Affiliation:
1. College of Civil Engineering and Architecture Zhejiang University Hangzhou China
2. Center For Balance Architecture Zhejiang University Hangzhou China
3. College of Risk Management Institute National University of Singapore Singapore Singapore
4. Architectural design and research institute Zhejiang University Hangzhou China
Abstract
AbstractBridge inspection ensures that in‐service bridges are managed and maintained in conformity. To enhance the accuracy and efficiency of bridge inspection, an automatic hierarchical model is proposed, which enables the classification and correlation of bridge surface images at three levels, namely, at the structure, component, and defect type level. Thus, the impact of both the defect types and the affected components on bridge safety can be simultaneously considered. The proposed model uses a group of sub‐models instead of the common flat network to realize the multiple tasks, which is advantageous in accuracy, training simplicity, and scalability. The classification accuracy of the hierarchical model in three levels has reached 96%, 92%, and 81%. Results demonstrate the effectiveness of the proposed method in the classification of multi‐scale targets. This study may provide a new strategy for developing a systematic and easily adaptable detection framework for practical bridge engineering.
Funder
National Natural Science Foundation of China
Science Fund for Distinguished Young Scholars of Zhejiang Province
Subject
Computational Theory and Mathematics,Computer Graphics and Computer-Aided Design,Computer Science Applications,Civil and Structural Engineering,Building and Construction
Reference70 articles.
1. Neural Networks and Deep Learning
2. A dynamic ensemble learning algorithm for neural networks;Alam K. M. R.;Neural Computing and Applications,2020
3. American Society of Civil Engineers. (2017).2017 report card for America's infrastructure. American Society of Civil Engineers.https://infrastructurereportcard.org/wp‐content/uploads/2016/10/2017‐Infrastructure‐Report‐Card.pdf
4. A new music‐empirical wavelet transform methodology for time–frequency analysis of noisy nonlinear and non‐stationary signals;Amezquita‐Sanchez J. P.;Digital Signal Processing,2015
5. Wireless smart sensors for monitoring the health condition of civil infrastructure;Amezquita‐Sanchez J. P.;Scientia Iranica,2018
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献