Application of Artificial Neural Networks for Developing Temperature-Dependent Fragility Curves for Vulnerability Assessment of I-Girder Bridges

Sabouri Ghomi, Saeid; Shiravand, Saman; Zare Zardeyni, Mohammad Mahdi; Rabiee, Najib

doi:10.61186/NMCE.2504.1087

Application of Artificial Neural Networks for Developing Temperature-Dependent Fragility Curves for Vulnerability Assessment of I-Girder Bridges

Document Type : Research

Authors

Saeid Sabouri Ghomi ¹

Saman Shiravand ²

Mohammad Mahdi Zare Zardeyni ³

Najib Rabiee ³

¹ Professor, Department of Civil and Environmental Engineering, K.N. Toosi University of Technology, Tehran, Iran

² PhD candidate,, Department of Civil and Environmental Engineering, K.N. Toosi University of Technology, Tehran, Iran

³ MSc student, Department of Civil and Environmental Engineering, K.N. Toosi University of Technology, Tehran, Iran

10.61186/NMCE.2504.1087

Abstract

Although previous investigations have shown that a bridge’s overall capacity may remain largely intact after a fire, its seismic performance in the aftermath of such events remains poorly understood. The primary objective of this study is to investigate the influence of fire on the seismic performance of a multi-span simply supported steel I-girder (MSSSS-IG). To achieve this, an artificial neural network (ANN) model was used to develop a multivariate probabilistic seismic demand model (MPSDM) and fragility curve. A total of 1,600 three-dimensional MSSSS-IG bridge models were generated using the OpenSees tool, incorporating material and geometric variability through Latin Hypercube Sampling (LHS). A set of 1,600 ISO 834 fires featuring peak temperatures varying between 200 °C to 1,000 °C was developed. The maximum temperature in the column was determined through heat transfer analysis. Accordingly, column reduction factors were computed via Eurocode provisions. Bridge, reduction factors, and input ground motion records were randomly paired using nonlinear response history analysis (NRHA). The XGBoost technique and grid search were employed to identify the important features and calibration hyperparameters of ANNs, respectively. It can be pointed out that the proposed ANN algorithm accurately estimates the component demands. Moreover, fragility findings demonstrate that local fire exposure in the column, ranging from 12.30 % and 22.30 %, increases the probability of system-level bridge failure.

Keywords

multi-hazard

post-fire seismic performance

artificial neural networks

steel I-girder bridges

high temperatures

grid search

Subjects

Earthquake Engineering

[1] N. Rabiee, S. Shiravand, and S. Soroushian, “Post-fire seismic capacity estimation using temperature-varying fragility curve in bridges,” Structures, vol. 76, no. March, p. 108876, 2025, doi: 10.1016/j.istruc.2025.108876.

[2] W. Wright, B. Lattimer, M. Woodworth, M. Nahid, and E. Sotelino, “Highway Bridge Fire Hazard Assessment,” no. 12, 2013.

[3] G. C. Lee, S. B. Mohan, C. Huang, and B. N. Fard, “A study of US bridge failures,” 2013.

[4] J. Alos-Moya, I. Paya-Zaforteza, A. Hospitaler, and P. Rinaudo, “Valencia bridge fire tests: Experimental study of a composite bridge under fire,” J. Constr. Steel Res., vol. 138, pp. 538–554, 2017, doi: 10.1016/j.jcsr.2017.08.008.

[5] J. Hu, A. Usmani, A. Sanad, and R. Carvel, “Fire resistance of composite steel & concrete highway bridges,” J. Constr. Steel Res., vol. 148, pp. 707–719, 2018, doi: 10.1016/j.jcsr.2018.06.021.

[6] C. Cui, A. Chen, and R. Ma, “Stability assessment of a suspension bridge considering the tanker fire nearby steel-pylon,” J. Constr. Steel Res., vol. 172, p. 106186, 2020, doi: 10.1016/j.jcsr.2020.106186.

[7] M. Ok, K. Kim, J. Hyun, and M. Kyum, “Fire risk assessment of cable bridges for installation of firefighting facilities,” vol. 115, 2020.

[8] R. Ma, C. Cui, M. Ma, and A. Chen, “Numerical simulation and simplified model of vehicle-induced bridge deck fire in the full-open environment considering wind effect,” Struct. Infrastruct. Eng., vol. 17, no. 12, pp. 1698–1709, 2021, doi: 10.1080/15732479.2020.1832535.

[9] G. Peris-Sayol, I. Paya-Zaforteza, J. Alos-Moya, and A. Hospitaler, “Analysis of the influence of geometric, modeling and environmental parameters on the fire response of steel bridges subjected to realistic fire scenarios,” Comput. Struct., vol. 158, pp. 333–345, 2015, doi: 10.1016/j.compstruc.2015.06.003.

