Automated damage diagnosis of concrete jack arch beam using optimized deep stacked autoencoders and multi-sensor fusion

A novel hybrid framework of optimized deep learning models combined with multi-sensor fusion is developed for condition diagnosis of concrete arch beam. The vibration responses of structure are first processed by principal component analysis for dimensionality reduction and noise elimination. Then,...

Full description

Saved in:

Bibliographic Details
Published in:	Developments in the built environment Vol. 14; p. 100128
Main Authors:	Yu, Yang, Li, Jiantao, Li, Jianchun, Xia, Yong, Ding, Zhenghao, Samali, Bijan
Format:	Journal Article
Language:	English
Published:	Elsevier Ltd 01.04.2023 Elsevier
Subjects:	Deep stacked autoencoders Multi-sensor fusion Structural damage diagnosis Whale optimization algorithm Multi-sensor fusion Whale optimization algorithm Deep stacked autoencoders Structural damage diagnosis
ISSN:	2666-1659, 2666-1659
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	A novel hybrid framework of optimized deep learning models combined with multi-sensor fusion is developed for condition diagnosis of concrete arch beam. The vibration responses of structure are first processed by principal component analysis for dimensionality reduction and noise elimination. Then, the deep network based on stacked autoencoders (SAE) is established at each sensor for initial condition diagnosis, where extracted principal components and corresponding condition categories are inputs and output, respectively. To enhance diagnostic accuracy of proposed deep SAE, an enhanced whale optimization algorithm is proposed to optimize network meta-parameters. Eventually, Dempster-Shafer fusion algorithm is employed to combine initial diagnosis results from each sensor to make a final diagnosis. A miniature structural component of Sydney Harbour Bridge with artificial multiple progressive damages is tested in laboratory. The results demonstrate that the proposed method can detect structural damage accurately, even under the condition of limited sensors and high levels of uncertainties. •A hybrid framework based on PCA, DSAE models and data fusion was proposed for structural damage diagnosis.•An enhanced WOA was developed to optimize the meta-parameters of DSAE model.•The DASE with optimal meta-parameters has higher prediction accuracy than other learning models.•Combination of optimized DSAE and data fusion can effectively enhance accuracy and confidence of diagnosis result.
ISSN:	2666-1659 2666-1659
DOI:	10.1016/j.dibe.2023.100128