Steel and Composite Structures

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Cable damage identification of cable-stayed bridge using multi-layer perceptron and graph neural network

  • Pham, Van-Thanh (Department. of Civil and Environmental Engineering, Sejong University) ;
  • Jang, Yun (Department. of Computer Engineering, Sejong University) ;
  • Park, Jong-Woong (School of Civil and Environmental Engineering, Chung-Ang University) ;
  • Kim, Dong-Joo (Department. of Civil and Environmental Engineering, Sejong University) ;
  • Kim, Seung-Eock (Department. of Civil and Environmental Engineering, Sejong University)
  • Received : 2021.03.21
  • Accepted : 2022.07.08
  • Published : 2022.07.25
⟨ Previous Next ⟩

Abstract

The cables in a cable-stayed bridge are critical load-carrying parts. The potential damage to cables should be identified early to prevent disasters. In this study, an efficient deep learning model is proposed for the damage identification of cables using both a multi-layer perceptron (MLP) and a graph neural network (GNN). Datasets are first generated using the practical advanced analysis program (PAAP), which is a robust program for modeling and analyzing bridge structures with low computational costs. The model based on the MLP and GNN can capture complex nonlinear correlations between the vibration characteristics in the input data and the cable system damage in the output data. Multiple hidden layers with an activation function are used in the MLP to expand the original input vector of the limited measurement data to obtain a complete output data vector that preserves sufficient information for constructing the graph in the GNN. Using the gated recurrent unit and set2set model, the GNN maps the formed graph feature to the output cable damage through several updating times and provides the damage results to both the classification and regression outputs. The model is fine-tuned with the original input data using Adam optimization for the final objective function. A case study of an actual cable-stayed bridge was considered to evaluate the model performance. The results demonstrate that the proposed model provides high accuracy (over 90%) in classification and satisfactory correlation coefficients (over 0.98) in regression and is a robust approach to obtain effective identification results with a limited quantity of input data.

