Prediction of fresh and hardened properties of self-compacting concrete using support vector regression approach

This article presents the feasibility of using support vector regression (SVR) technique to determine the fresh and hardened properties of self-compacting concrete. Two different kernel functions, namely exponential radial basis function (ERBF) and radial basis function (RBF), were used to develop the SVR model. An experimental database of 115 data samples was collected from different literatures to develop the SVR model. The data used in SVR model have been organized in the form of six input parameters that covers dosage of binder content, fly ash, water–powder ratio, fine aggregate, coarse aggregate and superplasticiser. The above-mentioned ingredients have been taken as input variables, whereas slump flow value, L-box ratio, V-funnel time and compressive strength have been considered as output variables. The obtained results indicate that the SVR–ERBF model outperforms SVR–RBF model for learning and predicting the experimental data with the highest value of the coefficient of correlation ( R ) equal to 0.965, 0.954, 0.979 and 0.9773 for slump flow, L-box ratio, V-funnel and compressive strength, respectively, with small values of statistical errors. Also, the efficiency of SVR model is compared to artificial neural network (ANN) and multivariable regression analysis (MVR). In addition, a sensitivity analysis was also carried out to determine the effects of various input parameters on output. This study indicates that SVR–ERBF model can be used as an alternative approach in predicting the properties of self-compacting concrete.

[1]  Ali Nazari,et al.  Prediction compressive strength of Portland cement-based geopolymers by artificial neural networks , 2012, Neural Computing and Applications.

[2]  Mohammed Sonebi,et al.  Modelling the fresh properties of self-compacting concrete using support vector machine approach , 2016 .

[3]  A. Beycioğlu,et al.  Workability and mechanical properties of self-compacting concretes containing LLFA, GBFS and MC , 2014 .

[4]  Yue Hu,et al.  Prediction of autogenous shrinkage of concretes by support vector machine , 2016 .

[5]  Prajapati Krishnapal,et al.  Strength Characteristics of Self Compacting Concrete Containing Flyash , 2013 .

[6]  Caijun Shi,et al.  Prediction of elastic modulus of normal and high strength concrete by support vector machine , 2010 .

[7]  Mehmet Gesoğlu,et al.  Strength and drying shrinkage properties of self-compacting concretes incorporating multi-system blended mineral admixtures , 2010 .

[8]  David G. Luenberger,et al.  Linear and nonlinear programming , 1984 .

[9]  Ali Nazari,et al.  Predicting the effects of nanoparticles on early age compressive strength of ash-based geopolymers by artificial neural networks , 2012, Neural Computing and Applications.

[10]  Shahrin Mohammad,et al.  Artificial neural network models for FRP-repaired concrete subjected to pre-damaged effects , 2017, Neural Computing and Applications.

[11]  Bakhta Boukhatem,et al.  Prediction of properties of self-compacting concrete containing fly ash using artificial neural network , 2017, Neural Computing and Applications.

[12]  Luiz A. Pereira-de-Oliveira,et al.  Methodology for the mix design of self-compacting concrete using different mineral additions in binary blends of powders , 2014 .

[13]  Emre Sancak,et al.  Rule-based Mamdani type fuzzy logic model for the prediction of compressive strength of silica fume included concrete using non-destructive test results , 2012, Neural Computing and Applications.

[14]  A. K. Dey,et al.  Prediction of Bearing Capacity of Geogrid-Reinforced Stone Columns Using Support Vector Regression , 2018 .

[15]  Mohsen Khatibinia,et al.  Experimental observations and SVM-based prediction of properties of polypropylene fibres reinforced self-compacting composites incorporating nano-CuO , 2017 .

[16]  V. V. Srinivas,et al.  Downscaling of precipitation for climate change scenarios: A support vector machine approach , 2006 .

[17]  Chuntian Cheng,et al.  Using support vector machines for long-term discharge prediction , 2006 .

[18]  Phillipp Kaestner,et al.  Linear And Nonlinear Programming , 2016 .

