The use of artificial intelligence combiners for modeling steel pitting risk and corrosion rate

Jui Sheng Chou, Ngoc Tri Ngo, Oswald Chong

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

Corrosion is a common deterioration that reduces the service life of concrete structures and steels. Particularly, corrosion behavior is a highly nonlinear problem influenced by complex characteristics. This study used advanced artificial intelligence (AI) techniques to predict pitting corrosion risk of steel reinforced concrete and marine corrosion rate of carbon steel. The AI-based models used for prediction included single and ensemble models constructed from four well-known machine learners including artificial neural networks (ANNs), support vector regression/machines (SVR/SVMs), classification and regression tree (CART), and linear regression (LR). Notably, a hybrid metaheuristic regression model was implemented by integrating a smart nature-inspired metaheuristic optimization algorithm (. i.e., smart firefly algorithm) with a least squares SVR. Prediction accuracy was evaluated using two real-world datasets. According to the comparison results, the hybrid metaheuristic regression model was better than the single and ensemble models in predicting the pitting corrosion risk (mean absolute percentage error=5.6%) and the marine corrosion rate (mean absolute percentage error=1.26%). The hybrid metaheuristic regression model is a promising and practical methodology for real-time tracking of corrosion in steel rebar. Civil engineers can use the hybrid model to schedule maintenance process that leads to risk reduction of structure failure and maintenance cost.

Original languageEnglish (US)
JournalEngineering Applications of Artificial Intelligence
DOIs
StateAccepted/In press - May 17 2016

Fingerprint

Pitting
Corrosion rate
Artificial intelligence
Steel
Corrosion
Linear regression
Concrete construction
Service life
Carbon steel
Deterioration
Reinforced concrete
Neural networks
Engineers
Costs

Keywords

  • Artificial intelligence
  • Corrosion rate
  • Engineering application
  • Machine learning
  • Meta ensemble
  • Metaheuristic regression
  • Pitting risk

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Artificial Intelligence
  • Electrical and Electronic Engineering

Cite this

@article{98aaa2e6edfc456f89245f7a1e2a1c98,
title = "The use of artificial intelligence combiners for modeling steel pitting risk and corrosion rate",
abstract = "Corrosion is a common deterioration that reduces the service life of concrete structures and steels. Particularly, corrosion behavior is a highly nonlinear problem influenced by complex characteristics. This study used advanced artificial intelligence (AI) techniques to predict pitting corrosion risk of steel reinforced concrete and marine corrosion rate of carbon steel. The AI-based models used for prediction included single and ensemble models constructed from four well-known machine learners including artificial neural networks (ANNs), support vector regression/machines (SVR/SVMs), classification and regression tree (CART), and linear regression (LR). Notably, a hybrid metaheuristic regression model was implemented by integrating a smart nature-inspired metaheuristic optimization algorithm (. i.e., smart firefly algorithm) with a least squares SVR. Prediction accuracy was evaluated using two real-world datasets. According to the comparison results, the hybrid metaheuristic regression model was better than the single and ensemble models in predicting the pitting corrosion risk (mean absolute percentage error=5.6{\%}) and the marine corrosion rate (mean absolute percentage error=1.26{\%}). The hybrid metaheuristic regression model is a promising and practical methodology for real-time tracking of corrosion in steel rebar. Civil engineers can use the hybrid model to schedule maintenance process that leads to risk reduction of structure failure and maintenance cost.",
keywords = "Artificial intelligence, Corrosion rate, Engineering application, Machine learning, Meta ensemble, Metaheuristic regression, Pitting risk",
author = "Chou, {Jui Sheng} and Ngo, {Ngoc Tri} and Oswald Chong",
year = "2016",
month = "5",
day = "17",
doi = "10.1016/j.engappai.2016.09.008",
language = "English (US)",
journal = "Engineering Applications of Artificial Intelligence",
issn = "0952-1976",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - The use of artificial intelligence combiners for modeling steel pitting risk and corrosion rate

AU - Chou, Jui Sheng

AU - Ngo, Ngoc Tri

AU - Chong, Oswald

PY - 2016/5/17

Y1 - 2016/5/17

N2 - Corrosion is a common deterioration that reduces the service life of concrete structures and steels. Particularly, corrosion behavior is a highly nonlinear problem influenced by complex characteristics. This study used advanced artificial intelligence (AI) techniques to predict pitting corrosion risk of steel reinforced concrete and marine corrosion rate of carbon steel. The AI-based models used for prediction included single and ensemble models constructed from four well-known machine learners including artificial neural networks (ANNs), support vector regression/machines (SVR/SVMs), classification and regression tree (CART), and linear regression (LR). Notably, a hybrid metaheuristic regression model was implemented by integrating a smart nature-inspired metaheuristic optimization algorithm (. i.e., smart firefly algorithm) with a least squares SVR. Prediction accuracy was evaluated using two real-world datasets. According to the comparison results, the hybrid metaheuristic regression model was better than the single and ensemble models in predicting the pitting corrosion risk (mean absolute percentage error=5.6%) and the marine corrosion rate (mean absolute percentage error=1.26%). The hybrid metaheuristic regression model is a promising and practical methodology for real-time tracking of corrosion in steel rebar. Civil engineers can use the hybrid model to schedule maintenance process that leads to risk reduction of structure failure and maintenance cost.

AB - Corrosion is a common deterioration that reduces the service life of concrete structures and steels. Particularly, corrosion behavior is a highly nonlinear problem influenced by complex characteristics. This study used advanced artificial intelligence (AI) techniques to predict pitting corrosion risk of steel reinforced concrete and marine corrosion rate of carbon steel. The AI-based models used for prediction included single and ensemble models constructed from four well-known machine learners including artificial neural networks (ANNs), support vector regression/machines (SVR/SVMs), classification and regression tree (CART), and linear regression (LR). Notably, a hybrid metaheuristic regression model was implemented by integrating a smart nature-inspired metaheuristic optimization algorithm (. i.e., smart firefly algorithm) with a least squares SVR. Prediction accuracy was evaluated using two real-world datasets. According to the comparison results, the hybrid metaheuristic regression model was better than the single and ensemble models in predicting the pitting corrosion risk (mean absolute percentage error=5.6%) and the marine corrosion rate (mean absolute percentage error=1.26%). The hybrid metaheuristic regression model is a promising and practical methodology for real-time tracking of corrosion in steel rebar. Civil engineers can use the hybrid model to schedule maintenance process that leads to risk reduction of structure failure and maintenance cost.

KW - Artificial intelligence

KW - Corrosion rate

KW - Engineering application

KW - Machine learning

KW - Meta ensemble

KW - Metaheuristic regression

KW - Pitting risk

UR - http://www.scopus.com/inward/record.url?scp=85008656047&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85008656047&partnerID=8YFLogxK

U2 - 10.1016/j.engappai.2016.09.008

DO - 10.1016/j.engappai.2016.09.008

M3 - Article

AN - SCOPUS:85008656047

JO - Engineering Applications of Artificial Intelligence

JF - Engineering Applications of Artificial Intelligence

SN - 0952-1976

ER -