Autors: Orhan A., Yordanov N., Ertarğın M., Zhilevski, M. M., Mikhov, M. R.
Title: A Comparative Study of Time–Frequency Representations for Bearing and Rotating Fault Diagnosis Using Vision Transformer
Keywords: bearing fault classification, continuous wavelet transform, Hilbert–Huang transform, rotating component fault classification, short-time Fourier transform, vision transformer, Wigner–Ville distributio

Abstract: This paper presents a comparative analysis of bearing and rotating component fault classification based on different time–frequency representations using vision transformer (ViT). Four different time–frequency transformation techniques—short-time Fourier transform (STFT), continuous wavelet transform (CWT), Hilbert–Huang transform (HHT), and Wigner–Ville distribution (WVD)—were applied to convert the signals into 2D images. A pretrained ViT-Base architecture was fine-tuned on the resulting images for classification tasks. The model was evaluated on two separate scenarios: (i) eight-class rotating component fault classification and (ii) four-class bearing fault classification. Importantly, in each task, the samples were collected under varying conditions of the other component (i.e., different rotating conditions in bearing classification and vice versa). This design allowed for an independent assessment of the model’s ability to generalize across fault domains. The experimental results demonstrate that the ViT-based approach achieves high classification performance across various time–frequency representations, highlighting its potential for mechanical fault diagnosis in rotating machinery. Notably, the model achieved higher accuracy in bearing fault classification compared to rotating component faults, suggesting higher sensitivity to bearing-related anomalies.

References

  1. Zhang Q. Deng L. An Intelligent Fault Diagnosis Method of Rolling Bearings Based on Short-Time Fourier Transform and Convolutional Neural Network J. Fail. Anal. Prev. 2023 23 795 811 10.1007/s11668-023-01616-9
  2. Zhong D. Guo W. He D. An Intelligent Fault Diagnosis Method based on STFT and Convolutional Neural Network for Bearings Under Variable Working Conditions Proceedings of the 2019 Prognostics and System Health Management Conference (PHM-Qingdao) Qingdao, China 25–27 October 2019 1 6 10.1109/PHM-Qingdao46334.2019.8943026
  3. Peng B. Xia H. Lv X. Annor-Nyarko M. Zhu S. Liu Y. Zhang J. An intelligent fault diagnosis method for rotating machinery based on data fusion and deep residual neural network Appl. Intell. 2022 52 3051 3065 10.1007/s10489-021-02555-4
  4. He M. He D. Deep learning based approach for bearing fault diagnosis IEEE Trans. Ind. Appl. 2017 53 3057 3065 10.1109/TIA.2017.2661250
  5. Tao H. Wang P. Chen Y. Stojanovic V. Yang H. An unsupervised fault diagnosis method for rolling bearing using STFT and generative neural networks J. Frankl. Inst. 2020 357 7286 7307 10.1016/j.jfranklin.2020.04.024
  6. Zhang Y. Xing K. Bai R. Sun D. Meng Z. An enhanced convolutional neural network for bearing fault diagnosis based on time–frequency image Measurement 2020 157 107667 10.1016/j.measurement.2020.107667
  7. Liu H. Li L. Ma J. Rolling bearing fault diagnosis based on STFT-deep learning and sound signals Shock Vib. 2016 2016 6127479 10.1155/2016/6127479
  8. Cheng Y. Lin M. Wu J. Zhu H. Shao X. Intelligent fault diagnosis of rotating machinery based on continuous wavelet transform-local binary convolutional neural network Knowl.-Based Syst. 2021 216 106796 10.1016/j.knosys.2021.106796
  9. Xu Y. Li Z. Wang S. Li W. Sarkodie-Gyan T. Feng S. A hybrid deep-learning model for fault diagnosis of rolling bearings Measurement 2021 169 108502 10.1016/j.measurement.2020.108502
