Smart Structures and Systems

  • 제29권4호
  • /
  • Pages.625-640
  • /
  • 2022
  • /
  • 1738-1584(pISSN)
  • /
  • 1738-1991(eISSN)
테크노프레스 (Techno-Press)
권호 표지
DOI QR코드

DOI QR Code

Multiple damage detection of maglev rail joints using time-frequency spectrogram and convolutional neural network

  • Wang, Su-Mei (Department of Civil and Environmental Engineering, The Hong Kong Polytechnic University) ;
  • Jiang, Gao-Feng (Department of Civil and Environmental Engineering, The Hong Kong Polytechnic University) ;
  • Ni, Yi-Qing (Department of Civil and Environmental Engineering, The Hong Kong Polytechnic University) ;
  • Lu, Yang (Department of Civil and Environmental Engineering, The Hong Kong Polytechnic University) ;
  • Lin, Guo-Bin (Shanghai Key Laboratory of Rail Infrastructure Durability and System Safety, Tongji University) ;
  • Pan, Hong-Liang (Maglev Transportation Engineering R&D Center, Tongji University) ;
  • Xu, Jun-Qi (Shanghai Key Laboratory of Rail Infrastructure Durability and System Safety, Tongji University) ;
  • Hao, Shuo (Department of Civil and Environmental Engineering, The Hong Kong Polytechnic University)
  • 투고 : 2021.06.27
  • 심사 : 2022.01.03
  • 발행 : 2022.04.25
⟨ 이전 논문 다음 논문 ⟩

초록

Maglev rail joints are vital components serving as connections between the adjacent F-type rail sections in maglev guideway. Damage to maglev rail joints such as bolt looseness may result in rough suspension gap fluctuation, failure of suspension control, and even sudden clash between the electromagnets and F-type rail. The condition monitoring of maglev rail joints is therefore highly desirable to maintain safe operation of maglev. In this connection, an online damage detection approach based on three-dimensional (3D) convolutional neural network (CNN) and time-frequency characterization is developed for simultaneous detection of multiple damage of maglev rail joints in this paper. The training and testing data used for condition evaluation of maglev rail joints consist of two months of acceleration recordings, which were acquired in-situ from different rail joints by an integrated online monitoring system during a maglev train running on a test line. Short-time Fourier transform (STFT) method is applied to transform the raw monitoring data into time-frequency spectrograms (TFS). Three CNN architectures, i.e., small-sized CNN (S-CNN), middle-sized CNN (M-CNN), and large-sized CNN (L-CNN), are configured for trial calculation and the M-CNN model with excellent prediction accuracy and high computational efficiency is finally optioned for multiple damage detection of maglev rail joints. Results show that the rail joints in three different conditions (bolt-looseness-caused rail step, misalignment-caused lateral dislocation, and normal condition) are successfully identified by the proposed approach, even when using data collected from rail joints from which no data were used in the CNN training. The capability of the proposed method is further examined by using the data collected after the loosed bolts have been replaced. In addition, by comparison with the results of CNN using frequency spectrum and traditional neural network using TFS, the proposed TFS-CNN framework is proven more accurate and robust for multiple damage detection of maglev rail joints.

키워드

과제정보

The research described in this paper was supported by a grant (RIF) from the Research Grants Council of the Hong Kong Special Administrative Region (SAR), China (Grant No. R-5020-18), a grant from the National Natural Science Foundation of China (Grant No. U1934209) and Wuyi University's Hong Kong and Macao Joint Research and Development Fund (Grants No. 2019WGALH15 and 2019WGALH17). The authors would also like to appreciate the funding support by the Innovation and Technology Commission of the Hong Kong SAR Government to the Hong Kong Branch of Chinese National Rail Transit Electrification and Automation Engineering Technology Research Center (Grant No. K-BBY1) and by the National Natural Science Foundation of China to the Maglev Transportation Engineering R&D Center (Grant No. 52072269).

