Li X. An interpretable convolutional neural network with multi-wavelet kernel fusion for intelligent fault diagnosis. Journal of Manufacturing Systems 2023; 70: 18–30. https://doi.org/10.1016/j.jmsy....
25.
Sethi M R, Subba A B, Faisal M, Sahoo S, Raju D K. Fault diagnosis of wind turbine blades with continuous wavelet transform based deep learning model using vibration signal. Engineering Applications of Artificial Intelligence 2024; 138: 109372. https://doi.org/10.1016/j.enga....
26.
Ruan D, Wang J, Yan J, Gühmann C. CNN parameter design based on fault signal analysis and its application in bearing fault diagnosis. Advanced Engineering Informatics 2023; 55: 101877. https://doi.org/10.1016/j.aei.....
27.
Sun J, Yang F, Cheng J, Wang S, Fu L. Nondestructive identification of soybean protein in minced chicken meat based on hyperspectral imaging and VGG16-SVM. Journal of Food Composition and Analysis 2024; 125: 105713. https://doi.org/10.1016/j.jfca....
28.
An Y, Zhang K, Liu Q, Chai Y, Huang X. Rolling bearing fault diagnosis method based on periodic sparse attention and LSTM. IEEE Sensors Journal 2022; 22(12): 12044–12053. https://doi.org/10.1109/JSEN.2....
29.
Gao D, Zhu Y, Ren Z, Yan K, Kang W. A novel weak fault diagnosis method for rolling bearings based on LSTM considering quasi-periodicity. Knowledge-Based Systems 2021; 231: 107413. https://doi.org/10.1016/j.knos....
30.
Hou Y, Wang J, Chen Z, Ma J, Li T. Diagnosisformer: An efficient rolling bearing fault diagnosis method based on improved transformer. Engineering Applications of Artificial Intelligence 2023; 124: 106507. https://doi.org/10.1016/j.enga....
31.
Yang Z, Cen J, Liu X, Xiong J, Chen H. Research on bearing fault diagnosis method based on transformer neural network. Measurement Science and Technology 2022; 33(8): 085111. https://doi.org/10.1088/1361-6....
32.
Han K, Wang Y, Chen H, Chen X, Guo J, Liu Z, Tang Y, Xiao A, Xu C, Xu Y, Yang Z, Zhang Y, Tao D. A survey on vision transformer. IEEE Transactions on Pattern Analysis and Machine Intelligence 2022; 45(1): 87–110. https://doi.org/10.1109/TPAMI.....
33.
Niu Z, Zhong G, Yu H. A review on the attention mechanism of deep learning. Neurocomputing 2021; 452: 48–62. https://doi.org/10.1016/j.neuc....
34.
Jin X, Xie Y, Wei X, Zhao B, Chen Z, Tan X. Delving deep into spatial pooling for squeeze-and-excitation networks. Pattern Recognition 2022; 121: 108159. https://doi.org/10.1016/j.patc....
35.
Woo S, Park J, Lee J Y, Kweon I S. CBAM: Convolutional block attention module. Proceedings of the European Conference on Computer Vision (ECCV), Munich, GER, 2018: 3–19. https://doi.org/10.1007/978-3-....
36.
Zhang J, Zhang M, Wang D, Yang M, Liang C. Multi-scale convolutional sparse attention transformer: A lightweight fault diagnosis model for rotating machinery. Neurocomputing 2025; 650: 130934. https://doi.org/10.1016/j.neuc....
37.
Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B. Swin transformer: Hierarchical vision transformer using shifted windows. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) 2021: 10012–10022. https://doi.org/10.1109/ICCV48....
38.
Zeng F, Ren X, Wu Q. A fault diagnosis method for motor vibration signals incorporating swin transformer with locally sensitive hash attention. Measurement Science and Technology 2024; 35(4): 046121. https://doi.org/10.1088/1361-6....
39.
Sun X, Ding H, Li N, Dong X, Sun J, Zheng G. Intelligent fault diagnosis method for shearer rocker gear based on swin transformer and multiscale convolution parallel integration. IEEE Transactions on Instrumentation and Measurement 2025; 74: 1–16. https://doi.org/10.1109/TIM.20....
40.
Zhou T, Yao D, Yang J, Meng C, Li A, Li X. DRSwin-ST: An intelligent fault diagnosis framework based on dynamic threshold noise reduction and sparse transformer with shifted windows. Reliability Engineering & System Safety 2024; 250: 110327. https://doi.org/10.1016/j.ress....
41.
Wang Q, Wu B, Zhu P, Li P, Zuo W, Hu Q. ECA-Net: Efficient channel attention for deep convolutional neural networks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020: 11531–11539. https://doi.org/10.1109/CVPR42....
42.
Rahman M M, Munir M, Marculescu R. EMCAD: Efficient multi-scale convolutional attention decoding for medical image segmentation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, 2024: 11769–11779.
43.
Adekunle A A, Fofana Issouf, Picher P, Rodriguez-Celis E M, Arroyo-Fernandez O H and Zemouri R. Optimizing deep learning predictive models: A comprehensive review of RNN and its variant architectures. Applied Soft Computing 2025; 185: 114015. https://doi.org/10.1016/j.asoc....
44.
Tang H, Zu X, Guo Y, Jiang X, Wang J, Lin R, Xue H, Wang H. A novel incremental method with dynamic learnable pruning mechanism for low-speed machinery fault diagnosis. Engineering Applications of Artificial Intelligence 2026; 166: 113562. https://doi.org/10.1016/j.enga....
45.
Xiang L, Bing H, Li X, Hu A. A frequency channel-attention based vision transformer method for bearing fault identification across different working conditions. Expert Systems with Applications 2025; 262: 125686. https://doi.org/10.1016/j.eswa....
46.
Ma Y, Wen G, Cheng S, He X and Mei S. Multimodal convolutional neural network model with information fusion for intelligent fault diagnosis in rotating machinery. Measurement Science and Technology 2022; 33(12): 125109. https://doi.org/10.1088/1361-6....
Share
RELATED ARTICLE
| eISSN: | 2956-3860 |
| ISSN: | 1507-2711 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
