Steel and Composite Structures

  • 제46권6호
  • /
  • Pages.731-744
  • /
  • 2023
  • /
  • 1229-9367(pISSN)
  • /
  • 1598-6233(eISSN)
테크노프레스 (Techno-Press)
권호 표지
DOI QR코드

DOI QR Code

A novel method for vehicle load detection in cable-stayed bridge using graph neural network

  • Van-Thanh Pham (Department of Civil and Environmental Engineering, Sejong University) ;
  • Hye-Sook Son (Department of Computer Engineering, Sejong University) ;
  • Cheol-Ho Kim (Department of Civil and Environmental Engineering, Sejong University) ;
  • Yun Jang (Department of Computer Engineering, Sejong University) ;
  • Seung-Eock Kim (Department of Civil and Environmental Engineering, Sejong University)
  • 투고 : 2021.10.17
  • 심사 : 2023.03.06
  • 발행 : 2023.03.25
⟨ 이전 논문 다음 논문 ⟩

초록

Vehicle load information is an important role in operating and ensuring the structural health of cable-stayed bridges. In this regard, an efficient and economic method is proposed for vehicle load detection based on the observed cable tension and vehicle position using a graph neural network (GNN). Datasets are first generated using the practical advanced analysis program (PAAP), a robust program for modeling and considering both geometric and material nonlinearities of bridge structures subjected to vehicle load with low computational costs. With the superiority of GNN, the proposed model is demonstrated to precisely capture complex nonlinear correlations between the input features and vehicle load in the output. Four popular machine learning methods including artificial neural network (ANN), decision tree (DT), random forest (RF), and support vector machines (SVM) are refereed in a comparison. A case study of a cable-stayed bridge with the typical truck is considered to evaluate the model's performance. The results demonstrate that the GNN-based model provides high accuracy and efficiency in prediction with satisfactory correlation coefficients, efficient determination values, and very small errors; and is a novel approach for vehicle load detection with the input data of the existing monitoring system.

키워드

과제정보

This research was supported by the National Research Foundation of Korea (NRF) funded by the Korean government (MSIT) (No. 2021R1A2B5B01002577 and No. 2019R1A4A1021702).