참고문헌

  1. Abdeljaber, O., Avci, O., Kiranyaz, S., Gabbouj, M. and Inman, D.J. (2017), "Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks", J. Sound Vib., 388, 154-170. https://doi.org/10.1016/j.jsv.2016.10.043
  2. Alberts, T.E., Hanasoge, A.M. and Omran, A.M. (2011), "On the influence of structural flexibility on feedback control stability for magnetically suspended vehicles", J. Dyn. Syst. Measur. Control, 133(5), 051010. https://doi.org/10.1115/1.4003802
  3. Cha, Y.J., Choi, W., Suh, G., Mahmoudkhani, S. and Buyukozturk, O. (2017), "Autonomous structural visual inspection using region-based deep learning for detecting multiple damage types", Comput.-Aided Civil Infrastr. Eng., 33(9), 731-747. https://doi.org/10.1111/mice.12334
  4. Chen, J.W., Liu, Z.G., Wang, H.R., Nunez, A. and Han, Z.W. (2018), "Automatic defect detection of fasteners on the catenary support device using deep convolutional neural network", IEEE Transact. Instrument. Measur., 67(2), 257-269. https://doi.org/10.1109/TIM.2017.2775345
  5. Dangre, H. (2019), "A review on insulated rail joints (IRJ) failure analysis", Int. J. Adv. Res. Publicat., 3(1), 5-9.
  6. Deng, L., Chu, H.H., Shi, P., Wang, W. and Kong, X. (2020), "Region-based CNN method with deformable modules for visually classifying concrete cracks", Appl. Sci., 10(7), 2528. https://doi.org/10.3390/app10072528
  7. Duan, Y.F., Chen, Q.Y., Zhang, H.M., Yun, C.B., Wu, S.K. and Zhu, Q. (2019), "CNN-based damage identification method of tied-arch bridge using spatial-spectral information", Smart Struct. Syst., Int. J., 23(5), 507-520. https://doi.org/10.12989/sss.2019.23.5.507
  8. Dung, C.V., Sekiya, H., Hirano, S., Okatani, T. and Miki, C. (2019), "A vision-based method for crack detection in gusset plate welded joints of steel bridges using deep convolutional neural networks", Automat. Constr., 102, 217-229. https://doi.org/10.1016/j.autcon.2019.02.013
  9. Faghih-Roohi, S., Hajizadeh, S., Nunez, A., Babuska, R. and De Schutter, B. (2016), "Deep convolutional neural networks for detection of rail surface defects", Proceedings of 2016 International Joint Conference on Neural Networks (IJCNN), Vancouver, Canada, July.
  10. Feng, J., Li, F.M., Lu, S.X., Liu, J.H. and Ma, D.Z. (2017), "Injurious or noninjurious defect identification from MFL images in pipeline inspection using convolutional neural network", IEEE Transact. Instrument. Measur., 66(7), 1883-1892. https://doi.org/10.1109/TIM.2017.2673024
  11. Fujie, J. (1989), "Current status of EDS system in Japan", Proceedings of 11th International Conference on Magnetically Levitated Systems and Linear Drives, Yokohama, Japan, July.
  12. Gibert, X., Patel, V.M. and Chellappa, R. (2017), "Deep multitask learning for railway track inspection", IEEE Transact. Intell. Transport. Syst., 18(1), 153-164. https://doi.org/10.1109/TITS.2016.2568758
  13. Goodall, R.M. (2008), "Generalised design models for EMS maglev", Proceedings of 20th International Conference on Magnetically Levitated Systems and Linear Drives, San Diego, CA, USA, December.
  14. Huang, J.Y., Wu, Z.W., Shi, J., Gao, Y. and Wang, D.Z. (2018), "Influence of track irregularities in high-speed Maglev transportation systems", Smart Struct. Syst., Int. J., 21(5), 571-582. https://doi.org/10.12989/sss.2018.21.5.571
  15. Ioffe, S. and Szegedy, C. (2015), "Batch normalization: accelerating deep network training by reducing internal covariate shift", Proceedings of 32nd International Conference on Machine Learning, Lile, France, July.
  16. Kabo, E., Nielsen, J.C.O. and Ekberg, A. (2006), "Prediction of dynamic train-track interaction and subsequent material deterioration in the presence of insulated rail joints", Vehicle Syst. Dyn., 44, 718-729. https://doi.org/10.1080/00423110600885715
