Journal of applied mathematics & informatics

  • 제41권6호
  • /
  • Pages.1257-1274
  • /
  • 2023
  • /
  • 2734-1194(pISSN)
  • /
  • 2234-8417(eISSN)
한국전산응용수학회 (The Korean Society for Computational and Applied Mathematics)
권호 표지
DOI QR코드

DOI QR Code

FAULT DIAGNOSIS OF ROLLING BEARINGS USING UNSUPERVISED DYNAMIC TIME WARPING-AIDED ARTIFICIAL IMMUNE SYSTEM

  • LUCAS VERONEZ GOULART FERREIRA (UNESP - Univ. Estadual Paulista, Faculty of Engineering of Ilha Solteira, Department of Mechanical Engineering) ;
  • LAXMI RATHOUR (Department of Mathematics, National Institute of Technology) ;
  • DEVIKA DABKE (Department of Mathematics, Block no. D-11, Central University of Karnataka) ;
  • FABIO ROBERTO CHAVARETTE (UNESP-Univ. Estadual Paulista, Institute of Chemistry, Department of Engineering, Physics and Mathematics) ;
  • VISHNU NARAYAN MISHRA (Department of Mathematics, Indira Gandhi National Tribal University)
  • 투고 : 2022.12.13
  • 심사 : 2023.09.12
  • 발행 : 2023.11.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Rotating machines heavily rely on an intricate network of interconnected sub-components, with bearing failures accounting for a substantial proportion (40% to 90%) of all such failures. To address this issue, intelligent algorithms have been developed to evaluate vibrational signals and accurately detect faults, thereby reducing the reliance on expert knowledge and lowering maintenance costs. Within the field of machine learning, Artificial Immune Systems (AIS) have exhibited notable potential, with applications ranging from malware detection in computer systems to fault detection in bearings, which is the primary focus of this study. In pursuit of this objective, we propose a novel procedure for detecting novel instances of anomalies in varying operating conditions, utilizing only the signals derived from the healthy state of the analyzed machine. Our approach incorporates AIS augmented by Dynamic Time Warping (DTW). The experimental outcomes demonstrate that the AIS-DTW method yields a considerable improvement in anomaly detection rates (up to 53.83%) compared to the conventional AIS. In summary, our findings indicate that our method represents a significant advancement in enhancing the resilience of AIS-based novelty detection, thereby bolstering the reliability of rotating machines and reducing the need for expertise in bearing fault detection.

키워드

과제정보

The authors are very grateful to The Sao Paulo Research Foundation (FAPESP) for the preparation of this work, through Process 2022/10599-6. As well, the authors would like to thank the Universidade Estadual Paulista "Julio de Mesquita Filho" and the Laboratory of Complex Systems (SisPLEXOS) for the space provided, without which it would not be possible to prepare the work.