[19]  Shuai Yang,et al.  Study on Mechanical Properties of Corroded Reinforced Concrete Using Support Vector Machines , 2014 .

[20]  S. Patro,et al.  Effect of lime and ferrochrome ash (FA) as partial replacement of cement on strength, ultrasonic pulse velocity and permeability of concrete , 2015 .

[21]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[22]  Okan Karahan,et al.  Predicting the compressive strength of ground granulated blast furnace slag concrete using artificial neural network , 2009, Adv. Eng. Softw..

[23]  Lai Ming,et al.  Nonlinear structural response prediction based on support vector machines , 2008 .

[24]  Dookie Kim,et al.  Application of support vector regression for the prediction of concrete strength , 2007 .

[25]  I-Fan Chang,et al.  Support vector regression for real-time flood stage forecasting , 2006 .

[26]  Rafat Siddique,et al.  Prediction of compressive strength of self-compacting concrete containing bottom ash using artificial neural networks , 2011, Adv. Eng. Softw..

[27]  Ali R. Pouladkhan,et al.  Comparative study on effects of Class F fly ash, nano silica and silica fume on properties of high performance self compacting concrete , 2015 .

[28]  Hasbi Yaprak,et al.  Prediction of the effect of varying cure conditions and w/c ratio on the compressive strength of concrete using artificial neural networks , 2011, Neural Computing and Applications.

[29]  M. Şahmaran,et al.  Transport and mechanical properties of self consolidating concrete with high volume fly ash , 2009 .

[30]  Okan Karahan,et al.  Comparison of artificial neural network and fuzzy logic models for prediction of long-term compressive strength of silica fume concrete , 2009, Adv. Eng. Softw..

[31]  Saeed Shojaee,et al.  Hybridizing two-stage meta-heuristic optimization model with weighted least squares support vector machine for optimal shape of double-arch dams , 2015, Appl. Soft Comput..

[32]  Hai Ying Yang,et al.  Modelling Concrete Strength Using Support Vector Machines , 2013 .

[33]  Dejan Vasovic,et al.  Prediction model for compressive strength of basic concrete mixture using artificial neural networks , 2014, Neural Computing and Applications.

[34]  Binu Sukumar,et al.  Evaluation of strength at early ages of self-compacting concrete with high volume fly ash , 2008 .

[35]  K. Lee,et al.  A comparative study of artificial neural networks and support vector machines for predicting groundwater levels in a coastal aquifer , 2011 .

[36]  R. Brereton,et al.  Support vector machines for classification and regression. , 2010, The Analyst.

[37]  I. Sfikas,et al.  Rheology and mechanical characteristics of self-compacting concrete mixtures containing metakaolin , 2014 .

[38]  P. Ramanathan,et al.  Study on Durability Characteristics of Self - Compacting Concrete with Fly Ash , 2013 .

[39]  Alexander J. Smola,et al.  Support Vector Method for Function Approximation, Regression Estimation and Signal Processing , 1996, NIPS.

[40]  Mucteba Uysal,et al.  Effect of mineral admixtures on properties of self-compacting concrete , 2011 .

[41]  Jinkyo F. Choo,et al.  Evaluation of the effects of high-volume fly ash on the flexural behavior of reinforced concrete beams , 2015 .

[42]  A. Ferhat Bingöl,et al.  Effects of different curing regimes on the compressive strength properties of self compacting concrete incorporating fly ash and silica fume , 2013 .

[43]  R. Siddique,et al.  Influence of water/powder ratio on strength properties of self-compacting concrete containing coal fly ash and bottom ash , 2012 .

[44]  Jafar Sobhani,et al.  Support vector machine for prediction of the compressive strength of no-slump concrete , 2013 .

[45]  Hadi Sadoghi Yazdi,et al.  Prediction of Elastic Modulus of Concrete Using Support Vector Committee Method , 2013 .

[46]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

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

[48]  Pijush Samui,et al.  Support vector regression based models to predict fracture characteristics of high strength and ultra high strength concrete beams , 2013 .