Smart Structures and Systems

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Real-time prediction of dynamic irregularity and acceleration of HSR bridges using modified LSGAN and in-service train

  • Huile Li (Key Laboratory of Concrete and Prestressed Concrete Structures of the Ministry of Education, School of Civil Engineering, Southeast University) ;
  • Tianyu Wang (School of Urban Construction and Safety Engineering, Shanghai Institute of Technology) ;
  • Huan Yan (School of Civil Engineering, Southeast University)
  • Received : 2022.11.01
  • Accepted : 2023.03.21
  • Published : 2023.05.25
⟨ Previous Next ⟩

Abstract

Dynamic irregularity and acceleration of bridges subjected to high-speed trains provide crucial information for comprehensive evaluation of the health state of under-track structures. This paper proposes a novel approach for real-time estimation of vertical track dynamic irregularity and bridge acceleration using deep generative adversarial network (GAN) and vibration data from in-service train. The vehicle-body and bogie acceleration responses are correlated with the two target variables by modeling train-bridge interaction (TBI) through least squares generative adversarial network (LSGAN). To realize supervised learning required in the present task, the conventional LSGAN is modified by implementing new loss function and linear activation function. The proposed approach can offer pointwise and accurate estimates of track dynamic irregularity and bridge acceleration, allowing frequent inspection of high-speed railway (HSR) bridges in an economical way. Thanks to its applicability in scenarios of high noise level and critical resonance condition, the proposed approach has a promising prospect in engineering applications.

Keywords

Acknowledgement

The authors gratefully acknowledge financial support from the National Natural Science Foundation of China (Grant No. 51708112), and National Key Research and Development Program of China (Grant No. 2020YFC1511905).