  10. Mian T. Choudhary A. Fatima S. Vibration and infrared thermography based multiple fault diagnosis of bearing using deep learning Nondestruct. Test. Eval. 2023 38 275 296 10.1080/10589759.2022.2118747
  11. Zhao H. Liu J. Chen H. Chen J. Li Y. Xu J. Deng W. Intelligent diagnosis using continuous wavelet transform and gauss convolutional deep belief network IEEE Trans. Reliab. 2022 72 692 702 10.1109/TR.2022.3180273
  12. Ahsan M. Hassan M.W. Rodriguez J. Abdelrahem M. Enhanced Fault Diagnosis in Rotating Machinery Using a Hybrid CWT-LeNet-5-LSTM Model: Performance Across Various Load Conditions IEEE Access 2024 13 1026 1045 10.1109/ACCESS.2024.3522948
  13. Yu S. Li Z. Gu J. Wang R. Liu X. Li L. Guo F. Ren Y. CWMS-GAN: A small-sample bearing fault diagnosis method based on continuous wavelet transform and multi-size kernel attention mechanism PLoS ONE 2025 20 e0319202 10.1371/journal.pone.0319202
  14. Liu H. Wang X. Lu C. Rolling Bearing Fault Diagnosis under Variable Conditions Using Hilbert-Huang Transform and Singular Value Decomposition Math. Probl. Eng. 2014 2014 765621 10.1155/2014/765621
  15. Suthar V. Vakharia V. Patel V.K. Shah M. Detection of compound faults in ball bearings using multiscale-SinGAN, heat transfer search optimization, and extreme learning machine Machines 2022 11 29 10.3390/machines11010029
  16. Lin S.L. Intelligent fault diagnosis and forecast of time-varying bearing based on deep learning VMD-DenseNet Sensors 2021 21 7467 10.3390/s21227467
  17. Wei P. Liu M. Wang X. Few-shot bearing fault diagnosis using GAVMD–PWVD time–frequency image based on meta-transfer learning J. Braz. Soc. Mech. Sci. Eng. 2023 45 277 10.1007/s40430-023-04202-0
  18. Hua L. Qiang Y. Gu J. Chen L. Zhang X. Zhu H. Mechanical fault diagnosis using color image recognition of vibration spectrogram based on quaternion invariable moment Math. Probl. Eng. 2015 2015 702760 10.1155/2015/702760
  19. Li X. Bi F. Zhang L. Lin J. Bi X. Yang X. Rotating machinery faults detection method based on deep echo state network Appl. Soft Comput. 2022 127 109335 10.1016/j.asoc.2022.109335
  20. Mo C. Huang K. Ji H. Li W. Xu K. Efficient intelligent fault diagnosis method and graphical user interface development based on fusion of convolutional networks and vision transformers characteristics Sci. Rep. 2025 15 7110 10.1038/s41598-025-88668-z 40016236
  21. Ren S. Lou X. Rolling Bearing Fault Diagnosis Method Based on SWT and Improved Vision Transformer Sensors 2025 25 2090 10.3390/s25072090 40218603
  22. Tang X. Xu Z. Wang Z. A Novel Fault Diagnosis Method of Rolling Bearing Based on Integrated Vision Transformer Model Sensors 2022 22 3878 10.3390/s22103878
  23. Zhang S. Zhou J. Ma X. Pirttikangas S. Yang C. TSViT: A Time Series Vision Transformer for Fault Diagnosis of Rotating Machinery Appl. Sci. 2024 14 10781 10.3390/app142310781
  24. He Q. Li S. Bai Q. Zhang A. Yang J. Shen M. A Siamese Vision Transformer for Bearings Fault Diagnosis Micromachines 2022 13 1656 10.3390/mi13101656
  25. Allen J. Short term spectral analysis, synthesis, and modification by discrete Fourier transform IEEE Trans. Acoust. Speech Signal Process. 1977 25 235 238 10.1109/TASSP.1977.1162950
  26. Gabor D. Theory of communication. Part 1: The analysis of information J. Inst. Electr. Eng.-Part III Radio Commun. Eng. 1946 93 429 441 10.1049/ji-3-2.1946.0074
  27. Ville J. Theorie et Applications de la Notion de Signal Analytique Cables Transm. 1948 2A 61 74
