Diagnosis of bearing faults in wind turbine systems using vibrational signal processing and machine learning

• Autorzy: Lakikza Abderrahmane , Cheghib Hocine , Kahoul Nabil

Identyfikatory

DOI

10.29354/diag/191393

• Języki publikacji: EN

Abstrakty

EN

This study employs an integrated methodology for the analysis and diagnosis of bearing faults in rotating machinery and wind turbine systems. The methodology begins by analyzing the original signal using Variational Mode Decomposition to extract distinct modes. Subsequently, the envelope is derived from the optimal mode and transformed into the frequency domain using Fast Fourier Transform to compute the envelope spectrum. The spectrum is segmented into specific frequency bands, and the energy within each band is quantified as features for training a K Nearest Neighbors classification model. The dataset is partitioned into training and testing subsets using cross-validation, and model performance is assessed using metrics such as accuracy and F1 score to ensure robust diagnostic capabilities. Comparative analysis of frequency spectra from real wind turbine signals highlights improvements in energy localization and distribution post-envelope processing. The proposed methodology is then applied to classify faults using the Case Western Reserve University dataset, demonstrating significant enhancements in diagnostic accuracy. These findings underscore the efficacy of the methodology in advancing fault diagnosis in complex machinery systems.

Słowa kluczowe

EN

wind turbine bearing fault; diagnosis; vibrational signal processing; K-Nearest Neighbors

• Wydawca: Polskie Towarzystwo Diagnostyki Technicznej
• Czasopismo: Diagnostyka
• Rocznik: 2024
• Tom: Vol. 25, No. 3
• Strony: art. no. 2024307
• Opis fizyczny: Bibliogr. 33 poz., rys., tab.

