原文传递
Mapping of Temperature-Induced Response Increments for Monitoring Long-Span Steel Truss Arch Bridges Based on Machine Learning
| 题名： | Mapping of Temperature-Induced Response Increments for Monitoring Long-Span Steel Truss Arch Bridges Based on Machine Learning |
| 正文语种： | eng |
| 作者： | Zhu, Qingxin;Wang, Hao;Spencer, B. F.;Mao, Jianxiao |
| 作者单位： | Southeast Univ Key Lab C&Pc Struct Minist Educ Nanjing 211189 Peoples R China;Southeast Univ Key Lab C&Pc Struct Minist Educ Nanjing 211189 Peoples R China;Univ Illinois Dept Civil & Environm Engn Civil Engn Urbana IL 61801 USA;Southeast Univ Key Lab C&Pc Struct Minist Educ Nanjing 211189 Peoples R China |
| 关键词： | Mapping;Temperature;Temperature increments;Temperature-induced responses;Field monitoring data |
| 摘要： | Temperature-induced responses have been found to be sensitive to changes in bridge properties. Accordingly, researchers have sought to develop temperature-response mappings that could be used in assessing bridge conditions; to date, obtaining sufficiently precise mappings analytically has proven intractable. Alternatively, numerous researchers have directly developed mappings between temperature and the associated responses using measured data. However, temperature-induced responses are a function of the temperatures throughout the entire bridge, and such spatial temperature distributions using a limited number of sensors are challenging to capture, particularly for steel truss bridges, due to the large number and variety of structural members. Mappings that have been obtained are generally a function of the long-term fluctuations, corresponding to daily variations; the short-term fluctuations (i.e., higher-frequency components) in temperature data are neglected. This paper first proposes that the relationship between increments in temperature and the associated increments in responses can be used as a surrogate to assess the bridge performance. Simulation results show that the statistical distribution of the error between measured and predicted response increments can be used for identifying abnormal structural behavior. Then, various mappings for both displacement and strain increments are explored and verified using field monitoring data. The mapping with all temperature sensors performs the best; principal component analysis (PCA) can effectively reduce the dimension of input without compromising accuracy. In addition, the recorded time of temperature data is validated to be a useful indicator of the spatial temperature distribution in bridges, which can be used to improve the performance of the mappings when the bridge has only a few temperature sensors. These findings provide an improved approach for mapping the relationship between increments in temperature to increments in temperature-induced responses that shows promise for identifying abnormal bridge behavior. |
| 出版年： | 2022 |
| 期刊名称： | Journal of structural engineering |
| 卷： | 148 |
| 期： | 5 |
| 页码： | 04022034.1-04022034.11 |
相关文献
- Sparse Bayesian Identification of Temperature-Displacement Model for Performance Assessment and Early Warning of Bridge Bearings
- Wind-Induced Buffeting Vibration of Long-Span Bridge Considering Geometric and Aerodynamic Nonlinearity Based on Reduced-Order Modeling
- Temperature-Based Structural Identification of Long-Span Bridges
- Seismic Design and Performance Evaluation of Long-Span Special Truss Moment Frames
- Probabilistic Framework with Bayesian Optimization for Predicting Typhoon-Induced Dynamic Responses of a Long-Span Bridge
- Buffeting Analysis of Long-Span Bridges under Typhoon Winds with Time-Varying Spectra and Coherences
检索历史
应用推荐
