The use of artificial intelligence combiners for modeling steel pitting risk and corrosion rate
Graphical abstract
Introduction
Civil infrastructures are often subject to aggressive conditions and consequently serious deterioration may occur. In recent years, the maintenance of concrete structures has become important with respect to the sustainability of infrastructure. Corrosion of reinforcing steel-bar (rebar) is a typical deterioration process that reduces the service lives of reinforced concrete structures and steel structures. To evaluate the performance of concrete members and structures, the corrosion of steel rebar must be predicted as early as possible.
For the industrial sectors in the USA, the repairing cost of corrosion damage is equal annually to 3.1% of the gross national product, among which the utilities, transportation and infrastructures contribute the most (Shaw and Kelly, 2006). Approximately 70% of corrosion occurs in a localized area (Nimmo and Hinds, 2003) and localized corrosion is more dangerous than uniform corrosion because it is more difficult to detect. The most common localized corrosion type is pitting corrosion, which may decrease steel strength as a result of a loss in rebar thickness and initiate early fatigue crack (Nimmo and Hinds, 2003). Worsening fatigue cracks can eventually cause a catastrophic failure of a structure. Risks are endemic in practically every aspect of our lives, and they always cause a great deal of potential damage (Wu and Birge, 2016). Thus, pitting corrosion must be identified before it reaches a dangerous level.
The rapid growth in the number of offshore structures urgently demand a model for predicting corrosion rate in order to reduce potential structural failures (Caines et al., 2013). However, corrosion is a highly nonlinear problem influenced by complex characteristics and models for predicting the corrosion rate of steel currently lack a theoretical basis. Researchers have yet to reach a consensus on the best model to predict corrosion rate or pitting risk due to the lack of good understanding of factors that affect the corrosion process. Many of the better known factors that affect corrosion of steel structure, like the electrochemical measurement of pitting corrosion, are not included in existing models. Therefore, an accurate model for predicting corrosion based on electrochemical data is needed.
Machine learning (ML) and artificial intelligence (AI)-based approaches have attracted a great deal of scientific attention (Chou and Ngo, 2016a, Wu et al., 2015) and have successfully used in civil engineering (Chou et al., 2015, Chou et al., 2016, Goel and Pal, 2009, Wen et al., 2009) such as modeling of pier scour (Pal et al., 2011). For instance, Wen et al. (2009) applied a single support vector regression (SVR) model for predicting the corrosion rate of 3C steel in five different seawater environments (Wen et al., 2009). Single artificial neural networks (ANNs) has been applied to predict pitting corrosion in steel reinforced concrete (Shi et al., 2011, Wen et al., 2009). To the best knowledge of the authors, only single AI models are proposed in literature to modeling the corrosion related issues.
Although the single AI-based models have proven moderately effective for solving prediction problems, one of the critical problems is how to select an appropriate model and fine-tune the model parameters, which plays an important role in good generalization performance and prediction accuracy for future use (Chou and Ngo, 2016b, Jiménez-Come et al., 2013, Yang et al., 2011). To overcome the drawback and enhance the accuracy, ensemble and metaheuristic approaches appear to be promising solutions for the above situations. Hybrid approaches that combine multiple AI models and optimization algorithms have been proposed to enhance the prediction accuracy of single AI models (Kazem et al., 2013).
This study investigated the applicability of four single AI models, four meta ensembles (i.e., voting, bagging, stacking, and tiering), and a hybrid metaheuristic regression in solving the non-linear problem of estimating pitting risk or corrosion rate of steel rebar. The single AI models are ANNs, support vector machines and regression (SVMs/SVR), classification and regression tree (CART), and linear regression (LR). These single AI models are the most commonly used techniques in related works (Chou and Pham, 2013). Moreover, four ensemble AI models are combined from the above single AI models. The ensemble AI models consists of voting, bagging, stacking, and tiering methods. The hybrid metaheuristic regression model integrates the nature-inspired metaheuristic optimization (i.e., smart firefly algorithm (SFA)) and least squares support vector regression (LSSVR).