참고문헌

  1. Avci Karatas, C. (2019), "Prediction of ultimate load capacity of concrete-filled steel tube columns using multivariate adaptive regression splines (MARS)" , Steel Compos. Struct., 33(4), 583-594. https://doi.org/10.12989/scs.2019.33.4.583. 
  2. Bao, Y. and Li, H. (2020), "Machine learning paradigm for Structural health monitoring", Struct. Health Monit., https://doi.org/10.1177/1475921720972416. 
  3. Bao, Y., Li, H., Zhang, F. and Ou, J. (2013), "Compressive sampling based approach for identification of moving loads distribution on cable-stayed bridges", Process Sens. Smart Struct. Technol. Civil, Mech. Aerosp. Syst., 8692, 86923B-1-10. https://doi.org/10.1117/12.2009542. 
  4. Bergstra, J., Bardenet, R., Bengio, Y. and Kegl, B. (2011), "Algorithms for hyper-parameter optimization", Proceedings of the 25th Annual Conference on Neural Information Processing Systems (NIPS), 1-9. 
  5. Bui, V.T., Truong, V.H., Trinh, M.C. and Kim, S.E. (2020), "Fully nonlinear analysis of steel-concrete Composite girder with web local buckling effects", Int. J. Mech. Sci., 184, 05729. https://doi.org/10.1016/j.ijmecSci.2020.105729. 
  6. Bui, V.T., Vu, Q.V., Truong, V.H. and Kim, S.E. (2021), "Fully nonlinear inelastic analysis of rectangular CFST frames with semi - rigid connections", Steel Compos. Struct., 38(5), 497-521. https://doi.org/10.12989/scs.2021.38.5.497. 
  7. Chen, B.H. and Huang, S.C. (2015), "Probabilistic neural networks based moving vehicles extraction algorithm for intelligent traffic surveillance systems", Inf. Sci., 299, 283-295. https://doi.org/10.1016/j.ins.2014.12.033. 
  8. Chen, S.Z., Wu, G. and Feng, D.C. (2019), "Development of a bridge weigh-in-motion method considering the presence of multiple vehicles", Eng. Struct., 191, 724-739. https://doi.org/10.1016/j.engStruct.2019.04.095. 
  9. Chen, Z., Li, H., Bao, Y., Li, N. and Jin, Y. (2016), "Identification of spatio-temporal distribution of vehicle loads on long-span bridges using computer vision technology", Struct. Control Heal. Monit., 23(3), 517-534. https://doi.org/10.1002/stc.1780. 
  10. Cho, S., Park, J., Jung, H. J., Yun, C. B., Jang, S., Jo, H. and Seo, J. W., (2010), "Structural health monitoring of a cable-stayed bridge using acceleration data via wireless smart sensor network", Bridg. Maintenance, Safety, Manage., Life-Cycle Optim. - Proc. 5th Int. Conf. Bridg. Maintenance, Saf. Manag., 6(5), 158-164. https://doi.org/10.1201/b10430-19. 
  11. Cho, K., Van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H. and Bengio, Y. (2014), "Learning phrase representations using RNN encoder-decoder for statistical machine translation", EMNLP 2014 - Conference on Empirical Methods in Natural Language Processing, 1724-1734. https://doi.org/10.3115/v1/d14-1179. 
  12. Dan, D., Ge, L. and Yan, X. (2019), "Identification of moving loads based on the information fusion of weigh-in-motion system and multiple camera machine vision", Meas. J. Int. Meas. Confed., 144, 155-166. https://doi.org/10.1016/j.measurement.2019.05.042. 
  13. Deng, Y., Li, A. and Feng, D. (2019), "Fatigue performance investigation for hangers of suspension bridges based on site-specific vehicle loads", Struct. Heal. Monit., 18(3), 934-948. https://doi.org/10.1177/1475921718786710. 
  14. Moses, F. (1979), "Weigh-in-motion system using instrumented bridges", Transp. Eng. J., 105(3), 233-249.  https://doi.org/10.1061/TPEJAN.0000783
  15. Fryba, L. (1999), Vibration of Solids and Structures under moving Loads, Thomas Telford Ltd. 
  16. Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O. and Dahl, G.E. (2017), "Neural message passing for quantum chemistry", Proc. 34th Int. Conf. Mach. Learn. Icml 2017, 3, 2053-2070. 
  17. Ha, M.H., Vu, Q.A. and Truong, V.H. (2018), "Optimum design of stay cables of steel cable-stayed bridges using nonlinear inelastic analysis and genetic algorithm", Struct., 16, 288-302. https://doi.org/10.1016/j.istruc.2018.10.007. 
  18. Hamilton, W.L., Zhang, J., Danescu-Niculescu-Mizil, C., Jurafsky, D. and Leskovec, J. (2017), "Loyalty in online communities", Proceedings of the 11th International Conference on Web and Social Media, ICWSM, 87. 
  19. Hassona, F., Hashem, M., Abdelmalak, R. and Hakeem, B. (2018), "Facing the challenges in structural engineering", Sustain. Civil Infrastruct., 265-280. https://doi.org/10.1007/978-3-319-61914-9. 
  20. Huang, Y., Li, J. and Fu, J. (2019), "Review on application of artificial intelligence in civil engineering", C. Comput. Model. Eng. Sci., 121(3), 845-875. https://doi.org/10.32604/cmes.2019.07653. 
  21. Kalin, J., Znidaric, A. and Lavric, I. (2006), "Practical implementation of nothing-on-the-road bridge weigh-in-motion system", Proc., 9th Int. Symp. Heavy Veh. Weight. Dimens., 207, 3-10. 