  28. “Apparatus & Procedures | Case School of Engineering” Available online: https://engineering.case.edu/bearingdatacenter/apparatus-and-procedures (accessed on 1 July 2025)
  29. Bechhoefer E. A Quick Introduction to Bearing Envelope Analysis, MFPT Data Available online: www.mfpt.org/fault-data-sets (accessed on 1 July 2025)
  30. Lessmeier C. Kimotho J.K. Zimmer D. Sextro W. Condition monitoring of bearing damage in electromechanical drive systems by using motor current signals of electric motors: A benchmark data set for data-driven classification PHM Soc. Eur. Conf. 2016 3 1 10.36001/phme.2016.v3i1.1577
  31. Graps A. An introduction to wavelets IEEE Comput. Sci. Eng. 1995 2 50 61 10.1109/99.388960
  32. Polikar R. Mastorakis N. The story of wavelets inPhysics and modern topics in mechanical and electrical engineering World Sci. Eng. Soc. Press 1999 192 197
  33. Huang N.E. Shen Z. Long S.R. Wu M.C. Shih H.H. Zheng Q. Yen N.-C. Tungand C.C. Liu H.H. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis Proc. R. Soc. Lond. Ser. A Math. Phys. Eng. Sci. 1998 454 903 995 10.1098/rspa.1998.0193
  34. Huang H. Baddour N. Bearing vibration data collected under time-varying rotational speed conditions Data Brief 2018 21 1745 1749 10.1016/j.dib.2018.11.019 30505910
  35. Boashash B. Time-Frequency Signal Analysis and Processing: A Comprehensive Reference Academic Press Cambridge, MA, USA 2015
  36. Lee S. Kim T. Kim T. Multi-domain vibration dataset with various bearing types under compound machine fault scenarios: Subset 1 (deep groove ball bearing) Mendeley Data 2024 57 110640 10.17632/53vtnjy6c6.1
  37. Lee S. Kim T. Kim T. Multi-domain vibration dataset with various bearing types under compound machine fault scenarios Data Brief 2024 57 110940 10.1016/j.dib.2024.110940
  38. SciPy Documentation—Scipy.signal.spectrogram Available online: https://docs.scipy.org/doc/scipy/reference/generated/scipy.signal.spectrogram.html (accessed on 12 August 2025)
  39. Jabloun M. Empirical mode decomposition revisited using ordinal pattern concepts Proceedings of the 2022 30th European Signal Processing Conference (EUSIPCO) Belgrade, Serbia 29 August–2 September 2022 2186 2190
  40. Tsai C.W. Hsiao Y.R. Lin M.L. Hsu Y. Development of a noise-assisted multivariate empirical mode decomposition framework for characterizing PM 2.5 air pollution in Taiwan and its relation to hydro-meteorological factors Environ. Int. 2020 139 105669 10.1016/j.envint.2020.105669
  41. Stallone A. Cicone A. Materassi M. New insights and best practices for the successful use of empirical mode decomposition, iterative filtering and derived algorithms Sci. Rep. 2020 10 15161 10.1038/s41598-020-72193-2
  42. Yu L. Bearing fault diagnosis using time-frequency synchrosqueezing transform Proceedings of the 2020 Chinese Automation Congress (CAC) Shanghai, China 6–8 November 2020 4260 4264
  43. Wang Z. Xu Z. Cai C. Wang X. Xu J. Shi K. Zhong X. Liao Z. Li Q. Rolling bearing fault diagnosis method using time-frequency information integration and multi-scale TransFusion network Knowl.-Based Syst. 2024 284 111344 10.1016/j.knosys.2023.111344
  44. Verstraete D. Ferrada A. Droguett E.L. Meruane V. Modarres M. Deep learning enabled fault diagnosis using time-frequency image analysis of rolling element bearings Shock Vib. 2017 2017 5067651 10.1155/2017/5067651

Issue

Machines, vol. 13, pp. 1-21, 2025, Switzerland, https://doi.org/10.3390/machines13080737

Copyright MDPI

Цитирания (Citation/s):
1. Lu, NW, Xiao, XY, Cui, J, Liu, YR, Huang, K, Yuen, K, An unsupervised cross-domain method for bridge damage detection based on multichannel symmetric dot pattern feature alignment, COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING, 2025, issn: 1093-9687, eissn: 1467-8667, doi: 10.1111/mice.70117 - 2025 - в издания, индексирани в Scopus и/или Web of Science
