Rapid and automated seismic design of cable restrainer for simply supported bridges crossing fault rupture zones using explainable machine learning

Earthquakes in recent decades have demonstrated that fault-crossing simply supported bridges were susceptible to damage caused by the fault-induced permanent ground dislocation. Cable restrainer can potentially reduce the relative displacement of bridge spans, but the current seismic design method f...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhang, Fan, Fu, Yuguang, Wang, Jingquan
Other Authors: School of Civil and Environmental Engineering
Format: Article
Language:English
Published: 2025
Subjects:
Online Access:https://hdl.handle.net/10356/182856
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-182856
record_format dspace
spelling sg-ntu-dr.10356-1828562025-03-04T08:09:06Z Rapid and automated seismic design of cable restrainer for simply supported bridges crossing fault rupture zones using explainable machine learning Zhang, Fan Fu, Yuguang Wang, Jingquan School of Civil and Environmental Engineering Engineering Fault-crossing bridge Seismic design of restrainer Earthquakes in recent decades have demonstrated that fault-crossing simply supported bridges were susceptible to damage caused by the fault-induced permanent ground dislocation. Cable restrainer can potentially reduce the relative displacement of bridge spans, but the current seismic design method for restrainer is time-consuming and labor-intensive. This study aims to develop a rapid and automated seismic design method for cable restrainer using explainable machine learning (ML) models. To do this, a large database was first generated based on the current design approach. ML algorithms were utilized to develop classification models to determine the design classes and then regression models to estimate the restrainer stiffness for the fault-crossing bridges. Furthermore, SHapley Additive exPlanations (SHAP) analysis was utilized to provide interpretations for the best regression model. In particular, an empirical formula and two explainable prediction models by combining the empirical formula with simplified ML models were finally proposed to facilitate the design for engineers. Results show that the proposed design method can provide accurate and robust results of bridge restrainers. Within the method, artificial neural network was selected among nine ML models, because of its highest accuracy for both classification and regression. The SHAP analysis reveals that, the allowable displacement has a negative nonlinear effect, while permanent ground dislocation and initial relative displacement present positive nonlinear effects. The proposed empirical formula for restrainer design can provide conservative estimations with an accuracy of 79 %, whereas the proposed explainable prediction models have a high accuracy of 94 % and are significantly efficient and user-friendly. Ministry of Education (MOE) Nanyang Technological University The authors would like to acknowledge financially supported by Natural Science Foundation of Jiangsu Province (Grant No. BK20241337), NTU Start-up Grant 021323-00001, MOE AcRF Tier 1 Grants (No. RG121/21 and No. RG136/22), Jiangsu transportation research project (CT-SGZT-30), the National Key Research and Development Program of China (2022YFB2302501), National Natural Science Foundation of China (Grant No. 42430711), and Academician special project of CCCC (Grant No. YSZX-01-2023-01-A). 2025-03-04T08:09:05Z 2025-03-04T08:09:05Z 2024 Journal Article Zhang, F., Fu, Y. & Wang, J. (2024). Rapid and automated seismic design of cable restrainer for simply supported bridges crossing fault rupture zones using explainable machine learning. Soil Dynamics and Earthquake Engineering, 187, 109011-. https://dx.doi.org/10.1016/j.soildyn.2024.109011 0267-7261 https://hdl.handle.net/10356/182856 10.1016/j.soildyn.2024.109011 2-s2.0-85205938308 187 109011 en NTU SUG 021323-00001 RG121/21 RG136/22 Soil Dynamics and Earthquake Engineering © 2024 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering
Fault-crossing bridge
Seismic design of restrainer
spellingShingle Engineering
Fault-crossing bridge
Seismic design of restrainer
Zhang, Fan
Fu, Yuguang
Wang, Jingquan
Rapid and automated seismic design of cable restrainer for simply supported bridges crossing fault rupture zones using explainable machine learning
description Earthquakes in recent decades have demonstrated that fault-crossing simply supported bridges were susceptible to damage caused by the fault-induced permanent ground dislocation. Cable restrainer can potentially reduce the relative displacement of bridge spans, but the current seismic design method for restrainer is time-consuming and labor-intensive. This study aims to develop a rapid and automated seismic design method for cable restrainer using explainable machine learning (ML) models. To do this, a large database was first generated based on the current design approach. ML algorithms were utilized to develop classification models to determine the design classes and then regression models to estimate the restrainer stiffness for the fault-crossing bridges. Furthermore, SHapley Additive exPlanations (SHAP) analysis was utilized to provide interpretations for the best regression model. In particular, an empirical formula and two explainable prediction models by combining the empirical formula with simplified ML models were finally proposed to facilitate the design for engineers. Results show that the proposed design method can provide accurate and robust results of bridge restrainers. Within the method, artificial neural network was selected among nine ML models, because of its highest accuracy for both classification and regression. The SHAP analysis reveals that, the allowable displacement has a negative nonlinear effect, while permanent ground dislocation and initial relative displacement present positive nonlinear effects. The proposed empirical formula for restrainer design can provide conservative estimations with an accuracy of 79 %, whereas the proposed explainable prediction models have a high accuracy of 94 % and are significantly efficient and user-friendly.
author2 School of Civil and Environmental Engineering
author_facet School of Civil and Environmental Engineering
Zhang, Fan
Fu, Yuguang
Wang, Jingquan
format Article
author Zhang, Fan
Fu, Yuguang
Wang, Jingquan
author_sort Zhang, Fan
title Rapid and automated seismic design of cable restrainer for simply supported bridges crossing fault rupture zones using explainable machine learning
title_short Rapid and automated seismic design of cable restrainer for simply supported bridges crossing fault rupture zones using explainable machine learning
title_full Rapid and automated seismic design of cable restrainer for simply supported bridges crossing fault rupture zones using explainable machine learning
title_fullStr Rapid and automated seismic design of cable restrainer for simply supported bridges crossing fault rupture zones using explainable machine learning
title_full_unstemmed Rapid and automated seismic design of cable restrainer for simply supported bridges crossing fault rupture zones using explainable machine learning
title_sort rapid and automated seismic design of cable restrainer for simply supported bridges crossing fault rupture zones using explainable machine learning
publishDate 2025
url https://hdl.handle.net/10356/182856
_version_ 1826362278015926272