原文传递
Probabilistic Framework with Bayesian Optimization for Predicting Typhoon-Induced Dynamic Responses of a Long-Span Bridge
| 题名： | Probabilistic Framework with Bayesian Optimization for Predicting Typhoon-Induced Dynamic Responses of a Long-Span Bridge |
| 正文语种： | eng |
| 作者： | Zhang, Yi-Ming;Wang, Hao;Mao, Jian-Xiao;Xu, Zi-Dong;Zhang, Yu-Feng |
| 作者单位： | Southeast Univ Minist Educ Key Lab Concrete & Prestressed Concrete Struct Nanjing 211189 Peoples R China|Monash Univ Dept Civil Engn Clayton Vic 3800 Australia;Southeast Univ Minist Educ Key Lab Concrete & Prestressed Concrete Struct Nanjing 211189 Peoples R China;Southeast Univ Minist Educ Key Lab Concrete & Prestressed Concrete Struct Nanjing 211189 Peoples R China;Southeast Univ Minist Educ Key Lab Concrete & Prestressed Concrete Struct Nanjing 211189 Peoples R China;Jiangsu Transportat Res Inst Co Ltd State Key Lab Safety & Hlth In Serv Long Span Bri Nanjing 211112 Peoples R China |
| 关键词： | Typhoon-induced response;Probabilistic prediction;Quantile random forest;Bayesian optimization;Long-span bridge |
| 摘要： | The long-span bridge, characterized by slenderness and flexibility, is particularly sensitive to wind action. Extreme wind events, including typhoons and hurricanes, will threaten the safety and serviceability of long-span bridges. More specifically, long-span bridges usually experience significant vibrations under typhoon events, increasing the risk of serviceability failure and traffic accidents. An efficient way to mitigate the risk of such threats is to predict the typhoon-induced response (TIR). Traditionally, TIR prediction of long-span bridges is usually carried out based on finite-element (FE) simulations. Due to the assumptions in formulating the FE model and establishing the wind load (e.g., boundary conditions, simplified structural elements, stationary aerodynamic wind forces), prediction accuracy is inevitably undermined. In this work, as opposed to traditional FE-based analysis, TIR is predicted in real time from a data-driven perspective. Quantile random forest (QRF) with Bayesian optimization is presented as the data-driven method for probabilistic prediction. A long-span cable-stayed bridge with a main span of 1,088 m is used as a test bed to illustrate the effectiveness of the present method. Other optimization algorithms used with QRF (grid search and random search) and response surface methodology (RSM) are also implemented for comparison purposes. Results indicate that QRF with Bayesian optimization can provide reliable probabilistic estimations allowing for quantification of uncertainty in prediction. It shows superior performance compared with other optimization algorithms and models in terms of accuracy and computa-tional expense. The analysis and predictive framework for TIR are expected to provide insight into data-driven structural wind engineering. DOI: 10.1061/(ASCE)ST.1943-541X.0002881. (c) 2020 American Society of Civil Engineers. |
| 出版年： | 2021 |
| 期刊名称： | Journal of Structural Engineering |
| 卷： | 147 |
| 期： | 1 |
| 页码： | 04020297.1-04020297.16 |
相关文献
- Buffeting Analysis of Long-Span Bridges under Typhoon Winds with Time-Varying Spectra and Coherences
- Measurement of Wind Effects on a Kilometer-Level Cable-Stayed Bridge during Typhoon Haikui
- Tropical Storm-Induced Buffeting Response of Long-Span Bridges: Enhanced Nonstationary Buffeting Force Model
- Analysis of Multimode Coupled Buffeting Response of Long-Span Bridges to Nonstationary Winds with Force Parameters from Stationary Wind
- Sparse Bayesian Identification of Temperature-Displacement Model for Performance Assessment and Early Warning of Bridge Bearings
- Framework of Nonlinear Dynamic Simulation of Long-Span Cable-Stayed Bridge and Traffic System Subjected to Cable-Loss Incidents
检索历史
应用推荐