2. Chaouech, L, Ben Ali, J, Berghout, T, Bechhoefer, E, Chaari, A, BSEMD-Transformer: A New Framework for Rolling Element Bearing Diagnosis in Electrical Machines Based on Classification of Time-Frequency Features, MACHINES, vol 13, 2025, eissn: 2075-1702, art_no: ARTN 961, doi: 10.3390/machines13100961 - 2025 - в издания, индексирани в Scopus и/или Web of Science
3. Volkov O., Bushma O., Sieriebriakov A., Taranukha V., Linder Y., Compact Acoustic Signal Portraits for Resource-Efficient Mechanical Fault Detection, 2026, Electronics Letters, issue 1, vol. 62, DOI 10.1049/ell2.70551, issn 00135194, eissn 1350911X - 2026 - в издания, индексирани в Scopus и/или Web of Science
4. Zhou J., Han R., Simultaneous estimation of fault type and severity in rolling bearings via multichannel measurement data fusion and a physics-informed measurement model, 2026, Measurement Journal of the International Measurement Confederation, issue 0, vol. 272, DOI 10.1016/j.measurement.2026.121095, issn 02632241 - 2026 - в издания, индексирани в Scopus и/или Web of Science
5. Qi X., Zhang H., Liu T., Zan Y., Zhang H., Tian G., A lightweight fault diagnosis method for rolling bearings based on optical signals and image modeling, 2026, Proceedings of SPIE the International Society for Optical Engineering, issue 0, vol. 14128, DOI 10.1117/12.3104214, issn 0277786X, eissn 1996756X - 2026 - в издания, индексирани в Scopus
6. Wei X., Research on intelligent diagnosis methods for transformer vibration signals combining CNN, 2026, Proceedings of SPIE the International Society for Optical Engineering, issue 0, vol. 14061, DOI 10.1117/12.3107952, issn 0277786X, eissn 1996756X - 2026 - в издания, индексирани в Scopus
7. Zhao, YC, Mao, ZJ, Acoustic-Vibration Fusion with Sparse Representation for Intelligent Fault Detection in Home Appliances, SENSORS AND MATERIALS, vol 38, 2026, issn: 0914-4935, doi: 10.18494/SAM6246 - 2026 - в издания, индексирани в Scopus и/или Web of Science
8. Shen, YJ, Cheng, S, Zhang, Y, Wen, XQ, Zhang, YY, Wang, JG, Multi-scale and multi-branch 1D-AM-CNN network for fault diagnosis based on Bayesian data fusion, WIND ENGINEERING, 2026, issn: 0309-524X, eissn: 2048-402X, doi: 10.1177/0309524X261436757 - 2026 - в издания, индексирани в Scopus и/или Web of Science
9. Sresakoolchai, J, Puttasrijaru, C, Predictive maintenance of railway suspension systems using multi-level time-frequency vibration analysis, DISCOVER APPLIED SCIENCES, vol 8, 2026, eissn: 3004-9261, art_no: ARTN 471, doi: 10.1007/s42452-026-08531-2 - 2026 - в издания, индексирани в Scopus и/или Web of Science
10. Dave, V, Vakharia, V, Karsh, PK, Dabhi, VM, Zalawadia, K, Generalized bearing fault diagnosis using comparative time-frequency scalogram features and machine learning with advanced feature ranking, INTERNATIONAL JOURNAL OF AUTOMOTIVE AND MECHANICAL ENGINEERING, vol 23, 2026, issn: 2229-8649, eissn: 2180-1606, doi: 10.15282/ijame.23.1.2026.20.1018 - 2026 - в издания, индексирани в Web of Science
11. Jing M., Jia G., Jiang Y., Shang X., Zhuang J., Six-Channel STFT-Difference Representation for Deep Learning-Based Inter-Turn Fault Diagnosis in PMSMs, 2025, Proceedings 2025 4th International Conference on Advanced Electronics Electrical and Green Energy Aeege 2025, issue 0, DOI 10.1109/AEEGE68222.2025.11473217 - 2026 - в издания, индексирани в Scopus