  17. Kim, K.J, Han, J.B., Han, H.S. and Yang, S.J. (2015), "Coupled vibration analysis of Maglev vehicle-guideway while standing still or moving at low speeds", Vehicle Syst. Dyn., 53(4) 587-601. http://dx.doi.org/10.1080/00423114.2015.1013039
  18. Kim, J.J., Kim, A.R. and Lee, S.W. (2020), "Artificial neural network-based automated crack detection and analysis for the inspection of concrete structures", Appl. Sci., 10(22), 8105. https://doi.org/10.3390/app10228105
  19. Kohavi, R. (1995), "A study of cross-validation and bootstrap for accuracy estimation and model selection", Proceedings of 14th International Joint Conference on Artificial Intelligence (IJCAI '95), San Francisco, CA, USA, August.
  20. Li, X.Y., Liu, Y.Z., Zhou, W.W. and Wu, J. (2015), "Research on the influence on running vehicle from non-coplanar disturbance of four magnetic pole surfaces of middle-low speed maglev train tracks", Proceedings of 2015 Seventh International Conference on Measuring Technology and Mechatronics Automation, Nanchang, China, June.
  21. Li, Y.J., Yu, P.C., Zhou, D.F. and Li, J. (2018), "Magnetic flux feedback strategy to suppress the gap fluctuation of low-speed maglev train caused by track steps", Proceedings of 37th Chinese Control Conference (CCC), Wuhan, China, July.
  22. Li, H.T., Xu, H.Y., Tian, X.D., Wang, Y., Cai, H.Y., Cui, K.R. and Chen, X.D. (2020a), "Bridge crack detection based on SSENets", Appl. Sci., 10(12), 4230. https://doi.org/10.3390/app10124230
  23. Li, X.Q., Zhai, M.D., Li, X.L. and Dong, W.H. (2020b), "Research on suppression strategy for track dislocation interference in medium-low speed maglev train", Proceedings of 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC), Chongqing, China, June.
  24. Lin, Y.Z., Nie, Z.H. and Ma, H.W. (2017), "Structural damage detection with automatic feature-extraction through deep learning", Comput.-Aided Civil Infrastr. Eng., 32(12), 1025-1046. https://doi.org/10.1111/mice.12313
  25. Luo, L.X., Feng, M.Q., Wu, J.P. and Leung, R.Y. (2019), "Autonomous pothole detection using deep region-based convolutional neural network with cloud computing", Smart Struct. Syst., Int. J., 24(6), 745-757. https://doi.org/10.12989/sss.2019.24.6.745
  26. Ma, Z.R., Gao, L., Zhong, Y.L., Ma, S. and An, B.L. (2020), "Arching detection method of slab track in high-speed railway based on track geometry data", Appl. Sci., 10(19), 6799. https://doi.org/10.3390/app10196799
  27. Masada, E. (1993), "Development of maglev transportation in Japan: present state and future prospects", Proceedings of 13th International Conference on Magnetically Levitated Systems and Linear Drives, Argonne, IL, USA, May.
  28. Marino, F., Distante, A., Mazzeo, P.L. and Stella, E. (2007), "A real-time visual inspection system for railway maintenance: automatic hexagonal-headed bolts detection", IEEE Transact. Syst. Man Cybernet. Part C (Applications and Reviews), 37(3), 418-428. https://doi.org/10.1109/TSMCC.2007.893278
  29. Ohtsuka, T. and Iguchi, M. (1982), "Maglev dynamics and ride quality: past, present and future", Proceedings of 2nd International Seminar on the Superconductive Magnetic Levitated Train, Miyazaki, Japan, November.
  30. Oregui, M., Li, S., Nunez, A., Li, Z., Carroll, R. and Dollevoet, R. (2017), "Monitoring bolt tightness of rail joints using axle box acceleration measurements", Struct. Control Health Monitor., 24(2), e1848. https://doi.org/10.1002/stc.1848
  31. Park, J.H., Kim, T.H. and Kim, J.T. (2015), "Image-based bolt-loosening detection technique of bolt Joint in steel bridges", Proceedings of 6th International Conference on Advances in Experimental Structural Engineering, Urbana-Champaign, IL, USA.
  32. Pham, H.C., Ta, Q.B., Kim, J.T., Ho, D.D., Tran, X.L. and Huynh, T.C. (2020a), "Bolt-loosening monitoring framework using an image-based deep learning and graphical model", Sensors, 20(12), 3382. https://doi.org/10.3390/s20123382