References

  1. Abbas, T., Kavrakov, I., Morgenthal, G. and Lahmer, T. (2020), "Prediction of aeroelastic response of bridge decks using artificial neural networks", Comput. Struct., 231, 106198. https://doi.org/10.1016/j.compstruc.2020.106198
  2. Alfi, S. and Bruni, S. (2008), "Estimation of long wavelength track irregularity from on board measurement", Proceedings of the 4th IET International Conference on Railway Condition Monitoring, Derby, UK, June. https://doi.org/10.1049/ic:20080323
  3. Amiri, G.G., Abdolahi Rad, A., Aghajari, S. and Khanmohamadi Hazaveh, N. (2012), "Generation of near-field artificial ground motions compatible with median-predicted spectra using PSO-based neural network and wavelet analysis", Comput.-Aided Civil Infrastr. Eng., 27(9), 711-730. https://doi.org/10.1111/j.1467-8667.2012.00783.x
  4. Arjovsky, M., Chintala, S. and Bottou, L. (2017), "Wasserstein generative adversarial networks", Proceedings of the 34th International Conference on Machine Learning, ICML, Sydney, August, pp. 298-321.
  5. Azim, M.R. and Gul, M. (2020), "Damage detection of steel-truss railway bridges using operational vibration data", J. Struct. Eng., 146(3), 04020008. https://ascelibrary.org/doi/10.1061/%28ASCE%29ST.1943-541X.0002547
  6. Bocciolone, M., Caprioli, A., Cigada, A. and Collina, A. (2007), "A measurement system for quick rail inspection and effective track maintenance strategy", Mech. Syst. Signal Process., 21(3), 1242-1254. https://doi.org/ 10.1016/j.ymssp.2006.02.007
  7. Cantero, D. and Basu, B. (2015), "Railway infrastructure damage detection using wavelet transformed acceleration response of traversing vehicle", Struct. Control Health Monitor., 22(1), 62-70. https://doi.org/10.1002/stc.1660
  8. Czop, P., Mendrok, K. and Uhl, T. (2011), "Application of inverse linear parametric models in the identification of rail track irregularities", Arch. Appl. Mech., 81, 1541-1554. https://doi.org/10.1007/s00419-010-0500-1
  9. Fan, G., Li, J. and Hao, H. (2021), "Dynamic response reconstruction for structural health monitoring using densely connected convolutional networks", Struct. Health Monitor., 20(4), 1373-1391. https://doi.org/10.1177/1475921720916881
  10. Fang, C., Tang, H.J., Li, Y.L. and Wang, Z.W. (2020), "Effects of random winds and waves on a long span cross-sea bridge using Bayesian regularized back propagation neural network", Adv. Struct. Eng., 23(4), 733-748. https://doi.org/10.1177/136943321988044
  11. Gao, Y., Kong, B. and Mosalam, K.M. (2019), "Deep leaf-bootstrapping generative adversarial network for structural image data augmentation", Comput.-Aided Civil Infrastr. Eng., 34(9), 755-773. https://doi.org/10.1111/mice.12458
  12. Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A. and Bengio, Y. (2014), "Generative adversarial nets", In: Advances in Neural Information Processing Systems, Montreal, Canada, pp. 2672-2680.
  13. Gou, H., Chen, X. and Bao Y. (2021), "A wind hazard warning system for safe and efficient operation of high-speed trains", Automat. Constr., 132, 103952. https://doi.org/10.1016/j.autcon.2021.103952
  14. Guo, F., Qian, Y. and Shi, Y. (2021), "Real-time railroad track components inspection based on the improved YOLOv4 framework", Automat. Constr., 125, 103596. https://doi.org/10.1016/j.autcon.2021.103596
  15. He, X., Wu, T., Zou, Y., Chen, F.Y., Guo, H. and Yu, Z. (2017), "Recent developments of high-speed railway bridges in China", Struct. Infrastr. Eng., 13(12) 1584-1595. https://doi.org/10.1080/15732479.2017.1304429
  16. Kim, J.T., Ho, D.D., Nguyen, K.D., Hong, D.S., Shin, S.W., Yun, C.B. and Shinozuka, M. (2017), "System identification of a cable-stayed bridge using vibration responses measured by a wireless sensor network", Smart Struct. Syst., Int. J., 11(5), 533-553. https://doi.org/10.12989/sss.2013.11.5.533
  17. Lee, J.S., Choi, S., Kim, S., Park, C. and Kim, Y.G. (2012), "A mixed filtering approach for track condition monitoring using accelerometers on the axle box and bogie", IEEE Transact. Instrument. Measur., 61(3) 749-758. https://doi.org/10.1109/TIM.2011.2170377
  18. Lei, X., Sun, L. and Xia, Y. (2021), "Lost data reconstruction for structural health monitoring using deep convolutional generative adversarial networks", Struct. Health Monitor., 20(4), 2069-2087. https://doi.org/10.1177/1475921720959226
  19. Li, H.L., Xia, H., Soliman, M. and Frangopol, D.M. (2015), "Bridge stress calculation based on the dynamic response of coupled train-bridge system", Eng. Struct., 99, 334-345. https://doi.org/10.1016/j.engstruct.2015.04.014
  20. Li, H.L., Wang, T.Y. and Wu, G. (2021), "Dynamic response prediction of vehicle-bridge interaction system using feedforward neural network and deep long short-term memory network", Structures, 34, 2415-2431. https://doi.org/10.1016/j.istruc.2021.09.008