12. Chaudhary V., Mukherjee A., Mypati O., Pal S.K., A Domain-agnostic Vision Transformer Framework for Machinery Fault Diagnosis using Wavelet Time–frequency Spectra, 2026, Journal of Vibration Engineering and Technologies, issue 6, vol. 14, DOI 10.1007/s42417-026-02545-1, issn 25233920, eissn 25233939 - 2026 - в издания, индексирани в Scopus и/или Web of Science
13. Song B., Zhang L., Zhou F., Bi H., Few-shot bearing fault diagnosis: a transfer learning framework via time–frequency information fusion, 2026, Engineering Research Express, issue 12, vol. 8, DOI 10.1088/2631-8695/ae79db, eissn 26318695 - 2026 - в издания, индексирани в Scopus и/или Web of Science
14. Krishnendu K., Priya G.L., Pradhan P.M., Bearing Fault Diagnosis Using Teager Energy Concentrated Time-Frequency Transforms, 2026, IEEE Sensors Journal, issue 0, DOI 10.1109/JSEN.2026.3693294, issn 1530437X, eissn 15581748 - 2026 - в издания, индексирани в Scopus и/или Web of Science
15. Ewert, P, Wicher, B, Pajchrowski, T, Detection of Rotor Unbalance in Multi-Mass Systems Using FFT and Bispectrum, POWER ELECTRONICS AND DRIVES, vol 11, 2026, issn: 2451-0262, eissn: 2543-4292, doi: 10.2478/pead-2026-0019 - 2026 - в издания, индексирани в Scopus и/или Web of Science
16. Kaya S.M., Jobani A.E., IoT-Driven Robust Bearing Fault Diagnosis for Induction Motors Under Operating-Condition Shift, 2026, Sensors, issue 12, vol. 26, DOI 10.3390/s26123829, eissn 14248220 - 2026 - в издания, индексирани в Scopus и/или Web of Science
17. Sun J., Qian Z., Yuan X., Yu M., Xu W., Fu F., Fault Diagnosis of Spacecraft Attitude Control System Using STFT-Based RGB Representation and Vision Mamba, 2026, Proceedings of the 5th Conference on Fully Actuated System Theory and Applications Fasta 2026, issue 0, pp. 1129-1136, DOI 10.1109/FASTA70174.2026.11549130 - 2026 - в издания, индексирани в Scopus
18. Abubacker K.M., Rajakannu A., Wekalao J., Al Tobi M., Vishnupriyan S., Non-Stationary Airborne Acoustic Emission Analysis for CNC Drill Wear Classification Using Synchrosqueezed Wavelet Representation and Vision Transformer, 2026, International Journal of Engineering Trends and Technology, issue 6, vol. 74, pp. 231-243, DOI 10.14445/22315381/IJETT-V74I6P117, issn 23490918, eissn 22315381 - 2026 - в издания, индексирани в Scopus
19. Tsiafis C., David C., Korlos A., Operator-Centred Visualization of Rolling-Element Bearing Faults: A Comparison of the Zhao–Atlas–Marks Distribution and CEEMDAN, with a Non-Specialist Readability Assessment of the ZAMD-Based Framework, 2026, Eng, issue 7, vol. 7, DOI 10.3390/eng7070342, eissn 26734117 - 2026 - в издания, индексирани в Scopus и/или Web of Science
20. Savu A.-D., Bizon N., Dragusin S.-A., Low-Cost Embedded System for Acoustic Fault Detection, 2026, Proceedings of the 18th International Conference on Electronics Computers and Artificial Intelligence Ecai 2026, issue 0, DOI 10.1109/ECAI69016.2026.11613762 - 2026 - в издания, индексирани в Scopus
21. Kibrete F., Feisa T.T., Woldemichael D.E., Mekonnen B.G., Vibration-based condition monitoring and fault diagnosis of rotating machinery: Fundamentals, signal processing techniques, standards, and emerging trends, 2026, Results in Engineering, issue 0, vol. 32, DOI 10.1016/j.rineng.2026.112372, eissn 25901230 - 2026 - в издания, индексирани в Scopus и/или Web of Science
22. Zhang, JX, Shen, GX, Protocol and Implementation Sensitivity in Raw-Index-Audited Few-Shot Bearing Fault Diagnosis Benchmarking: Evidence from CWRU and HUSTbearing, MACHINES, vol 14, 2026, eissn: 2075-1702, art_no: ARTN 891, doi: 10.3390/machines14080891 - 2026 - в издания, индексирани в Scopus и/или Web of Science

Вид: статия в списание, публикация в издание с импакт фактор, публикация в реферирано издание, индексирана в Scopus и Web of Science