Carbonation model for fly ash concrete based on artificial neural network: Development and parametric analysis

Abstract Control and prediction of the carbonation depth in reinforced concrete structures has great relevance for construction industry, since the carbonation process is directly related to the service life and durability of these structures. One challenge in carbonation modelling is to understand the complex relation between the main parameters of the phenomenon. An Artificial Neural Network (ANN) may overcome this challenge, finding solutions to these nonlinear and complex problems. In this study, an ANN with backpropagation algorithm is used in predicting the carbonation depth of concretes that contains fly ash addition. A total of 90 ANN topologies are implemented. It was observed in the training process that networks with two hidden layers are able to generate models with determination coefficient greater than 0.8. One of them is select as the one that best fit the problem. The optimized configuration provided smallest root mean square error associated with the best determination coefficient. Besides, the parametric study shown that the parameters that had most influence on the carbonation depth in fly ash-concretes were the cement consumption, fly ash content, CO2 rate and relative humidity. Besides, results indicate that the model can be applied to estimate the lifespan of concrete structures, and may be used as simulation tool in the development of engineering projects focused on durability.

[1]  S. Poyet,et al.  Carbonation of hardened cement pastes: Influence of temperature , 2019, Cement and Concrete Research.

[2]  Jelena Dragaš,et al.  Model for practical carbonation depth prediction for high volume fly ash concrete and recycled aggregate concrete , 2019, Construction and Building Materials.

[3]  E. Possan,et al.  Modeling the Carbonation Front of Concrete Structures in the Marine Environment through ANN , 2018, IEEE Latin America Transactions.

[4]  Y. F. Houst.  Diffusion de gaz, carbonatation et retrait de la pâte de ciment durcie , 1993 .

[5]  L. Parrott.  A REVIEW OF CARBONATION IN REINFORCED CONCRETE , 1987 .

[6]  N. Belie,et al.  A service life based global warming potential for high-volume fly ash concrete exposed to carbonation , 2014 .

[7]  Ana Carolina Parapinski dos Santos,et al.  CO2 uptake potential due to concrete carbonation: A case study , 2017 .

[8]  Luiz F. S. Coletta,et al.  Artificial Neural Network for Classification and Analysis of Degraded Soils , 2017 .

[9]  J. J. O. Andrade,et al.  Model to Estimate Concrete Carbonation Depth and Service Life Prediction , 2020 .

[10]  K. Kobayashi.  Mechanism of Carbonation of Concrete , 1990 .

[11]  Jianzhuang Xiao,et al.  Prediction model of carbonation depth for recycled aggregate concrete , 2018 .

[12]  K. Maekawa,et al.  Multi-scale Modeling of Concrete Performance , 2003 .

[13]  Esko Sistonen,et al.  CaPrM: Carbonation prediction model for reinforced concrete using machine learning methods , 2015 .

[14]  N. Banthia,et al.  Carbonation in concrete infrastructure in the context of global climate change – Part 1: Experimental results and model development , 2012 .

[15]  S. Tangtermsirikul,et al.  A study on carbonation depth prediction for fly ash concrete , 2006 .

[16]  Rogério Carrazedo,et al.  Análisis paramétrico de la carbonatación en estructuras de hormigón por Redes Neuronales Artificiales , 2017 .

[17]  D. D. Molin,et al.  Carbonation-induced reinforcement corrosion in silica fume concrete , 2009 .

[18]  Laurene V. Fausett,et al.  Fundamentals Of Neural Networks , 1994 .

[19]  Jinrui Zhang,et al.  Long-age wet curing effect on performance of carbonation resistance of fly ash concrete , 2016 .

[20]  Ditao Niu,et al.  Application of Neural Network for Concrete Carbonation Depth Prediction , 2014 .

[21]  Ha-Won Song,et al.  Analysis of carbonation behavior in concrete using neural network algorithm and carbonation modeling , 2010 .

[22]  Jari Puttonen,et al.  Reactive transport modelling of long-term carbonation , 2014 .

[23]  C. Atiş.  ACCELERATED CARBONATION AND TESTING OF CONCRETE MADE WITH FLY ASH , 2003 .

[24]  Qingtao Li,et al.  Effects of micro-environmental climate on the carbonation depth and the pH value in fly ash concrete , 2018 .

[25]  Rogério Carrazedo,et al.  Parametric analysis of carbonation process in reinforced concrete structures through Artificial Neural Networks , 2017 .

[26]  S. Singh,et al.  Comparative study of accelerated carbonation of plain cement and fly-ash concrete , 2017 .

[27]  Ahmed Loukili,et al.  A performance based approach for durability of concrete exposed to carbonation , 2009 .

[28]  Ronggui Liu,et al.  Predicting Carbonation Depth of Prestressed Concrete under Different Stress States Using Artificial Neural Network , 2009, Adv. Artif. Neural Syst..

[29]  B. B. Das,et al.  Influence of Fineness of Fly Ash on the Carbonation and Electrical Conductivity of Concrete , 2011 .

[30]  Koichi Maekawa,et al.  MODELING OF PH PROFILE IN PORE WATER BASED ON MASS TRANSPORT AND CHEMICAL EQUILIBRIUM THEORY , 2000 .

[31]  Peng Zhang,et al.  Effect of Fly Ash on Durability of High Performance Concrete Composites , 2013 .

[32]  Bakhta Boukhatem,et al.  Exploring the major factors affecting fly-ash concrete carbonation using artificial neural network , 2019, Neural Computing and Applications.

[33]  Fundamental Modeling and Experimental Investigation of Polymer Washing Process , 2016 .

[34]  Carlos Alberto Villacorta Cardoso,et al.  Forecasting Natural Gas Consumption using ARIMA Models and Artificial Neural Networks , 2016 .

[35]  Teresa B Ludermir,et al.  Redes neurais artificiais: teoria e aplicações , 2000 .

[36]  Linhua Jiang,et al.  A model for predicting carbonation of high-volume fly ash concrete , 2000 .

[37]  Jorge de Brito,et al.  Carbonation of concrete made with high amount of fly ash and recycled concrete aggregates for utilization of CO2 , 2019, Journal of CO2 Utilization.

[38]  A. Leemann,et al.  Carbonation of concrete: the role of CO2 concentration, relative humidity and CO2 buffer capacity , 2017 .

[39]  Cristiane Pauletti,et al.  Carbonatação acelerada : estado da arte das pesquisas no Brasil , 2007 .

[40]  Rogério Carrazedo,et al.  Artificial Intelligence Applied in the Concrete Durability Study , 2020 .

[41]  P. Akpınar.  INTELLIGENT PREDICTION OF CONCRETE CARBORATION DEPTH USING NEURAL NETWORKS , 2016 .

[42]  Stephen O. Ekolu,et al.  Model for practical prediction of natural carbonation in reinforced concrete: Part 1-formulation , 2018 .

[43]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[44]  Y. Kim,et al.  Accelerated Carbonation Assessment of High-Volume Fly Ash Concrete , 2020 .

[45]  Li Zheng,et al.  Carbonation of loaded RC elements made of different concrete types: Accelerated testing and future predictions , 2020, Construction and Building Materials.

[46]  Ahmed Loukili,et al.  Performance-based design and carbonation of concrete with high fly ash content , 2011 .

[47]  B. Bruggen,et al.  Developing a feed forward multilayer neural network model for prediction of CO2 solubility in blended aqueous amine solutions , 2014 .