[10] C. Song, G. Zhang, V. Kodur, Y. Zhang, and S. He, “Fire response of horizontally curved continuous composite bridge girders,” J. Constr. Steel Res., vol. 182, p. 106671, 2021, doi: 10.1016/j.jcsr.2021.106671.

[11] J. Hu, R. Carvel, and A. Usmani, “Bridge fires in the 21st century: A literature review,” Fire Saf. J., vol. 126, no. February, p. 103487, 2021, doi: 10.1016/j.firesaf.2021.103487.

[12] B. Behnam and H. Ronagh, “Performance of reinforced concrete structures subjected to Fire following earthquake,” Eur. J. Environ. Civ. Eng., vol. 17, no. 4, pp. 270–292, 2013, doi: 10.1080/19648189.2013.783882.

[13] M. Memari, H. Mahmoud, and B. Ellingwood, “Post-earthquake fire performance of moment resisting frames with reduced beam section connections,” J. Constr. Steel Res., vol. 103, pp. 215–229, 2014, doi: 10.1016/j.jcsr.2014.09.008.

[14] S. Ni and A. C. Birely, “A simplified model for the post-fire earthquake flexural response of reinforced concrete walls with boundary elements,” Eng. Struct., vol. 175, no. July, pp. 721–730, 2018, doi: 10.1016/j.engstruct.2018.08.044.

[15] Y. Deng, M. Zhang, D. M. Feng, and A. Q. Li, “Predicting fatigue damage of highway suspension bridge hangers using weigh-in-motion data and machine learning,” Struct. Infrastruct. Eng., vol. 17, no. 2, pp. 233–248, 2021, doi: 10.1080/15732479.2020.1734632.

[16] N. Hider, A. Marahlleh, H. Liu, A. M. Asce, O. Abudayyeh, and M. Asce, “Deterioration Prediction Models for the Condition Assessment of Concrete Bridge Decks Using Machine Learning Techniques,” 2015.

[17] Y. Shi, L. Xiong, H. Qin, J. Han, and Z. Sun, “Seismic fragility analysis of LRB-isolated bridges considering the uncertainty of regional temperatures using BP neural networks,” Structures, vol. 44, no. August, pp. 566–578, 2022, doi: 10.1016/j.istruc.2022.08.035.

[18] Z. Wang, W. Zhang, Y. Zhang, and Z. Liu, “Temperature Prediction of Flat Steel Box Girders of Long-Span Bridges Utilizing In Situ Environmental Parameters and Machine Learning,” J. Bridg. Eng., vol. 27, no. 3, pp. 1–18, 2022, doi: 10.1061/(asce)be.1943-5592.0001840.

[19] F. Wedel and S. Marx, “Application of machine learning methods on real bridge monitoring data,” Eng. Struct., vol. 250, no. February 2021, p. 113365, 2022, doi: 10.1016/j.engstruct.2021.113365.

[20] V. K. Kodur and M. Z. Naser, “Classifying bridges for the risk of fire hazard via competitive machine learning,” Adv. Bridg. Eng., vol. 2, no. 1, 2021, doi: 10.1186/s43251-020-00027-2.

[21] J. Feng, K. Gao, W. Gao, Y. Liao, and G. Wu, “Machine learning-based bridge cable damage detection under stochastic effects of corrosion and fire,” Eng. Struct., vol. 264, no. January, p. 114421, 2022, doi: 10.1016/j.engstruct.2022.114421.

[22] E. Aziz and V. Kodur, “An approach for evaluating the residual strength of fire exposed bridge girders,” J. Constr. Steel Res., vol. 88, pp. 34–42, 2013, doi: 10.1016/j.jcsr.2013.04.007.

[23] S. Shiravand, N. Rabiee, and S. Soroushian, “Fuzzy analytical hierarchy process and component importance measures for selection optimal intensity measures and development fragility curves in bridges,” Soil Dyn. Earthq. Eng., vol. 194, no. February, p. 109352, 2025, doi: 10.1016/j.soildyn.2025.109352.

[24] K. Ramanathan, J. E. Padgett, and R. DesRoches, “Temporal evolution of seismic fragility curves for concrete box-girder bridges in California,” Eng. Struct., vol. 97, pp. 29–46, 2015, doi: 10.1016/j.engstruct.2015.03.069.

[25] K. N. Ramanathan, “Next generation seismic fragility curves for california bridges incorporating the evolution in seismic design philosophy,” 2012.