  22. Ketkar, N. (2017), "Introduction to PyTorch", Deep Learning with Python, 195-208. https://doi.org/10.1007/978-1-4842-2766-4. 
  23. Kim, S.E., Vu, Q.V., Papazafeiropoulos, G., Kong, Z. and Truong, V.H. (2020), "Comparison of machine learning algorithms for regression and classification of ultimate load-carrying capacity of steel frames", Steel Compos. Struct., 37(2), 193-209. https://doi.org/10.12989/scs.2020.37.2.193. 
  24. Kingma, D.P. and Ba, J.L. (2015), "Adam: A method for stochastic optimization", 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings, 1-15. 
  25. Lansdell, A., Song, W. and Dixon, B. (2017), "Development and testing of a bridge weigh-in-motion method considering nonconstant vehicle speed", Eng. Struct., 152, 709-726. https://doi.org/10.1016/j.engStruct.2017.09.044. 
  26. Law, S.S., Bu, J.Q., Zhu, X.Q. and Chan, S.L., (2004), "Vehicle axle loads identification using finite element method, Eng. Struct., 26(8), 1143-1153. https://doi.org/10.1016/j.engStruct.2004.03.017. 
  27. Law, S.S. and Fang, Y.L., (2001), "Moving force identification: Optimal state estimation approach", J. Sound Vib., 239(2), 233-254. https://doi.org/10.1006/jsvi.2000.3118. 
  28. Li, S., Li, H., Liu, Y., Lan, C., Zhou, W. and Ou, J., (2013), "SMC Structural health monitoring benchmark problem using monitored data from an actual cable-stayed bridge", Struct. Control Heal. Monit., 21(2), 156-172. https://doi.org/10.1002/stc.1559. 
  29. Li, L., Jamieson, K., Rostamizadeh, A., Gonina, E., Moritz, J.B., Recht, B. and Talwalkar, A. (2020), "A system for massively parallel hyperparameter tuning", Proceedings of the Machine Learning and Systems 2020. Texas, USA. 
  30. Liu, Z. and Zhou, J. (2020), Introduction Graph Neural Networks, Morgan & Claypool. https://doi.org/10.2200/S00980ED1V01Y202001AIM045. 
  31. Luat, N.V., Shin, J., Han, S.W., Nguyen, N.V. and Lee, K. (2021), "Ultimate axial capacity prediction of CCFST columns using hybrid intelligence models - A new approach" , Steel Compos. Struct., 40(3), 461-479. https://doi.org/10.12989/scs.2021.40.3.461. 
  32. Lydon, M., Taylor, S.E., Robinson, D., Mufti, A. and Brien, E.J.O. (2016), "Recent developments in bridge weigh in motion (BWIM)", J. Civ. Struct. Heal. Monit., 6(1), 69-81. https://doi.org/10.1007/s13349-015-0119-6. 
  33. Malekjafarian, A., McGetrick, P.J. and Obrien, E.J. (2015), "A review of indirect bridge monitoring using passing vehicles", Shock Vib., 2015, 1-16. https://doi.org/10.1155/2015/286139. 
  34. Marwala, T. (2010), Finite-Element-Model Updating Using Computional Intelligence Techniques: Applications to Struct. Dynam., https://doi.org/10.1007/978-1-84996-323-7. 
  35. OBrien, E.J., Enright, B. and Dempsey, T. (2010), "The influence of correlation on the extreme traffic loading of bridges", Proceedings of the 5th International Conference on Bridge Maintenance, Safety and Management, 958-964. https://doi.org/10.1201/b10430-136. 
  36. Rahimi, A., Cohn, T. and Baldwin, T. (2018), "Semi-supervised user geolocation via graph convolutional networks", ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers), 2009-2019. https://doi.org/10.18653/v1/p18-1187. 
  37. Serban, A. (2017), "Failure estimation of the Composite laminates using machine learning techniques", Steel Compos. Struct., 25(6), 663-670. https://doi.org/10.12989/scs.2017.25.6.663. 
  38. Shariati, M., Mafipour, M.S., Mehrabi, P., Zandi, Y., Dehghani, D., Bahadori, A., Shariati, A., Trung, N.T., Salih, M.N.A. and PoiNgian, S. (2019), "Application of extreme learning machine (ELM) and Genetic Programming (GP) to design steel-concrete composite floor systems at elevated temperatures", Steel Compos. Struct., 33(3), 319-332. https://doi.org/10.12989/scs.2019.33.3.319. 
  39. Song, M.T., Cao, D.Q., Zhu, W.D. and Bi, Q.S., (2016), "Dynamic response of a cable-stayed bridge subjected to a moving vehicle load", Acta Mech., 227(10), 2925-2945. https://doi.org/10.1007/s00707-016-1635-0. 
  40. Thai, H.T. and Choi, D.H. (2011), "A fiber beam-column element for frame analysis", Proceedings of the 7th International Conference on Steel and Aluminium Structures ICSAS, 128-134. 
  41. Thai, H.T. and Choi, D.H. (2011), "A fiber beam-column element for frame analysis", Mater. Sci., https://doi.org/10.3850/978-981-08-9247-0_rp017-icsas11. 
  42. Thai, H.T. and Kim, S.E. (2007), "Practical nonlinear dynamic analysis of cable-stayed bridge", Construction, 13-16.
  43. Thai, H.T. and Kim, S.E. (2008), "Second-order inelastic dynamic analysis of three-dimensional cable-stayed bridges", Steel Struct., 8, 205-214. 
  44. Thai, H.T. and Kim, S.E. (2009), "Practical advanced analysis software for nonlinear inelastic analysis of space steel structures", Adv. Eng. Softw., 40(9), 786-797. https://doi.org/10.1016/j.advengsoft.2009.02.001. 