  33. Pham, M.T., Kim, J.M. and Kim, C.H. (2020b), "Accurate bearing fault diagnosis under variable shaft speed using convolutional neural networks and vibration spectrogram", Appl. Sci., 10(18), 6385. https://doi.org/10.3390/app10186385
  34. Sato, Y., Matsuura, A., Miura, S. and Satoh, Y. (1985), "Development of guideway for maglev", Proceedings of 7th International Conference on Maglev Transport'85, Tokyo, Japan, September.
  35. Scherer, D., Muller, A. and Behnke, S. (2010), "Evaluation of pooling operations in convolutional architectures for object recognition", Proceedings of 20th International Conference on Artificial Neural Networks (ICANN), Thessaloniki, Greece, September.
  36. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I. and Salakhutdinov, R. (2014), "Dropout: a simple way to prevent neural networks from overfitting", J. Mach. Learn. Res., 15(1), 1929-1958.
  37. Sung, H.K., Jho, J.M., Bae, D.K., Rho, K.S., Lee, J.M., Yoo, M.H. and Nam, Y.Y. (2006), "A fuzzy based treatment to reduce airgap disturbance at the rail joints with step-wise rail joint", Proceedings of 19th International Conference on Magnetically Levitated Systems and Linear Drives, Dresden, Germany, September.
  38. Teng, Z.Q., Teng, S., Zhang, J.Q., Chen, G.F. and Cui, F.S. (2020), "Structural damage detection based on real-time vibration signal and convolutional neural network", Appl. Sci., 10(14), 4720. https://doi.org/10.3390/app10144720
  39. Verstraete, D., Ferrada, A., Droguett, E.L., Meruane, V. and Modarres, M. (2017), "Deep learning enabled fault diagnosis using time-frequency image analysis of rolling element bearings", Shock Vib., 5067651. https://doi.org/10.1155/2017/5067651
  40. Wu, D., Sun, X., Chang, Y., Xu, W., Huang, J., Wu, Z. and Wang, D. (2019), "The temperature effect analysis of high-speed maglev transit", Proceedings of 4th International Conference on Automatic Control and Mechatronic Engineering (ACME 2019), Chongqing, China, May.
  41. Yau, J.D. (2009), "Response of a maglev vehicle moving on a series of guideways with differential settlement", J. Sound Vib., 324, 3-5. https://doi.org/10.1016.jsv.2009.02.031 https://doi.org/10.1016.jsv.2009.02.031
  42. Ye, X.W., Jin, T. and Yun, C.B. (2019), "A review on deep learning-based structural health monitoring of civil infrastructures", Smart Struct. Syst., Int. J., 24(5), 567-585. https://doi.org/10.12989/sss.2019.24.5.567
  43. Zhang, L. and Huang, J.Y. (2018), "Thermal effect on dynamic performance of high-speed maglev train/guideway system", Struct. Eng. Mech., Int. J., 68(4), 459-473. https://doi.org/10.12989/sem.2018.68.4.459
  44. Zhang, D.K., Gao, S.B., Yu, L. and Zhan, D. (2017), "Dynamic detection method of medium-low speed maglev F-track seams based on machine vision", CES Transact. Electr. Mach. Syst., 1(4), 343-353. https://doi.org/10.23919/TEMS.2017.8241355
  45. Zhang, Y., Sun, X.W., Loh, K.J., Su, W.S., Xue, Z.G. and Zhao, X.F. (2020), "Autonomous bolt loosening detection using deep learning", Struct. Health Monitor., 19(1), 105-122. https://doi.org/10.1177/1475921719837509
  46. Zhao, X.F., Zhang, Y. and Wang, N.N. (2019), "Bolt loosening angle detection technology using deep learning", Struct. Control Health Monitor., 26(1), e2292. https://doi.org/10.1002/stc.2292
  47. Zheng, R.H., Xiong, C., Deng, X.B., Li, Q.S. and Li, Y. (2020), "Assessment of earthquake destructive power to structures based on machine learning methods", Appl. Sci., 10(18), 6210. https://doi.org/10.3390/app10186210
  48. Zhong, K.F., Teng, S., Liu, G., Chen, G.F. and Cui, F.S. (2020), "Structural damage features extracted by convolutional neural networks from mode shapes", Appl. Sci., 10(12), 4247. https://doi.org/10.3390/app10124247
  49. Zhou, D.F., Yu, P.C., Wang, L.C. and Li, J. (2017), "An adaptive vibration control method to suppress the vibration of the maglev train caused by track irregularities", J. Sound Vib., 408, 331-350. https://doi.org/10.1016/j.jsv.2017.07.037