New machine learning prediction models for compressive strength of concrete modified with glass cullet

PurposeRecycled waste glasses have been widely used in Portland cement and concrete as aggregate or supplementary cementitious material. Compressive strength is one of the most important properties of concrete containing waste glasses, providing information about the loading capacity, pozzolanic reaction and porosity of the mixture. This study aims to propose highly nonlinear models to predict the compressive strength of concrete containing finely ground glass particles.Design/methodology/approachA robust machine leaning method called genetic programming is used the build the compressive strength prediction models. The models are developed using a number of test results on 50-mm mortar cubes containing glass powder according to ASTM C109. Parametric and sensitivity analyses are conducted to evaluate the effect of the predictor variables on the compressive strength. Furthermore, a comparative study is performed to benchmark the proposed models against classical regression models.FindingsThe derived design equations accurately characterize the compressive strength of concrete with ground glass fillers and remarkably outperform the regression models. A key feature of the proposed models as compared to the previous studies is that they include the simultaneous effect of various parameters such as glass compositions, size distributions, curing age and isothermal temperatures. Parametric and sensitivity analyses indicate that compressive strength is very sensitive to the curing age, curing temperature and particle surface area.Originality/valueThis study presents accurate machine learning models for the prediction of one of the most important mechanical properties of cementitious mixtures modified by waste glass, i.e. compressive strength. In addition, it provides an insight into the effect of several parameters influencing the compressive strength. From a computing perspective, a robust machine learning technique that overcomes the shortcomings of existing soft computing methods is introduced.

[1]  Usama Ebead,et al.  Stoichiometric study of activated glass powder hydration , 2012 .

[2]  Xu Ji,et al.  Prediction of concrete compressive strength: Research on hybrid models genetic based algorithms and ANFIS , 2014, Adv. Eng. Softw..

[3]  G. N. Smith.  Probability and statistics in civil engineering: An introduction , 1986 .

[4]  Kyle A. Riding,et al.  Methods for Calculating Activation Energy for Portland Cement , 2007 .

[5]  Pijush Samui,et al.  Application of statistical learning algorithms to ultimate bearing capacity of shallow foundation on cohesionless soil , 2012 .

[6]  Kiang Hwee Tan,et al.  Waste glass powder as cement replacement in concrete , 2014 .

[7]  Pengcheng Jiao,et al.  Next generation prediction model for daily solar radiation on horizontal surface using a hybrid neural network and simulated annealing method , 2017 .

[8]  R. Singh,et al.  Comparative Study of Waste Glass Powder as Pozzolanic material in Concrete , 2012 .

[9]  Akhil Garg,et al.  An evolutionary framework in modelling of multi-output characteristics of the bone drilling process , 2018, Neural Computing and Applications.

[10]  A. Gandomi,et al.  Nonlinear modeling of shear strength of SFRC beams using linear genetic programming , 2011 .

[11]  Thomas P. Ryan,et al.  Modern Regression Methods , 1996 .

[12]  Amir Hossein Alavi,et al.  Prediction of principal ground-motion parameters using a hybrid method coupling artificial neural networks and simulated annealing , 2011 .

[13]  Amir Hossein Alavi,et al.  Machine learning in geosciences and remote sensing , 2016 .

[14]  Mustafa Saridemir,et al.  Prediction of compressive strength of concretes containing metakaolin and silica fume by artificial neural networks , 2009, Adv. Eng. Softw..

[15]  John R. Koza,et al.  Genetic programming as a means for programming computers by natural selection , 1994 .

[16]  Akhil Garg,et al.  Measurement of properties of graphene sheets subjected to drilling operation using computer simulation , 2014 .

[17]  P. Samui,et al.  Comparison of machine learning techniques to predict compressive strength of concrete , 2018 .

[18]  C. Shi,et al.  A review on the use of waste glasses in the production of cement and concrete , 2007 .

[19]  Elham Sadat Mostafavi,et al.  Gene expression programming as a basis for new generation of electricity demand prediction models , 2014, Comput. Ind. Eng..

[20]  Feng Xing,et al.  The Effect of Recycled Glass Powder and Reject Fly Ash on the Mechanical Properties of Fibre-Reinforced Ultrahigh Performance Concrete , 2012 .

[21]  Okan Önal,et al.  Artificial neural network application on microstructure-compressive strength relationship of cement mortar , 2010, Adv. Eng. Softw..

[22]  Amir Hossein Alavi,et al.  A robust data mining approach for formulation of geotechnical engineering systems , 2011 .

[23]  Kyle A. Riding,et al.  Effect of curing temperature and glass type on the pozzolanic reactivity of glass powder , 2014 .

[24]  Pengcheng Jiao,et al.  Enhancement of quasi-static strain energy harvesters using non-uniform cross-section post-buckled beams , 2017 .

