Quantitative measure of concrete fragment using ANN to consider uncertainties under impact loading

Kyeongjin Kim, Woo Seok Kim, Junwon Seo, Yoseok Jeong, Jaeha Lee

Research output: Contribution to journalArticlepeer-review

Abstract

In this study, numerical analysis was performed to predict amount of fragments and travel distance after collision of a concrete median barrier with a truck under impact loading using Smooth Particle Hydrodynamics (SPH). The obtained results of the SPH analysis showed that amount of fragments and the travel distance can be changed depending on different velocity-to-mass ratios under same local impact energy. Using the results of the SPH analysis, artificial neural network (ANN) was constructed to consider the uncertainties for the prediction of amount of fragments and travel distance of concrete after collision. In addition, the results of the ANN were compared with the results of multiple linear regression analysis (MRA). The ANN results showed better coefficient of determination (R2) than the MRA results. Therefore, the ANN showed improvement than the MRA results in terms of the uncertainties of the prediction of amount of fragments and travel distance. Using the constructed ANN, data augmentation was conducted from a limited number of analysis data using a statistical distribution method. Finally, the fragility curves of the concrete median barrier were suggested to estimate the probability of exceed specific amount of fragments and travel distance under same impact energy.

Original languageEnglish
Article number11248
JournalScientific Reports
Volume12
Issue number1
DOIs
StatePublished - Dec 2022

Bibliographical note

Funding Information:
This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) (2021R1I1A1A01061283, 2021R1I1A3044831). The authors greatly acknowledge the support.

Publisher Copyright:
© 2022, The Author(s).

ASJC Scopus subject areas

  • General

Fingerprint

Dive into the research topics of 'Quantitative measure of concrete fragment using ANN to consider uncertainties under impact loading'. Together they form a unique fingerprint.

Cite this