  21. Li, H.L., Wang, T.Y. and Wu, G. (2022), "A Bayesian deep learning approach for random vibration analysis of bridges subjected to vehicle dynamic interaction", Mech. Syst. Signal Process., 170, 108799. https://doi.org/10.1016/j.ymssp.2021.108799
  22. Li, H.L., Wang, T.Y. and Wu, G. (2023a), "Probabilistic safety analysis of coupled train-bridge system using deep learning based surrogate model", Struct. Infrastr. Eng., 19(8), 1138-1157. https://doi.org/10.1080/15732479.2021.2010104
  23. Li, H.L., Wang, T.Y., Yang, J.P. and Wu, G. (2023b), "Deep learning models for time-history prediction of vehicle-induced bridge responses: A comparative study", Int. J. Struct. Stabil. Dyn., 23(1), 2350004. https://doi.org/10.1142/S0219455423500049
  24. Liao, W., Lu, X., Huang, Y., Zheng, Z. and Lin, Y. (2021), "Automated structural design of shear wall residential buildings using generative adversarial networks", Automat. Constr., 132, 103931. https://doi.org/10.1016/j.autcon.2021.103931
  25. Lim, J., Kim, S., Kim, H.K. and Kim, Y.K. (2022), "Long short-term memory (LSTM)-based wind speed prediction during a typhoon for bridge traffic control", J. Wind Eng. Industr. Aerodyn., 220, 104788. https://doi.org/10.1016/j.jweia.2021.104788
  26. Liu, G., Niu, Y., Zhao, W., Duan, Y. and Shu, J. (2022), "Data anomaly detection for structural health monitoring using a combination network of GANomaly and CNN", Smart Struct. Syst., Int. J., 29(1), 53-62. https://doi.org/10.12989/sss.2022.29.1.053
  27. Maeda, H., Kashiyama, T., Sekimoto, Y., Seto, T. and Omata, H. (2021), "Generative adversarial network for road damage detection", Comput.-Aided Civil Infrastr. Eng., 36, 47-60. https://doi.org/10.1111/mice.12561
  28. Mao, X., Li, Q., Xie, H., Lau, Y.K., Wang, Z. and Smolley, S.P. (2017), "Least squares generative adversarial networks", Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, pp. 2813-2821.
  29. Matsuoka, K. and Tanaka, H. (2023), "Drive-by deflection estimation method for simple support bridges based on track irregularities measured on a traveling train", Mech. Syst. Signal Process., 182, 109549. https://doi.org/10.1016/j.ymssp.2022.109549
  30. Meixedo, A., Santos, J., Ribeiro, D., Calcada, R. and Todd, M. (2021), "Damage detection in railway bridges using traffic-induced dynamic responses", Eng. Struct., 238, 112189. https://doi.org/10.1016/j.engstruct.2021.112189
  31. Mirza, M. and Osindero, S. (2014), "Conditional generative adversarial nets", arXiv preprint arXiv, 1411.1784. https://arxiv.org/abs/1411.1784
  32. Montenegro, P.A., Carvalho, H., Ribeiro, D., Calcada, R., Tokunaga, M., Tanabe, M. and Zhai, W.M. (2021), "Assessment of train running safety on bridges: A literature review", Eng. Struct., 241, 112425. https://doi.org/10.1016/j.engstruct.2021.112425
  33. National Railway Administration (NRA) (2014), TB/T 3352-2014, PSD of ballastless track irregularities of high-speed railway, China Railway Press, Beijing, China.
  34. Obrien, E.J., Bowe, C., Quirke, P. and Cantero, D. (2017), "Determination of longitudinal profile of railway track using vehicle-based inertial readings", Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit, 231(5), 518-534. https://doi.org/10.1177/0954409716664936
  35. Onat, O. and Gul, M. (2018), "Application of Artificial Neural Networks to the prediction of out-of-plane response of infill walls subjected to shake table", Smart Struct. Syst., Int. J., 21(4), 521-535. https://doi.org/10.12989/sss.2018.21.4.521
  36. Peixer, M.A., Montenegro, P.A., Carvalho, H., Ribeiro, D., Bittencourt, T.N. and Calcada, R. (2021), "Running safety evaluation of a train moving over a high-speed railway viaduct under different track conditions", Eng. Fail. Anal., 121, 105133. https://doi.org/10.1016/j.engfailanal.2020.105133
  37. Rachedi, M., Matallah, M. and Kotronis, P. (2021), "Seismic behavior & risk assessment of an existing bridge considering soil-structure interaction using artificial neural networks", Eng. Struct., 232, 111800. https://doi.org/10.1016/j.engstruct.2020.111800
  38. Real, J., Salvador, P., Montalban, L. and Bueno, M. (2011), "Determination of rail vertical profile through inertial methods", Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit, 225(1), 14-23. https://doi.org/10.1243/09544097JRRT353
  39. Salcher, P. and Adam, C. (2015), "Modeling of dynamic train-bridge interaction in high-speed railways", Acta Mechanica, 226(8), 2473-2495. https://doi.org/10.1007/s00707-015-1314-6
  40. Shim, S., Kim, J., Lee, S.W. and Cho, G.C. (2022), "Road damage detection using super-resolution and semi-supervised learning with generative adversarial network", Automat. Constr., 135, 104139. https://doi.org/10.1016/j.autcon.2022.104139
  41. Soleimani, F. and Liu, X. (2022), "Artificial neural network application in predicting probabilistic seismic demands of bridge components", Earthq. Eng. Struct. Dyn., 51(3), 612-629. https://doi.org/10.1002/eqe.3582
