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

doi:10.1016/j.autcon.2021.103665

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

Department of Architecture and Architectural Engineering

Research output: Contribution to journal › Article › peer-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 language	English
Article number	103665
Journal	Automation in Construction
Volume	126
DOIs	https://doi.org/10.1016/j.autcon.2021.103665
Publication status	Published - 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

Access to Document

10.1016/j.autcon.2021.103665

Cite this

@article{3b4321c43d4f47d3ad9f05160f1c89b6,

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

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.",

author = "Oh, {Byung Kwan} and Park, {Hyo Seon} and Branko Glisic",

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: {\textcopyright} 2021",

year = "2021",

month = jun,

doi = "10.1016/j.autcon.2021.103665",

language = "English",

volume = "126",

journal = "Automation in Construction",

issn = "0926-5805",

publisher = "Elsevier",

}

TY - JOUR

T1 - Prediction of long-term strain in concrete structure using convolutional neural networks, air temperature and time stamp of measurements

AU - Oh, Byung Kwan

AU - Park, Hyo Seon

AU - Glisic, Branko

N1 - 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

PY - 2021/6

Y1 - 2021/6

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85102361606&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85102361606&partnerID=8YFLogxK

U2 - 10.1016/j.autcon.2021.103665

DO - 10.1016/j.autcon.2021.103665

M3 - Article

AN - SCOPUS:85102361606

VL - 126

JO - Automation in Construction

JF - Automation in Construction

SN - 0926-5805

M1 - 103665

ER -

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

Abstract

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this