[25]  Pei-ming Wang,et al.  Effect of microwave curing on the hydration properties of cement-based material containing glass powder , 2018 .

[26]  Holger R. Maier,et al.  ARTIFICIAL NEURAL NETWORK APPLICATIONS IN GEOTECHNICAL ENGINEERING , 2001 .

[27]  H. Md. Azamathulla,et al.  ANFIS-based approach for predicting sediment transport in clean sewer , 2012, Appl. Soft Comput..

[28]  João Castro-Gomes,et al.  The potential pozzolanic activity of glass and red-clay ceramic waste as cement mortars components , 2012 .

[29]  Javad Akbari Torkestani.  An adaptive learning automata-based ranking function discovery algorithm , 2012 .

[30]  Linda M Pierce,et al.  Use of the Maturity Method In Accelerated PCCP Construction , 2009 .

[31]  Mohammad Ghasem Sahab,et al.  New formulation for compressive strength of CFRP confined concrete cylinders using linear genetic programming , 2010 .

[32]  Javad Akbari Torkestani.  An adaptive learning automata-based ranking function discovery algorithm , 2012, Journal of Intelligent Information Systems.

[33]  Kyle A. Riding,et al.  Influence of different particle sizes on reactivity of finely ground glass as supplementary cementitious material (SCM) , 2015 .

[34]  Pedro M. Ramos,et al.  Gene expression programming for automatic circuit model identification in impedance spectroscopy: Performance evaluation , 2013 .

[35]  Liang Gao,et al.  An application of evolutionary system identification algorithm in modelling of energy production system , 2018 .

[36]  Pengcheng Jiao,et al.  Control of Postbuckling Mode Transitions Using Assemblies of Axially Loaded Bilaterally Constrained Beams , 2017 .

[37]  Gregor Fischer,et al.  Investigating the Alkali Silica Reaction of Recycled Glass Aggregates in Concrete Materials , 2010 .

[38]  Pijush Samui,et al.  Support vector machine applied to settlement of shallow foundations on cohesionless soils , 2008 .

[39]  Zaher Mundher Yaseen,et al.  Predicting compressive strength of lightweight foamed concrete using extreme learning machine model , 2018, Adv. Eng. Softw..

[40]  Alaa M. Rashad,et al.  Recycled waste glass as fine aggregate replacement in cementitious materials based on Portland cement , 2014 .

[41]  Amir Hossein Gandomi,et al.  A new predictive model for compressive strength of HPC using gene expression programming , 2012, Adv. Eng. Softw..

[42]  Akhil Garg,et al.  Design and analysis of capacity models for Lithium-ion battery , 2018 .

[43]  A. Gandomi,et al.  Modeling of compressive strength of HPC mixes using a combined algorithm of genetic programming and orthogonal least squares , 2010 .

[44]  Caijun Shi,et al.  Characteristics and pozzolanic reactivity of glass powders , 2005 .

[45]  Yixin Shao,et al.  Studies on concrete containing ground waste glass , 2000 .

[46]  P. Roy,et al.  On Some Aspects of Variable Selection for Partial Least Squares Regression Models , 2008 .

[47]  H. Md. Azamathulla,et al.  Support vector machine approach for longitudinal dispersion coefficients in natural streams , 2011, Appl. Soft Comput..

[48]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[49]  Amir Hossein Gandomi,et al.  New prediction models for concrete ultimate strength under true-triaxial stress states: An evolutionary approach , 2017, Adv. Eng. Softw..

[50]  G. M. Sadiqul Islam,et al.  Waste glass powder as partial replacement of cement for sustainable concrete practice , 2017 .

[51]  Parviz Soroushian,et al.  Field investigation of concrete incorporating milled waste glass , 2011 .

[52]  A. Tropsha,et al.  Beware of q2! , 2002, Journal of molecular graphics & modelling.

[53]  Kyle A. Riding,et al.  Effect of Combined Glass Particles on Hydration in Cementitious Systems , 2015 .

[54]  Subhamoy Bhattacharya,et al.  CPT-based probabilistic evaluation of seismic soil liquefaction potential using multi-gene genetic programming , 2014 .

[55]  Arezki Tagnit-Hamou,et al.  Partial substitution of silica fume with fine glass powder in UHPC: Filling the micro gap , 2017 .

[56]  Sarat Kumar Das,et al.  Artificial Neural Networks in Geotechnical Engineering: Modeling and Application Issues , 2013 .

[57]  Amir Hossein Gandomi,et al.  Design equations for prediction of pressuremeter soil deformation moduli utilizing expression programming systems , 2012, Neural Computing and Applications.

[58]  Ankit Garg,et al.  An integrated SRM-multi-gene genetic programming approach for prediction of factor of safety of 3-D soil nailed slopes , 2014, Eng. Appl. Artif. Intell..