Keywords

Acknowledgement

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

References

  1. Bakhary, N., Hao, H. and Deeks, A.J. (2007), "Damage detection using artificial neural network with consideration of uncertainties", Eng. Struct., 29(11), 2806-2815. https://doi.org/10.1016/j.engstruct.2007.01.013.
  2. 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(January), 105729. https://doi.org/10.1016/j.ijmecsci.2020.105729.
  3. 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/https://doi.org/10.12989/scs.2021.38.5.497.
  4. Caruana, R. (1997), "Multitask Learning", Kluwer Academic, 41-75. https://doi.org/10.1111/j.1468-0319.1995.tb00042.x.
  5. Chandrashekhar, M. and Ganguli, R. (2009), "Damage assessment of structures with uncertainty by using mode-shape curvatures and fuzzy logic", J. Sound Vib., 326(3-5), 939-957. https://doi.org/10.1016/j.jsv.2009.05.030.
  6. 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.
  7. Dackermann, U., Smith, W.A. and Randall, R.B. (2014), "Damage identification based on response-only measurements using cepstrum analysis and artificial neural networks", Struct. Heal. Monit., 13(4), 430-444. https://doi.org/10.1177/1475921714542890.
  8. Ding, Z., Lu, Z., Huang, M. and Liu, J. (2017), "Improved artificial bee colony algorithm for crack identification in beam using natural frequencies only", Inverse Probl. Sci. Eng., 25(2), 218-238. https://doi.org/10.1080/17415977.2016.1160391.
  9. Ding, Z.H., Huang, M. and Lu, Z.R. (2016), "Structural damage detection using artificial bee colony algorithm with hybrid search strategy", Swarm Evol. Comput., 28, 1-13. https://doi.org/10.1016/j.swevo.2015.10.010.
  10. Fan, W. and Qiao, P. (2011), "Vibration-based damage identification methods: A review and comparative study", Struct. heal. monit., 10(1), 83-111. https://doi.org/10.1177/1475921710365419.
  11. Frank, L. and Christopher, P. (1996), Cable Corrosion in Bridges and Other Structures: Causes and Solutions Amer Society of Civil Engineers.
  12. 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.
  13. 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", 16(October), 288-302. https://doi.org/10.1016/j.istruc.2018.10.007.
  14. Hakim, S.J.S. and Abdul Razak, H. (2013), "Structural damage detection of steel bridge girder using artificial neural networks and finite element models", Steel Compos. Struct., 14(4), 367-377. https://doi.org/10.12989/scs.2013.14.4.367.
  15. Hao, H. and Xia, Y. (2002), "Vibration-based damage detection of structures by genetic algorithm", J Comput Civil Eng ASCE. https://doi.org/10.1061/(asce)0887-3801(2002)16:3(222).
  16. Hastie, T., Tibshirani, R. and Friedman, J. (2011), "The Elements of Statistical Learning: Data Mining, Inference, and Prediction", J. Amer. Statistic. Asso., 567-567. https://doi.org/10.1198/jasa.2004.s339.
  17. Hecht-Nielsen, R. (1989), "Theory of the Backpropagation Neural Network", International 1989 Joint Conference on Neural Networks for Perception, 593-605. https://doi.org/10.1109/IJCNN.1989.118638.
  18. Ho, H.N., Kim, K.D., Park, Y.S. and Lee, J.J. (2013), "An efficient image-based damage detection for cable surface in cable-stayed bridges", NDT E Int., 58, 18-23. https://doi.org/10.1016/j.ndteint.2013.04.006.
  19. Hossain, M.S., Ong, Z.C., Ismail, Z., Noroozi, S. and Khoo, S.Y. (2017), "Artificial neural networks for vibration based inverse parametric identifications: A review", Appl. Soft Comput. J., 52, 203-219. https://doi.org/10.1016/j.asoc.2016.12.014.
  20. Hou, Z., Xia, H. and Zhang, Y.L. (2012), "Dynamic analysis and shear connector damage identification of steel-concrete composite beams", Steel Compos. Struct., 13(4), 327-341. https://doi.org/10.12989/scs.2012.13.4.327.
  21. Ketkar, N. (2017), "Introduction to PyTorch" , Deep Learning with Python, 195-208. https://doi.org/10.1007/978-1-4842-2766-4.
  22. Kim, B.J., Lee, S.H. and Kim, H.K. (2012), "Mokpo bridge: New landmark in Mokpo city" , Struct. Eng. Int. J. Int. Assoc. Bridg. Struct. Eng., 22(1), 29-31. https://doi.org/10.2749/101686612X13216060213031.
  23. 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.
  24. Lee, J.J., Lee, J.W., Yi, J.H., Yun, C.B. and Jung, H.Y. (2005), "Neural networks-based damage detection for bridges considering errors in baseline finite element models" , J. Sound Vib., 280(3-5), 555-578. https://doi.org/10.1016/j.jsv.2004.01.003.
  25. Li, R., Mita, A. and Zhou, J. (2013), "Integral resonant control scheme for cancelling human-induced vibrations in light-weight pedestrian structures", Struct. Control Heal. Monit., 20, 1255-1270. https://doi.org/10.1002/stc.1530.
  26. Li, X., Gao, C., Guo, Y., He, F. and Shao, Y. (2019), "Cable surface damage detection in cable-stayed bridges using optical techniques and image mosaicking", Opt. laser technol., 110, 36-43. https://doi.org/10.1016/j.optlastec.2018.07.012.
  27. Lin, H., Xiang, Y. and Jia, Y. (2018), "Study on health monitoring system design of cable-stayed bridge", Sustain. Civ. Infrastruct., 1(Wong 2004), 42-54. https://doi.org/10.1007/978-3-319-61914-9.
  28. Liu, Q., Liu, L., Chen, H., Zhou, Y. and Lei, X. (2020), "Prediction of vibration and noise from steel/composite bridges based on receptance and statistical energy analysis", Steel Compos. Struct., 37(3), 291-306. https://doi.org/10.12989/scs.2020.37.3.291.
  29. Liu, X., Xiao, J., Wu, B. and He, C. (2018), "A novel sensor to measure the biased pulse magnetic response in steel stay cable for the detection of surface and internal flaws", Sensors Actuators, Phys., 269, 218-226. https://doi.org/10.1016/j.sna.2017.11.005.