참고문헌

  1. A. Abid, M.T. Khan and M.S. Khan, Multidomain Features-Based GA Optimized Artificial Immune System for Bearing Fault Detection, IEEE Transactions On Systems, Man, And Cybernetics: Systems 50 (2020), 348-359. https://doi.org/10.1109/TSMC.2017.2746762
  2. N. Bayar, S. Darmoul, S. Hajri-Gabouj and H. Pierreval, Fault detection, diagnosis and recovery using Artificial Immune Systems: a review, Engineering Applications Of Artificial Intelligence 46 (2015), 43-57. https://doi.org/10.1016/j.engappai.2015.08.006
  3. F. Castellani, L. Garibaldi, A.P. Daga, D. Astolfi and F. Natili, Diagnosis of Faulty Wind Turbine Bearings Using Tower Vibration Measurements, Energies 13-6 (2020), 1474.
  4. P. Saurabh and B. Verma, Negative selection in anomaly detection-A survey, Computer Science Review 48 (2023), 100557.
  5. A.P. Daga, A. Fasana, S. Marchesiello and L. Garibaldi, The Politecnico di Torino rolling bearing test rig: description and analysis of open access data, Mechanical Systems And Signal Processing 120 (2019), 252-273. https://doi.org/10.1016/j.ymssp.2018.10.010
  6. Y. Dai and J. Zhao, Fault Diagnosis of Batch Chemical Processes Using a Dynamic Time Warping (DTW)-Based Artificial Immune System, Industrial & Engineering Chemistry Research 8 (2011), 4534-4544.
  7. D. Dasgupta and S. Forrest Novelty Detection in Time Series Data Using Ideas from Immunology, In: Proceedings of the Fifth International Conference on Intelligent Systems 1994.
  8. C.R. Farrar, Structural Health Monitoring: a machine learning perspective, John Wiley & Sons, 2013.
  9. S. Forrest, A.S. Perelson, L. Allen and R. Cherukuri, Self-nonself discrimination in a computer, In: Proceedings of 1994 IEEE Computer Society Symposium On Research In Security And Privacy, 1994.
  10. J. G'orski, A. Jab lo'nski, M. Heesch, M. Dziendzikowski and Z. Dworakowski, Comparison of Novelty Detection Methods for Detection of Various Rotary Machinery Faults, Sensors 21-10 (2021), 3535.
  11. T. Han, X. Liu and A.C.C. Tan, Fault diagnosis of rolling element bearings based on Multi-scale Dynamic Time Warping, Measurement 95 (2017), 355-366. https://doi.org/10.1016/j.measurement.2016.10.038
  12. X. Sun, H. Wang, S. Liu, H. Xiao and L. Wang, Continual learning fault diagnosis method based on grid-based artificial immune system, Measurement Science and Technology 33-11 (2022), 115004.
  13. A. Althubaiti, F. Elasha and J.A. Teixeira, Fault diagnosis and health management of bearings in rotating equipment based on vibration analysis - a review, 24-1 (2021), 46-74. https://doi.org/10.21595/jve.2021.22100
  14. Q. Jiang and F.A. Chang, A novel antibody population optimization based artificial immune sys-tem for rotating equipment anomaly detection, Journal Of Mechanical Science And Technology 34-9 (2020), 3565-3574. https://doi.org/10.1007/s12206-020-0808-x
  15. Y. Lei, B. Yang, X. Jiang, F. Jia, N. Li, and A.K. Nandi, Applications of machine learning to machine fault diagnosis: a review and roadmap, Mechanical Systems And Signal Processing 138 (2020), 106587.
  16. F.P.A. Lima, F.R. Chavarette, S.S.F. Souza and M.L.M. Lopes, Monitoring and Fault Identification in Aeronautical Structures Using an Wavelet-Artificial Immune System Algorithm, Probabilistic Prognostics And Health Management Of Energy Systems (2017), 203-219.
  17. L. Montechiesi, M. Cocconcelli and R. Rubini, Artificial immune system via Euclidean Dis-tance Minimization for anomaly detection in bearings, Mechanical Systems And Signal Processing 76-77 (2016), 380-393. https://doi.org/10.1016/j.ymssp.2015.04.017
  18. R. Outa, F.R. Chavarette, P.F. Toro, A.C. Gon,calves and L.H. Santos, Prognosis and Detection of Experimental Failures in Open Field Diesel Engines Applying Wiener's Artificial Immunological Systems, Journal of Applied And Computational Mechanics 7-1 (2020), 1-12.
  19. R. Outa, F.R. Chavarette, A.C. Goncalves, S.L. Silva, V.N. Mishra, A.R. Panosso and L.N. Mishra, Reliability Analysis Using Experimental Statistical Methods And Artificial Immune Systems: Application In Continuous Flow Tubes Of Gaseous Medium, Acta Scientiarum-Technology 43-1 (2021), e55825.
  20. B. Pang, T. Tian and G. Tang, Fault state recognition of wind turbine gearbox based on generalized multi-scale dynamic time warping, Structural Health Monitoring 6-20 (2020), 3007-3023. https://doi.org/10.1177/1475921720978622
  21. M.R. Shahriar, P. Borghesani and A.C.C. Tan, Electrical Signature Analysis-Based Detection of External Bearing Faults in Electromechanical Drivetrains, IEEE Transactions On Industrial Electronics 65-7 (2018), 5941-5950. https://doi.org/10.1109/TIE.2017.2782240
  22. H. Shao, M. Xia, G. Han, Y. Zhang and J. Wan, Intelligent Fault Diagnosis of Rotor-Bearing System Under Varying Working Conditions With Modified Transfer Convolutional Neural Network and Thermal Images, IEEE Transactions On Industrial Electronics 17-5 (2021), 3488-3496. https://doi.org/10.1109/TII.2020.3005965
  23. L. Tarassenko, A. Nairac, N. Townsend, I. Buxton and P. Cowley, Novelty detection for the identification of abnormalities, International Journal Of Systems Science 31-11 (2020), 1427-1439. https://doi.org/10.1080/00207720050197802
  24. S. Tyagi and S.K. Panigrahi, A DWT and SVM based method for rolling element bearing fault diagnosis and its comparison with Artificial Neural Networks, Journal Of Applied And Computational Mechanics 3-1 (2017), 80-91.
  25. X. Zhao, J. Cheng, P. Wang, Z. He, H. Shao and Y. Yang, A novelty detection scheme for rolling bearing based on multiscale fuzzy distribution entropy and hybrid kernel convex hull approximation, Measurement 156 (2020), 107589.