Optimized neural network based carbonation prediction model

Woubishet Z. Taffese, Fahim Al-Neshawy, Esko Sistonen, Miguel Ferreira

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

Abstract

Concrete carbonation is one of the major causes of steel corrosion in reinforced concrete structure that can lead to shortened service life. Several carbonation prediction models including mathematical and neural network are available. The mathematical models are simplified and do not take all influential parameters of concrete materials into consideration. Most of the existing neural network based carbonation prediction models do not employ all parameters that influence the microstructural properties of the concrete. They also failed to perform certain essential steps during the model development, which in turn degrade their performance. In this work, novel neural network based carbonation prediction model is proposed. The model selects most relevant parameters, and removes irrelevant and/or redundant features from the original input data to build robust learning models. The performance evaluation of the model shows that the proposed carbonation prediction model predicts reasonably well with increased generalization ability.
Original languageEnglish
Title of host publicationInternational Symposium Non-Destructive Testing in Civil Engineering (NDT-CE) September 15 - 17, 2015, Berlin, Germany
Pages1074-1083
Number of pages10
Publication statusPublished - 2015
MoE publication typeA4 Article in a conference publication
EventInternational Symposium Non-Destructive Testing in Civil Engineering, NDTCE 2015 - Berlin, Germany
Duration: 15 Sep 201517 Sep 2015
https://www.ndt.net/search/docs.php3?MainSource=178&sessionID=1200 (International Symposium Non-Destructive Testing in Civil Engineering (NDTCE 2015), 15-17 Sep 2015, Berlin, Germany)

Publication series

SeriesNDT.net

Conference

ConferenceInternational Symposium Non-Destructive Testing in Civil Engineering, NDTCE 2015
Abbreviated titleNDTCE 2015
CountryGermany
CityBerlin
Period15/09/1517/09/15
Internet address

Fingerprint

Carbonation
Neural networks
Concretes
Mathematical models
Steel corrosion
Concrete construction
Service life
Reinforced concrete

Keywords

  • concrete carbonation
  • carbonation prediction
  • modelling
  • neural network

Cite this

Taffese, W. Z., Al-Neshawy, F., Sistonen, E., & Ferreira, M. (2015). Optimized neural network based carbonation prediction model. In International Symposium Non-Destructive Testing in Civil Engineering (NDT-CE) September 15 - 17, 2015, Berlin, Germany (pp. 1074-1083). NDT.net
Taffese, Woubishet Z. ; Al-Neshawy, Fahim ; Sistonen, Esko ; Ferreira, Miguel. / Optimized neural network based carbonation prediction model. International Symposium Non-Destructive Testing in Civil Engineering (NDT-CE) September 15 - 17, 2015, Berlin, Germany. 2015. pp. 1074-1083 (NDT.net).
@inproceedings{853068856f5a4fda88d89a5d97330934,
title = "Optimized neural network based carbonation prediction model",
abstract = "Concrete carbonation is one of the major causes of steel corrosion in reinforced concrete structure that can lead to shortened service life. Several carbonation prediction models including mathematical and neural network are available. The mathematical models are simplified and do not take all influential parameters of concrete materials into consideration. Most of the existing neural network based carbonation prediction models do not employ all parameters that influence the microstructural properties of the concrete. They also failed to perform certain essential steps during the model development, which in turn degrade their performance. In this work, novel neural network based carbonation prediction model is proposed. The model selects most relevant parameters, and removes irrelevant and/or redundant features from the original input data to build robust learning models. The performance evaluation of the model shows that the proposed carbonation prediction model predicts reasonably well with increased generalization ability.",
keywords = "concrete carbonation, carbonation prediction, modelling, neural network",
author = "Taffese, {Woubishet Z.} and Fahim Al-Neshawy and Esko Sistonen and Miguel Ferreira",
year = "2015",
language = "English",
series = "NDT.net",
pages = "1074--1083",
booktitle = "International Symposium Non-Destructive Testing in Civil Engineering (NDT-CE) September 15 - 17, 2015, Berlin, Germany",

}

Taffese, WZ, Al-Neshawy, F, Sistonen, E & Ferreira, M 2015, Optimized neural network based carbonation prediction model. in International Symposium Non-Destructive Testing in Civil Engineering (NDT-CE) September 15 - 17, 2015, Berlin, Germany. NDT.net, pp. 1074-1083, International Symposium Non-Destructive Testing in Civil Engineering, NDTCE 2015, Berlin, Germany, 15/09/15.

Optimized neural network based carbonation prediction model. / Taffese, Woubishet Z.; Al-Neshawy, Fahim; Sistonen, Esko; Ferreira, Miguel.

International Symposium Non-Destructive Testing in Civil Engineering (NDT-CE) September 15 - 17, 2015, Berlin, Germany. 2015. p. 1074-1083 (NDT.net).

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Optimized neural network based carbonation prediction model

AU - Taffese, Woubishet Z.

AU - Al-Neshawy, Fahim

AU - Sistonen, Esko

AU - Ferreira, Miguel

PY - 2015

Y1 - 2015

N2 - Concrete carbonation is one of the major causes of steel corrosion in reinforced concrete structure that can lead to shortened service life. Several carbonation prediction models including mathematical and neural network are available. The mathematical models are simplified and do not take all influential parameters of concrete materials into consideration. Most of the existing neural network based carbonation prediction models do not employ all parameters that influence the microstructural properties of the concrete. They also failed to perform certain essential steps during the model development, which in turn degrade their performance. In this work, novel neural network based carbonation prediction model is proposed. The model selects most relevant parameters, and removes irrelevant and/or redundant features from the original input data to build robust learning models. The performance evaluation of the model shows that the proposed carbonation prediction model predicts reasonably well with increased generalization ability.

AB - Concrete carbonation is one of the major causes of steel corrosion in reinforced concrete structure that can lead to shortened service life. Several carbonation prediction models including mathematical and neural network are available. The mathematical models are simplified and do not take all influential parameters of concrete materials into consideration. Most of the existing neural network based carbonation prediction models do not employ all parameters that influence the microstructural properties of the concrete. They also failed to perform certain essential steps during the model development, which in turn degrade their performance. In this work, novel neural network based carbonation prediction model is proposed. The model selects most relevant parameters, and removes irrelevant and/or redundant features from the original input data to build robust learning models. The performance evaluation of the model shows that the proposed carbonation prediction model predicts reasonably well with increased generalization ability.

KW - concrete carbonation

KW - carbonation prediction

KW - modelling

KW - neural network

M3 - Conference article in proceedings

T3 - NDT.net

SP - 1074

EP - 1083

BT - International Symposium Non-Destructive Testing in Civil Engineering (NDT-CE) September 15 - 17, 2015, Berlin, Germany

ER -

Taffese WZ, Al-Neshawy F, Sistonen E, Ferreira M. Optimized neural network based carbonation prediction model. In International Symposium Non-Destructive Testing in Civil Engineering (NDT-CE) September 15 - 17, 2015, Berlin, Germany. 2015. p. 1074-1083. (NDT.net).