The first originality of this study was a comprehensive investigation of AI models for modeling pitting corrosion risk and marine corrosion rate. The combination of those AI models has not been proposed yet in modeling steel corrosion. Secondly, the hybrid metaheuristic regression was presented to predict steel corrosion, in which the SFA was used to automatically optimize the hyperparameters of the LSSVR for improving prediction accuracy. Lastly, the findings of this study provide civil engineers with a promising and practical methodology for tracking of steel corrosion. Two real-world datasets were used to evaluate the applicability of various AI models. The performance of the investigated models is compared in terms of mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE), and synthesis index (SI).
The rest of this paper is organized as follows. Section 2 briefly reviews the relevant literature on corrosion behavior of steel rebar in reinforced concrete structures as well as steel structures. The machine learners, meta ensembles, metaheuristic regression, and the method used for model performance evaluation are introduced in Section 3. Section 4 presents the results of numerical experiments using two real-world datasets. Finally, Section 5 concludes with remarks and discussions.
Section snippets
Literature review
Risk management has become a vital topic both in academia and practice during the past decades and most intelligence tools have been used to enhance risk management (Wu, 2016, Wu et al., 2014). In civil infrastructure domain, corrosion behavior has been identified as a critical issue of risk by many researchers. Han et al. investigated the initial corrosion behavior of carbon steel exposed to cyclic wet-dry conditions in an outdoor environment (Han et al., 2014). They found that the stages of
Methodology
Researchers in many fields now use ML techniques to simulate material behavior. The ANNs, CART, LR, and SVMs are the most commonly used techniques in related works and are also considered the best data mining algorithms (Wu et al., 2007). Therefore, these four techniques were adopted in this study to develop single (baseline) models as well as their ensembles, and metaheuristic regression model. The meta ensembles are voting, bagging, stacking, and tiering models. The single and ensemble models
Dataset preparation and descriptive analysis
The efficacy of the baseline machine learners and ensemble models was assessed using two published datasets for pitting corrosion risk of steel rebar (Shi et al., 2011) and corrosion rate of 3C steel in seawater environments (Liu et al., 2005). For simplicity, WEKA software (Hall et al., 2009b) was used to implement machine learners and meta classifiers. MATLAB (MathWorks, 2015), the language of technical computing, was employed to execute the developed SFA-LSSVR codes.
Table 1 presents the
Conclusions
Corrosion, a natural process involving many complex factors, can substantially reduce the service life of reinforced concrete structures and steel structures. This study investigated the efficacy of advanced artificial intelligence approaches for enhancing accuracy in predicting pitting corrosion risk of steel reinforced concrete and marine corrosion rate of carbon steel.
The AI-based single, ensemble, and hybrid models were used. The ensemble models were constructed from four well-known AI
Jui-Sheng (Rayson) Chou specializes in project analytics and engineering management. Dr. Chou received his BS and MS at the Department of Civil Engineering –National Taiwan University and his Ph.D. in Construction Engineering and Project Management –- The University of Texas at Austin. Currently, he is a Full Professor in the Department of Civil and Construction Engineering at National Taiwan University of Science and Technology (Taiwan Tech). He holds registered professional engineer licenses
References (57)
- et al.
Artificial neural network development by means of a novel combination of grammatical evolution and genetic algorithm
Eng. Appl. Artif. Intell.
(2015) - et al.
Neural networks for predicting compressive strength of structural light weight concrete
Constr. Build. Mater.
(2009) - et al.
Analysis of pitting corrosion on steel under insulation in marine environments
J. Loss Prev. Process Ind.
(2013) - et al.
Enhanced artificial intelligence for ensemble approach to predicting high performance concrete compressive strength
Constr. Build. Mater.
(2013) - et al.
Time series analytics using sliding window metaheuristic optimization-based machine learning system for identifying building energy consumption patterns
Appl. Energy
(2016) - et al.
Optimized artificial intelligence models for predicting project award price
Autom. Constr.
(2015) - et al.
Modular implementation of artificial neural network in predicting in-flight particle characteristics of an atmospheric plasma spray process
Eng. Appl. Artif. Intell.
(2015) - et al.
Evaluation of simple performance measures for tuning SVM hyperparameters
Neurocomputing
(2003) - et al.
