Artificial neural network for vertical displacement prediction of a bridge from strains (part 1): Girder bridge under moving vehicles

Hyun Su Moon, Suyeol Ok, Pang jo Chun, Yun Mook Lim

Research output: Contribution to journalArticle

Abstract

A real-time prediction method using a multilayer feedforward neural network is proposed for estimating vertical dynamic displacements of a bridge from the longitudinal strains of the bridge when vehicles pass across it. A numerical model for an existing five-girder bridge spanning 36 m proved by actual experimental values was used to verify the proposed method. To obtain a realistic vehicle distribution for the bridge, vehicle type and actual headways of moving vehicles were taken, and the measured vehicle distribution was generalized using Pearson Type III theory. Twenty-five load scenarios were created with assumed vehicle speeds of 40 km/h, 60 km/h, and 80 km/h. The results indicate that the model can reasonably predict the overall displacements of the bridge (which is difficult to measure) from the strain (which is relatively easy to measure) in the field in real time.

Original languageEnglish
Article number2881
JournalApplied Sciences (Switzerland)
Volume9
Issue number14
DOIs
Publication statusPublished - 2019 Jul 1

Fingerprint

vehicles
Neural networks
predictions
Feedforward neural networks
Multilayer neural networks
Numerical models
estimating

All Science Journal Classification (ASJC) codes

  • Materials Science(all)
  • Instrumentation
  • Engineering(all)
  • Process Chemistry and Technology
  • Computer Science Applications
  • Fluid Flow and Transfer Processes

Cite this

@article{0202cff32742428abcdff3956e2324a6,
title = "Artificial neural network for vertical displacement prediction of a bridge from strains (part 1): Girder bridge under moving vehicles",
abstract = "A real-time prediction method using a multilayer feedforward neural network is proposed for estimating vertical dynamic displacements of a bridge from the longitudinal strains of the bridge when vehicles pass across it. A numerical model for an existing five-girder bridge spanning 36 m proved by actual experimental values was used to verify the proposed method. To obtain a realistic vehicle distribution for the bridge, vehicle type and actual headways of moving vehicles were taken, and the measured vehicle distribution was generalized using Pearson Type III theory. Twenty-five load scenarios were created with assumed vehicle speeds of 40 km/h, 60 km/h, and 80 km/h. The results indicate that the model can reasonably predict the overall displacements of the bridge (which is difficult to measure) from the strain (which is relatively easy to measure) in the field in real time.",
author = "Moon, {Hyun Su} and Suyeol Ok and Chun, {Pang jo} and Lim, {Yun Mook}",
year = "2019",
month = "7",
day = "1",
doi = "10.3390/app9142881",
language = "English",
volume = "9",
journal = "Applied Sciences (Switzerland)",
issn = "2076-3417",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "14",

}

Artificial neural network for vertical displacement prediction of a bridge from strains (part 1) : Girder bridge under moving vehicles. / Moon, Hyun Su; Ok, Suyeol; Chun, Pang jo; Lim, Yun Mook.

In: Applied Sciences (Switzerland), Vol. 9, No. 14, 2881, 01.07.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Artificial neural network for vertical displacement prediction of a bridge from strains (part 1)

T2 - Girder bridge under moving vehicles

AU - Moon, Hyun Su

AU - Ok, Suyeol

AU - Chun, Pang jo

AU - Lim, Yun Mook

PY - 2019/7/1

Y1 - 2019/7/1

N2 - A real-time prediction method using a multilayer feedforward neural network is proposed for estimating vertical dynamic displacements of a bridge from the longitudinal strains of the bridge when vehicles pass across it. A numerical model for an existing five-girder bridge spanning 36 m proved by actual experimental values was used to verify the proposed method. To obtain a realistic vehicle distribution for the bridge, vehicle type and actual headways of moving vehicles were taken, and the measured vehicle distribution was generalized using Pearson Type III theory. Twenty-five load scenarios were created with assumed vehicle speeds of 40 km/h, 60 km/h, and 80 km/h. The results indicate that the model can reasonably predict the overall displacements of the bridge (which is difficult to measure) from the strain (which is relatively easy to measure) in the field in real time.

AB - A real-time prediction method using a multilayer feedforward neural network is proposed for estimating vertical dynamic displacements of a bridge from the longitudinal strains of the bridge when vehicles pass across it. A numerical model for an existing five-girder bridge spanning 36 m proved by actual experimental values was used to verify the proposed method. To obtain a realistic vehicle distribution for the bridge, vehicle type and actual headways of moving vehicles were taken, and the measured vehicle distribution was generalized using Pearson Type III theory. Twenty-five load scenarios were created with assumed vehicle speeds of 40 km/h, 60 km/h, and 80 km/h. The results indicate that the model can reasonably predict the overall displacements of the bridge (which is difficult to measure) from the strain (which is relatively easy to measure) in the field in real time.

UR - http://www.scopus.com/inward/record.url?scp=85071345766&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85071345766&partnerID=8YFLogxK

U2 - 10.3390/app9142881

DO - 10.3390/app9142881

M3 - Article

AN - SCOPUS:85071345766

VL - 9

JO - Applied Sciences (Switzerland)

JF - Applied Sciences (Switzerland)

SN - 2076-3417

IS - 14

M1 - 2881

ER -