Mitigating effects of temperature variations through probabilistic-based machine learning for vibration-based bridge sco
- PDF / 2,937,315 Bytes
- 16 Pages / 595.276 x 790.866 pts Page_size
- 73 Downloads / 204 Views
ORIGINAL PAPER
Mitigating effects of temperature variations through probabilistic‑based machine learning for vibration‑based bridge scour detection Wei Zheng1 · Feng Qian2 · Jinlei Shen3 · Feng Xiao4 Received: 11 October 2019 / Revised: 24 May 2020 / Accepted: 27 July 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract This paper presents a novel approach to mitigating the effect of temperature variations on the bridges’ dynamic modal properties for more reliably detecting scour damage around bridge piles based on the vibration-based measurements. The novelty of the presented approach lies in its ability to reasonably remove the impacts on the modal properties of bridges, particularly caused by changes in material properties and structural boundary conditions due to temperature variations without explicitly modeling these complex effects. The main idea is to adopt the probabilistic-based machine learning method, Gaussian Process Model, to learn the correlation between the changes of modal properties of a monitored bridge and the corresponding temperature variations from in situ sensor measurements, and probabilistically infer the bridge scour based on the modified vibration measurements, which have mitigated the identified impacts of temperature variations, by applying Bayesian inference through the Transitional Markov Chain Monte Carlo simulation. The proposed approach and its applicability are presented and validated through the numerical simulation of a prototype bridge, demonstrating its potential for practical application for mitigating effects of temperature variations or other environmental impacts for vibration-based Structural Health Monitoring. The limitation of the presented study and future research needs are also discussed. Keywords Temperature effect · Scour damage · Damage identification · Informatics · Artificial intelligence · Machine learning · Gaussian process model · Bayesian inference · Sampling · TMCMC
* Wei Zheng [email protected] Feng Qian [email protected] Jinlei Shen [email protected] Feng Xiao [email protected] 1
Department of Civil and Environmental Engineering, Jackson State University, 1400 J. R. Lynch Street, P. O. Box 17068, Jackson, MS 39217, USA
2
Department of Mechanical Engineering, Virginia Tech, 310 Goodwin Hall, 635 Prices Fork Road, MC 0238, Blacksburg, VA 24061, USA
3
Department of Civil and Systems Engineering, Johns Hopkins University, Homewood Campus, Latrobe Hall 205, Baltimore, MD 21218‑2682, USA
4
Department of Civil Engineering, Nanjing University of Science and Technology, No.200 Xiaolingwei, Nanjing 210094, Jiangsu, China
1 Introduction Bridge scour is referred to as the removal of sediment around the bridge foundation due to rapid floods and has been recognized as one of the primary causes of bridge failures. Direct field inspections of scour may disrupt traffics and cannot be carried out during the flood period. Advanced sensing instrumentations have been developed and deployed at piles or foundations of bridges
Data Loading...
