Prediction of long-term strain in concrete structure using convolutional neural networks, air temperature and time stamp of measurements

Byung Kwan Oh, Hyo Seon Park, Branko Glisic

Research output: Contribution to journalArticlepeer-review

Abstract

A data prediction method for long-term strain measurements from concrete structures based on the strong correlation between air temperature and structural response is proposed. A convolutional neural network (CNN) is employed to capture and define the relationship between the structural response and air temperature. The CNN is trained using measurements of air temperature and strain collected before the data interruption. To reflect the time-dependent long-term behavior of a concrete structure, the air temperature and corresponding time information are simultaneously utilized in the input layer of the proposed CNN. The trained CNN is then used to estimate the strain in the structure using only the air temperature data from the weather station in the event of a data loss from the structure's sensors. The presented method is validated using long-term data from fiber optic sensors embedded in a concrete footbridge at Princeton University and air temperature data from a nearby weather station.

Original languageEnglish
Article number103665
JournalAutomation in Construction
Volume126
DOIs
Publication statusPublished - 2021 Jun

Bibliographical note

Funding Information:
This work was supported by a National Research Foundation of Korea (NRF) grant funded by the Korea government (Ministry of Science, ICT & Future Planning, MSIP) (No. 2021R1A2C3008989 ). We would like to thank Steve Hancock and Turner Construction Company ; Ryan Woodward and Ted Zoli, HNTB Corporation ; Dong Lee and A.G. Construction Corporation ; Steven Mancini and Timothy R. Wintermute, Vollers Excavating & Construction, Inc .; SMARTEC SA, Switzerland ; Micron Optics, Inc ., Atlanta, GA. In addition the following personnel, departments, and offices from Princeton University supported and helped realization of the project: Geoffrey Gettelfinger, James P. Wallace, Miles Hersey, Paul Prucnal, Yanhua Deng, Mable Fok; Faculty and staff of Department of Civil and Environmental Engineering and our students: Maryanne Wachter, Jessica Hsu, George Lederman, Kenneth Liew, Chienchuan Chen, Allison Halpern, Morgan Neal, Daniel Reynolds, Konstantinos Bakis, Daniel Schiffner, Dorotea Sigurdardottir, David Hubbel, Yao Yao, Hiba Abdel-Jaber, Kaitlyn Kliewer, and Jack Reilly.

Publisher Copyright:
© 2021

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Civil and Structural Engineering
  • Building and Construction

Fingerprint Dive into the research topics of 'Prediction of long-term strain in concrete structure using convolutional neural networks, air temperature and time stamp of measurements'. Together they form a unique fingerprint.

Cite this