  45. Thai, H.T. and Kim, S.E. (2011a), "Nonlinear static and dynamic analysis of cable structures", Finite Elem. Anal. Des., 47(3), 237-246. https://doi.org/10.1016/j.finel.2010.10.005. 
  46. Thai, H.T. and Kim, S.E. (2011b), "Practical advanced analysis software for nonlinear inelastic dynamic analysis of steel structures", J. Constr. Steel Res., 67(3), 453-461. https://doi.org/10.1016/j.jcsr.2010.09.009. 
  47. Thai, H.T. and Kim, S.E. (2012), "Second-order inelastic analysis of cable-stayed bridges", Finite Elem. Anal. Des., 53, 48-55. https://doi.org/10.1016/j.finel.2011.07.002. 
  48. Tran, V.L., Jang, Y. and Kim, S.E. (2021), "Improving the axial compression capacity prediction of elliptical CFST columns using a hybrid ANN-IP model", Steel Compos. Struct., 39(3), 319-335. https://doi.org/10.12989/scs.2021.39.3.319. 
  49. Transportation, M. of C. and (2015), Standard Design Specification of Highway Bridges Seoul, Korea. 
  50. Truong, V.H. and Kim, S.E. (2017), "An efficient method for reliability-based design optimization of nonlinear inelastic steel space frames", Struct. Multidimscip. Optim., 56(2), 331-351. https://doi.org/10.1007/s00158-017-1667-7. 
  51. Berg, V.D.R., Kipf, T.N. and Welling, M. (2017), "Graph convolutional matrix completion", arXiv:1706.02263. 
  52. Vinyals, O., Bengio, S. and Kudlur, M. (2016), "Order matters: sequence to sequence for sets", 4th International Conference on Learning Representations, ICLR 2016 - Conference Track Proceedings, 1-11. 
  53. Wang, L., Chen, F. and Yin, H. (2016), "Detecting and tracking vehicles in traffic by unmanned aerial vehicles", Autom. Constr., 72, 294-308. https://doi.org/10.1016/j.autcon.2016.05.008. 
  54. Wang, M., Zheng, D., Ye, Z., Gan, Q., Li, M., Song, X., Zhou, J., Ma, C., Yu, L., Gai, Y., Xiao, T., He, T., Karypis, G., Li, J. and Zhang, Z. (2019), "Deep graph library: a graph-centric, highly-performant package for graph neural networks", Comput. Sci., Math., 1-18. http://arxiv.org/abs/1909.01315. 
  55. Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C. and Yu, P.S. (2020), "A Comprehensive survey on graph neural networks", IEEE Transactions on Neural Networks and Learning Systems, 1-21. https://doi.org/10.1109/tnnls.2020.2978386. 
  56. Yan, W., Deng, L., Zhang, F., Li, T. and Li, S. (2019), "Probabilistic machine learning approach to bridge fatigue failure analysis due to vehicular overloading", Eng. Struct., 193, 91-99. https://doi.org/10.1016/j.engStruct.2019.05.028. 
  57. Yang, H., Qian, H. and Wang, P. (2021), "Fatigue property analysis of U rib-to-crossbeam connections under heavy traffic vehicle load considering in-plane shear stress", Steel Compos. Struct., 38(3), 271-280. https://doi.org/10.12989/scs.2021.38.3.271. 
  58. Yang, Y.B. and Shieh, M.S. (1990), "Solution method for nonlinear problems with multiple critical points", AIAA J., 28(12), 2110-2116.  https://doi.org/10.2514/3.10529
  59. Ye, X.W., Yi, T.H., Dong, C.Z. and Liu, T. (2016), "Vision-based structural displacement measurement: system performance evaluation and influence factor analysis", Meas. J. Int. Meas. Confed., 88, 372-384. https://doi.org/10.1016/j.measurement.2016.01.024. 
  60. Ying, R., Morris, C. and Hamilton, W.L. (2018), "Hierarchical graph representation learning with differentiable pooling", Adv. Neural Inform. Process. Syst., 4800-4810. 
  61. Yu, L. and Chan, T.H.T. (2007), "Recent research on identification of moving loads on bridges", J. Sound Vib., 305(1-2), 3-21. https://doi.org/10.1016/j.jsv.2007.03.057. 
  62. Yu, Y., Cai, C.S. and Deng, L. (2017), "Nothing-on-road bridge weigh-in-motion considering the transverse position of the vehicle" , Struct. Infrastruct. Eng., 14(8), 1108-1122.  https://doi.org/10.1080/15732479.2017.1401095
  63. Zhang, F. and Li, H. (2012), "Moving forces and their bounds identification method for cable-stayed bridges with uncertain parameters and noisy measurements", Heal. Monit. Struct. Biol. Syst., 8348, 1-11. https://doi.org/10.1117/12.917410. 
  64. Zhang, L., Qiu, G. and Chen, Z. (2021), "Structural health monitoring methods of cables in cable-stayed bridge: A review", Meas. J. Int. Meas. Confed., 168(May 2020), 108343-1-7. https://doi.org/10.1016/j.measurement.2020.108343. 
  65. Zhou, Y., Pei, Y., Li, Z., Fang, L., Zhao, Y. and Yi, W. (2020), "Vehicle weight identification system for spatiotemporal load distribution on bridges based on non-contact machine vision technology and deep learning algorithms", 159, 107801. https://doi.org/10.1016/j.measurement.2020.107801. 
  66. Zhu, X.Q. and Law, S.S. (2002), "Dynamic load on continuous multi-lane bridge deck from moving vehicles", J. Sound Vib., 251(4), 697-716. https://doi.org/10.1006/jsvi.2001.3996.