  42. Soleimani-Babakamali, M.H., Soleimani-Babakamali, R. and Sarlo, R. (2022), "A general framework for supervised structural health monitoring and sensor output validation mitigating data imbalance with generative adversarial networks-generated high-dimensional features", Struct. Health Monitor., 21(3), 1167-1182. https://doi.org/10.1177/1475921721102548
  43. Thiyagarajan, J.S., Su, D., Tanaka, H., Zhao, B. and Nagayama, T. (2021), "Response based track profile estimation using observable train models with numerical and experimental validations", Smart Struct. Syst., Int. J., 27(2), 267-284. https://doi.org/10.12989/sss.2021.27.2.267
  44. Tsunashima, H., Naganuma, Y. and Kobayashi, T. (2014), "Track geometry estimation from car-body vibration", Vehicle Syst. Dyn., 52, 207-219. https://doi.org/10.1080/00423114.2014.889836
  45. Vahedian, V., Omranian, E. and Abdollahzadeh, G. (2022), "A new method for generating aftershock records using artificial neural network", J. Earthq. Eng., 26(1), 140-161. https://doi.org/10.1080/13632469.2019.1664675
  46. Wang, Y., Wang, P., Tang, H., Liu, X., Xu, J., Xiao, J. and Wu, J. (2021), "Assessment and prediction of high speed railway bridge long-term deformation based on track geometry inspection big data", Mech. Syst. Signal Process., 158, 107749. https://doi.org/10.1016/j.ymssp.2021.107749
  47. Wang, C., Song, L. and Fan, J. (2022), "End-to-end structural analysis in civil engineering based on deep learning", Automat Constr., 138, 104255. https://doi.org/10.1016/j.autcon.2022.104255
  48. Wei, X., Liu, F. and Jia, L. (2016), "Urban rail track condition monitoring based on in-service vehicle acceleration measurements", Measurement: J. Int. Measur. Confed., 80, 217-228. https://doi.org/10.1016/j.measurement.2015.11.033
  49. Weston, P.F., Ling, C.S., Roberts, C., Goodman, C.J., Li, P. and Goodall, R.M. (2007), "Monitoring vertical track irregularity from in-service railway vehicles", Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit, 221(1), 75-88. https://doi.org/10.1243/0954409JRRT65
  50. Xia, H., Li, H.L., Guo, W.W. and De Roeck, G. (2014), "Vibration resonance and cancellation of simply supported bridges under moving train loads", J. Eng. Mech., 140(5) 04014015. https://doi.org/10.1061/(ASCE)EM.1943-7889.0000714
  51. Xia, H., Zhang, N. and Guo, W.W. (2018), Dynamic interaction of train-bridge systems in high-speed railways: theory and applications, Springer, Berlin.
  52. Xiao, X., Sun, Z. and Shen, W. (2020), "A Kalman filter algorithm for identifying track irregularities of railway bridges using vehicle dynamic responses", Mech. Syst. Signal Process., 138, 106582. https://doi.org/10.1016/j.ymssp.2019.106582
  53. Xiong, J.C. and Chen, J. (2021), "Crowd jumping load simulation with generative adversarial networks", Smart Struct. Syst., Int. J., 27(4), 607-621. https://doi.org/10.12989/sss.2021.27.4.607
  54. Xu, B. and Liu, C. (2022), "Pavement crack detection algorithm based on generative adversarial network and convolutional neural network under small samples", Measurement: J. Int. Measur. Confed., 196, 111219. https://doi.org/10.1016/j.measurement.2022.111219
  55. Xue, J. and Ou, G. (2021), "Predicting wind-induced structural response with LSTM in transmission tower-line system", Smart Struct. Syst., Int. J., 28(3), 391-405. https://doi.org/ 10.12989/sss.2021.28.3.391
  56. Yang, Y.B., Yau, J.D. and Wu, Y.S. (2004), Vehicle-bridge interaction dynamics: with applications to high-speed railways, World Scientific, Singapore.
  57. Yu, C., Li, Y., Xiang, H. and Zhang, M. (2018), "Data mining-assisted short-term wind speed forecasting by wavelet packet decomposition and Elman neural network", J. Wind Eng. Industr. Aerodyn., 175, 136-143. https://doi.org/10.1016/j.jweia.2018.01.020
  58. Yu, Y., Cai, C.S. and Liu, Y.M. (2021), "Probabilistic vehicle weight estimation using physics-constrained generative adversarial network", Comput.-Aided Civil Infrastr. Eng., 36(6), 781-799. https://doi.org/10.1111/mice.12677
  59. Yuan, Z., Luo, J., Zhu, S. and Zhai, W. (2021), "A Wasserstein generative adversarial network-based approach for real-time track irregularity estimation using vehicle dynamic responses", Vehicle Syst. Dyn., 60(12), 4186-4205. https://doi.org/10.1080/00423114.2021.1999480
  60. Zhai, W., Xia, H., Cai, C., Gao, M., Li, X., Guo, X., Zhang, N. and Wang, K. (2013), "High-speed train-track-bridge dynamic interactions - Part I: theoretical model and numerical simulation", Int. J. Rail Transport., 1(1-2), 3-24. https://doi.org/10.1080/23248378.2013.791498
  61. Zhang, K., Zhang, Y. and Cheng, H.D. (2020), "Self-supervised structure learning for crack detection based on cycle-consistent generative adversarial networks", J. Comput. Civil Eng., 34(3), 04020004. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000883