Creep modeling of polypropylenes using artificial neural networks trained with Bee algorithms
Eng. Appl. Artif. Intell.
(2015) - et al.
Application of support vector machines in scour prediction on grade-control structures
Eng. Appl. Artif. Intell.
(2009)
A study on the initial corrosion behavior of carbon steel exposed to outdoor wet-dry cyclic condition
Corros. Sci.
SVR with hybrid chaotic genetic algorithms for tourism demand forecasting
Appl. Soft Comput.
Pitting potential modeling using Bayesian neural networks
Electrochem. Commun.
A kernel functions analysis for support vector machines for land cover classification
Int. J. Appl. Earth Obs. Geoinf.
Support vector regression with chaos-based firefly algorithm for stock market price forecasting
Appl. Soft Comput.
Correlation between seawater environmental factors and marine corrosion rate using artificial neural network analysis
J. Chin. Soc. Corros. Prot. 25
Tourism demand forecasting using novel hybrid system
Expert Syst. Appl.
Support vector regression based modeling of pier scour using field data
Eng. Appl. Artif. Intell.
Artificial neural network simulation of hourly groundwater levels in a coastal aquifer system of the Venice lagoon
Eng. Appl. Artif. Intell.
Corrosion rate prediction of 3C steel under different seawater environment by using support vector regression
Corros. Sci.
Original contribution: stacked generalization
Neural Netw.
Decision making in enterprise risk management: a review and introduction to special issue
Omega
Business intelligence in risk management: some recent progresses
Inf. Sci.
Bagging predictors
Mach. Learn.
Classification and Regression Trees
Smart artificial firefly colony algorithm-based support vector regression for enhanced forecasting in civil engineering
Comput.-Aided Civ. Infrastruct. Eng.
Shear strength prediction in reinforced concrete deep beams using nature-inspired metaheuristic support vector regression
J. Comput. Civ. Eng.
Cited by (0)
Jui-Sheng (Rayson) Chou specializes in project analytics and engineering management. Dr. Chou received his BS and MS at the Department of Civil Engineering –National Taiwan University and his Ph.D. in Construction Engineering and Project Management –- The University of Texas at Austin. Currently, he is a Full Professor in the Department of Civil and Construction Engineering at National Taiwan University of Science and Technology (Taiwan Tech). He holds registered professional engineer licenses and serves on several professional committees. He has provided consulting services to a number of private and public engineering sectors. He is the author or co-author of hundreds of journal articles, conference papers, and technical reports related to engineering management and is a member of several international journal editorial boards. As a devoted researcher, he has received Outstanding Young Scholar Research Awards twice from MOST, R.O.C. and Best Paper Awards multiple times in international conferences. He was awarded RISUD Visiting Fellowship by the Kwong Wah Education Foundation and Del E. Webb Eminent Scholar at the Del E. Webb School of Construction as invited by The Hong Kong Polytechnic University and Arizona State University, respectively. His main teaching and research interests are engineering issues related to data mining, knowledge discovery in databases, analytics and intelligence, technology and behavior management, decision, risk and reliability, simulation, sustainability, and hazard mitigation in spatial planning practices.
Ngoc-Tri Ngo is a doctoral candidate in the Department of Civil and Construction Engineering at National Taiwan University of Science and Technology (Taiwan Tech) under the mentorship of Professor Jui-Sheng Chou. Ngo is currently pursuing his doctoral degree in construction management at Taiwan Tech. He is also a lecturer at the Faculty of Project Management, University of Danang –University of Science and Technology, Vietnam.
Wai K. (Oswald) Chong’s two research foci include, first, clustering, modeling and disseminating sustainable engineering knowledge, and, second, understanding and modeling the degradation and recovery processes (EDEC) of materials, products, buildings, infrastructure, and systems. His research crosses path with the following theories and concepts: (1) knowledge mining and modeling; (2) causality models between impacts and outcomes; (3) cloud technology; (4) BIM platform; (5) Big Data; (6) predictive analytics; (7) sustainability; (8) engineering knowledge; (9) information technology; (10) life cycle analysis; and (11) materials, products and systems behaviors.