[26] S. Mazzoni, F. Mckenna, M. Scott, and G. Fenves, “OpenSees Command Language Manual,” Pacific Earthq. Eng. Res. Cent., vol. 264, no. 1, pp. 137–158, 2006.

[27] A. Gomes and J. Appleton, “Nonlinear cyclic stress-strain relationship of reinforcing bars including buckling,” Eng. Struct., vol. 19, no. 10, pp. 822–826, 1997, doi: 10.1016/S0141-0296(97)00166-1.

[28] R. P. Dhakal and K. Maekawa, “Modeling for Postyield Buckling of Reinforcement,” J. Struct. Eng., vol. 128, no. 9, pp. 1139–1147, 2002, doi: 10.1061/(asce)0733-9445(2002)128:9(1139).

[29] Chang G. A. and J. B. Mander, “Seismic energy based fatigue damage analysis of bridge columns: Part I - Evaluation of seismic capacity.NCEER Technical Report No. NCEER-94-0006,” 1994.

[30] S. H. Megally, P. F. Silva, and F. Seible, “Seismic Response of Sacrificial,” Security, no. 59, 2002.

[31] A. Shamsabadi and L. Yan, “Closed-F[1] A. Shamsabadi and L. Yan, ‘Closed-Form Force-Displacement Backbone Curves for Bridge Abutment-Backfill Systems,’ pp. 1–10, 2008, doi: 10.1061/40975(318)159.

[32] P. Wilson and A. Elgamal, “Large-Scale Passive Earth Pressure Load-Displacement Tests and Numerical Simulation,” J. Geotech. Geoenvironmental Eng., vol. 136, no. 12, pp. 1634–1643, 2010, doi: 10.1061/(asce)gt.1943-5606.0000386.

[33] J. W. Baker, T. Lin, and S. K. Shahi, “New Ground Motion Selection Procedures and Selected Motions for the PEER Transportation Research Program - DRAFT,” PEER Rep., vol. 03, no. March, p. 87, 2011.

[34] L. Jiang, Y. Jiang, Z. Zhang, and A. Usmani, “Thermal Analysis Infrastructure in OpenSees for Fire and its Smart Application Interface Towards Natural Fire Modelling,” Fire Technol., vol. 57, no. 6, pp. 2955–2980, 2021, doi: 10.1007/s10694-020-01071-0.

[35] M. Chaboki, M. Heshmati, and A. A. Aghakouchak, “Investigating the behaviour of steel framed-tube and moment-resisting frame systems exposed to fire,” Structures, vol. 33, no. December 2020, pp. 1802–1818, 2021, doi: 10.1016/j.istruc.2021.05.053.

[36] H. Cilsalar, “Post-earthquake fire collapse performance and residual story drift fragility of two-dimensional structural frames,” Structures, vol. 38, no. February, pp. 1438–1452, 2022, doi: 10.1016/j.istruc.2022.03.001.

[37] Y. S. Wang, H. Zhou, and J. Y. Wu, “Hybrid fire collapse simulation of reinforced concrete structures under localized fires,” Eng. Struct., vol. 292, no. May, p. 116525, 2023, doi: 10.1016/j.engstruct.2023.116525.

[38] Eurocode 2: Design of concrete structures - Part 1-2: General rules, vol. 2, no. 2004. 2011.

[39] K. R. Kodur, M. M. S. Dwaikat, and M. B. Dwaikat, “High-temperature properties of concrete for fire resistance modeling of structures,” ACI Mater. J., vol. 106, no. 4, p. 390, 2009.

[40] A. Géron, Hands-on Machine Learning whith Scikit-Learing, Keras and Tensorfow. 2019.

[41] T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., vol. 13-17-Augu, pp. 785–794, 2016, doi: 10.1145/2939672.2939785.

[42] H. Liu, L. Liu, and H. Zhang, “Boosting feature selection using information metric for classification,” Neurocomputing, vol. 73, no. 1–3, pp. 295–303, 2009, doi: 10.1016/j.neucom.2009.08.012.

[43] A. Alsahaf, N. Petkov, V. Shenoy, and G. Azzopardi, “A framework for feature selection through boosting,” Expert Syst. Appl., vol. 187, no. June 2021, p. 115895, 2022, doi: 10.1016/j.eswa.2021.115895.

[44] Federal Emergency Management Agency (FEMA), “HAZUS-MH MR4 Multi-Hazar d Loss Estimation Methodology – Earthquake Model: Technical Manual. Department of Homeland Security,” Fed. Emerg. Manag. Agency, Washington, …, pp. 257–261, 2003, [Online]. Available: www.fema.gov/plan/prevent/hazus.