Twórcy

autor

Lakikza Abderrahmane

• Electromechanical Systems Laboratory, Badji Mokhtar-Annaba University, Algeria

• https://orcid.org/0009-0000-1238-3609

autor

Cheghib Hocine

• Electromechanical Systems Laboratory, Badji Mokhtar-Annaba University, Algeria

• https://orcid.org/0000-0002-1737-8099

autor

Kahoul Nabil

• Electromechanical Systems Laboratory, Badji Mokhtar-Annaba University, Algeria

• https://orcid.org/0000-0002-7156-727X

Bibliografia

• 1. Adlen K, Ridha K. Recurrent neural network optimization for wind turbine condition prognosis. Diagnostyka 2022; 23(3): 1-11. https://doi.org/10.29354/diag/151608.
• 2. An G, Tong Q, Zhang Y, Liu R, Li W, Cao J, et al. An improved variational mode decomposition and its application on fault feature extraction of rolling element bearing. Energies 2021; 14(4): 1079. https://doi.org/10.3390/en14041079.
• 3. Lu B, Li Y, Wu X, Yang Z. A review of recent advances in wind turbine condition monitoring and fault diagnosis. 2009 IEEE Power Electronics and Machines in Wind Applications 2009; 1-7. https://doi.org/10.1109/PEMWA.2009.5208325.
• 4. Bakir T, Boussaid B, Hamdaoui R, Abdelkrim MN, Aubrun C. Fault detection in wind turbine system using wavelet transform: Multi-resolution analysis. 2015 IEEE 12th International Multi-Conference on Systems, Signals & Devices (SSD15) 2015; 1-6. https://doi.org/10.1109/SSD.2015.7348223.
• 5. Bechhoefer E, Van Hecke B, He D. Processing for improved spectral analysis. Annual Conference of the PHM Society 2013; 5(1) https://doi.org/10.36001/phmconf.2013.v5i1.2220.
• 6. Bouaouiche K, Menasria Y, Khalfa D. Detection of defects in a bearing by analysis of vibration signals. Diagnostyka 2023; 24(2): 1-7. https://doi.org/10.29354/diag/162230.
• 7. CWRU. Vibration Database. Case Western Reserve University, 2023. https://engineering.case.edu/bearingdatacenter/downl oad-data-file.
• 8. Djemili I, Medoued A, Soufi Y. A wind turbine bearing fault detection method based on improved CEEMDAN and AR-MEDA. Journal of Vibration Engineering & Technologies 2024; 12(3): 4225-46. https://doi.org/10.1007/s42417-023-01117-x.
• 9. Encalada-Dávila Á, Puruncajas B, Tutivén C, Vidal Y. Wind turbine main bearing fault prognosis based solely on SCADA Data. Sensors 2021; 21(6): 2228. https://doi.org/10.3390/s21062228.
• 10. Gao Z, Liu X. An Overview on fault diagnosis, prognosis and resilient control for wind turbine systems. Processes 2021;9(2):300. https://doi.org/10.3390/pr9020300.
• 11. Leite GDNP, Araújo AM, Rosas PAC, Stosic T, Stosic B. Entropy measures for early detection of bearing faults. Physica A: Statistical Mechanics and its Applications 2019; 514: 458-72. https://doi.org/10.1016/j.physa.2018.09.052.
• 12. Gu H, Liu WY, Gao QW, Zhang Y. A review on wind turbines gearbox fault diagnosis methods. Journal of Vibroengineering 2021; 23(1): 26-43. https://doi.org/10.21595/jve.2020.20178.
• 13. Wang J, Qiao L, Ye Y, Chen Y. Fractional envelope analysis for rolling element bearing weak fault feature extraction. IEEE/CAA Journal of Automatica Sinica 2017; 4(2): 353-60. https://doi.org/10.1109/JAS.2016.7510166.
• 14. Bouaouiche K, Menasria Y, Khalfa D. Detection and diagnosis of bearing defects using vibration signal processing. Archive of Mechanical Engineering 2023: 433-52. https://doi.org/10.24425/ame.2023.146849.
• 15. Malik H. Wavelet and Hilbert Huang transform based wind turbine imbalance fault classification model using k-nearest neighbour algorithm. International Journal of Renewable Energy Technology 2018; 9(1/2):66. https://doi.org/10.1504/IJRET.2018.090105.
• 16. Xiao M, Wen K, Zhang C, Zhao X, Wei W, Wu D. Research on fault feature extraction method of rolling bearing based on NMD and wavelet threshold denoising. Shock and Vibration. 2018(1): 9495265. https://doi.org/10.1155/2018/9495265.
• 17. Meng D, Wang H, Yang S, Lv Z, Hu Z, Wang Z. Fault analysis of wind power rolling bearing based on EMD feature extraction. Computer Modeling in Engineering & Sciences 2022;130(1):543-58. https://doi.org/10.32604/cmes.2022.018123.
• 18. Niesłony A, Böhm M, Owsiński R. Crest factor and kurtosis parameter under vibrational random loading. International Journal of Fatigue 2021; 147: 106179. https://doi.org/10.1016/j.ijfatigue.2021.106179.
• 19. Olabi AG, Wilberforce T, Elsaid K, Sayed ET, Salameh T, Abdelkareem MA, et al. A Review on failure modes of wind turbine components. Energies 2021; 14(17): 5241. https://doi.org/10.3390/en14175241.
• 20. Peng H, Zhang H, Fan Y, Shangguan L, Yang Y. A review of research on wind turbine bearings’ failure analysis and fault diagnosis. Lubricants 2022; 11(1):14. https://doi.org/10.3390/lubricants11010014.
• 21. Lu Q, Shen X, Wang X, Li M, Li J, Zhang M. Fault diagnosis of rolling bearing based on improved VMD and KNN. Mathematical Problems in Engineering. 2021; 2021: 1-11. https://doi.org/10.1155/2021/2530315.
• 22. Ahmed SD, Al-Ismail FSM, Shafiullah M, AlSulaiman FA, El-Amin IM. Grid integration challenges of wind energy: A Review. IEEE Access 2020; 8: 10857-78. https://doi.org/10.1109/ACCESS.2020.2964896.
• 23. Shen W, Xiao M, Wang Z, Song X. Rolling bearing fault diagnosis based on support vector machine optimized by improved grey Wolf algorithm. Sensors 2023; 23(14): 6645. https://doi.org/10.3390/s23146645.
• 24. Strömbergsson D, Marklund P, Berglund K, Larsson P. Bearing monitoring in the wind turbine drivetrain: A comparative study of the FFT and wavelet transforms. Wind Energy 2020; 23(6): 1381-93. https://doi.org/10.1002/we.2491.
• 25. The data is available on this website: https://github.com/mathworks/WindTurbineHighSpee dBearingPrognosis-Data.
• 26. Liu WY, Tang BP, Han JG, Lu XN, Hu NN, He ZZ. The structure healthy condition monitoring and fault diagnosis methods in wind turbines: A review. Renewable and Sustainable Energy Reviews 2015; 44: 466-72. https://doi.org/10.1016/j.rser.2014.12.005.
• 27. Wang X, Ruan J, Zhou T, Peng X, Deng Y, Yang Q. Data mining in the vibration signal of the trip mechanism in circuit breakers based on VMD-PSR. Electronics 2022; 11(22): 3700. https://doi.org/10.3390/electronics11223700.
• 28. Gong X, Qiao W. Bearing fault detection for directdrive wind turbines via stator current spectrum analysis. 2011 IEEE Energy Conversion Congress and Exposition, Phoenix, AZ, USA, 2011; 313-318. https://doi.org/10.1049/iet-rpg.2012.0278.
• 29. Zhang Y, Zhang C, Liu , Wang W, Han Y, Wu N. Fault diagnosis method of wind turbine bearing based on improved intrinsic time-scale decomposition and spectral Kurtosis. 2019 Eleventh International Conference on Advanced Computational Intelligence (ICACI), Guilin, China, 2019;29-34. https://doi.org/10.1109/TEC.2012.2227746.
• 30. Yang J, Zhou C, Li X. Research on fault feature extraction method based on parameter optimized variational mode decomposition and robust independent component analysis. Coatings 2022; 12(3): 419. https://doi.org/10.3390/coatings12030419.
• 31. Yang J, Zhou C, Li X, Pan A, Yang T. A fault feature extraction method based on improved VMD multiscale dispersion entropy and TVD-CYCBD. Entropy 2023;25(2):277. https://doi.org/10.3390/e25020277.
• 32. Zhang F, Chen M, Zhu Y, Zhang K, Li Q. A Review of fault diagnosis, status prediction, and evaluation technology for wind turbines. Energies 2023; 16(3): 1125. https://doi.org/10.3390/en16031125.
• 33. Zhao H, Li L. Fault diagnosis of wind turbine bearing based on variational mode decomposition and Teager energy operator. IET Renewable Power Generation 2017; 11(4): 453-60. https://doi.org/10.1049/ietrpg.2016.0070.