  30. Liu, Z. and Zhou, J. (2020), Introduction to Graph Neural Networks Morgan & Claypool.
  31. Magalhaes, F., Cunha, A. and Caetano, E. (2009), "Online automatic identification of the modal parameters of a long span arch bridge", Mech. Syst. Signal Process., 23(2), 316-329. https://doi.org/10.1016/j.ymssp.2008.05.003.
  32. 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.
  33. Mehrabi, A.B. and Telang, N.M. (2003), "Cable-stayed bridge performance evaluation lessons from the field", Proc. Struct. Congr. Expo., 1083(2003).
  34. Mehrabi, Armin B., P.E. and A.M.ASCE (2006), "In-service evaluation of cable-stayed bridges, overview of available methods and findings", J. bridg. eng., 11(6), 716-724. https://doi.org/10.1061/(ASCE)1084-0702(2006)11:6(716).
  35. Nazarian, E., Ansari, F., Zhang, X. and Taylor, T. (2016), "Detection of tension loss in cables of cable-stayed bridges by distributed monitoring of bridge deck strains", J. Struct. Eng. 142(6), 1-13. https://doi.org/10.1061/(ASCE)ST.1943-541X.0001463.
  36. Nobahari, M., Ghasemi, M.R. and Shabakhty, N. (2017), "Truss structure damage identification using residual force vector and genetic algorithm", Steel Compos. Struct., 25(4), 485-496. https://doi.org/10.12989/scs.2017.25.4.485.
  37. Padil, K.H., Bakhary, N. and Hao, H. (2017), "The use of a nonprobabilistic artificial neural network to consider uncertainties in vibration-based-damage detection", Mech. Syst. Signal Process., 83, 194-209. https://doi.org/10.1016/j.ymssp.2016.06.007.
  38. Pathirage, C.S.N., Li, J., Li, L., Hao, H., Liu, W. and Ni, P. (2018), "Structural damage identification based on autoencoder neural networks and deep learning", Eng. struct., 172(April), 13-28. https://doi.org/10.1016/j.engstruct.2018.05.109.
  39. Peeters, B. and Roeck, G. De (2001), "Stochastic system identification for operational modal analysis: A Review", J. Dyn. Syst. Meas. Control. Trans. Asme, 123(4), 659-667. https://doi.org/10.1115/1.1410370.
  40. Ramachandran, P., Zoph, B. and Le, Q.V (2017), "Searching for activation functions", International Conference on Learning Representations, 1-13.
  41. Seyedpoor, S.M. and Nopour, M.H. (2020), "A two-step method for damage identification in moment frame connections using support vector machine and differential evolution algorithm", Appl. Soft Comput. J., 88, 106008. https://doi.org/10.1016/j.asoc.2019.106008.
  42. Stalling, J.M. and Frank, K.H. (1991), "Stay-cable fatigue behavior", J. Struct. Eng., 117(3), 936-950. https://doi.org/10.1061/(asce)0733-9445(1991)117:3(936).
  43. Svensson, H. (2013), Cable-Stayed Bridges: 40 Years of Experience Worldwide Ernst & Sohn.
  44. Svozil, D., Kvasnicka, V. and Pospichal, J. (1997), "Introduction to multi-layer feed-forward neural networks", Chemom. Intell. Lab. Syst., 39. https://doi.org/https://doi.org/10.1016/S0169-7439(97)00061-0.
  45. 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.
  46. Thai, H.T. and Kim, S.E. (2007), "Practical Nonlinear Dynamic Analysis of Cable-Stayed Bridge", Construction, 13-16.
  47. Thai, H.T. and Kim, S.E. (2008), "Second-order inelastic dynamic analysis of three-dimensional cable-stayed bridges" , Steel Struct., 8, 205-214.
  48. 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.
  49. 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.
  50. 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.
  51. 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.
  52. Vonder-Malsburg, C. (1986), "Principles of neurodynamics: perceptrons and the theory of brain mechanisms", Brain Theory, 245-248. https://doi.org/10.1007/978-3-642-70911-1_20.
  53. 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.
  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, highlyperformant package for graph neural networks", Comput. Sci., Mathem., 1-18. http://arxiv.org/abs/1909.01315.
  55. Wang, S., Jiang, Y., Xu, M., Li, Y. and Li, Z. (2020), "Structural damage identification using an iterative two-stage method combining a modal energy based index with the BAS algorithm", Steel Compos. Struct., 36(1), 31-45. https://doi.org/10.12989/scs.2020.36.1.031.
  56. Wickramasinghe, W.R., Thambiratnam, D.P., Chan, T.H.T. and Nguyen, T. (2016), "Vibration characteristics and damage detection in a suspension bridge", J. Sound Vib., 375, 254-274. https://doi.org/10.1016/j.jsv.2016.04.025.
  57. 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.
  58. Xu, Y., Qian, Y., Song, G. and Guo, K. (2015), "Damage detection using finite element model updating with an improved optimization algorithm", Steel Compos. Struct., 19(1), 191-208. https://doi.org/10.12989/scs.2015.19.1.191.
  59. Yeung, W.T. and Smith, J.W. (2005), "Damage detection in bridges using neural networks for pattern recognition of vibration signatures", Eng. Struct., 27(5), 685-698. https://doi.org/10.1016/j.engstruct.2004.12.006.
  60. Zhang, J. and Au, F.T.K. (2013), "Effect of baseline calibration on assessment of long-term performance of cable-stayed bridges", Eng. Fail. Anal., 35, 234-246. https://doi.org/10.1016/j.engfailanal.2013.01.031.
  61. 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.
  62. Zhang, S., Shen, R., Dai, K., Wang, L., De Roeck, G. and Lombaert, G. (2019), "A methodology for cable damage identification based on wave decomposition", J. Sound Vib., 442, 527-551. https://doi.org/10.1016/j.jsv.2018.11.018.
  63. Zhu, J.J., Huang, M. and Lu, Z.R. (2017), "Bird mating optimizer for structural damage detection using a hybrid objective function", Swarm Evol. Comput., 35(September 2016), 41-52. https://doi.org/10.1016/j.swevo.2017.02.006.