Concrete is a highly complex composite construction material and modeling using computing tools to predict concrete strength is a difficult task. In this work an effort is made to predict compressive strength of concrete after 28 days of curing, using Artificial Neural Network (ANN) and Genetic programming (GP). The data for analy- sis mainly consists of mix design parameters of concrete, coefficient of soft sand and maximum size of aggregates as input parameters. ANN yields trained weights and biases as the final model which sometime may impediment in its application at oper- ational level. GP on other hand yields an equation as its output making its plausible tool for operational use. Comparison of the prediction results displays the result the model accuracy of both ANN and GP as satisfactory, giving GP a working advantage owing to its output in an equation form. A knowledge extraction technique used with the weights and biases of ANN model to understand the most influencing parameters to predict the 28 day strength of concrete, promises to prove ANN as grey box rather than a black box. GP models, in form of explicit equations, show the influencing pa- rameters with reference to the presence of the relevant parameters in the equations.
Ahmet OZ, Murat PB, Erdogan O, Erdog K, Naci C, Bhatti A (2006). Pre- dicting the compressive strength and slump of high strength con- crete using neural network. Construction and Building Materials, 20, 769–775.
Behfarnia K, Khademi F (2017). A comprehensive study on the con- crete compressive strength estimation using artificial neural net- work and adaptive neuro-fuzzy inference system. Iran University of Science & Technology, 7(1), 71-80.
Bowden GJ, Dandy GC, Maier HR (2005). Input determination for neu- ral network models in water resources applications. Part 1—back- ground and methodology. Journal of Hydrology, 301(1-4), 75–92.
Bishnoi U (2014). Mathematical modeling for bond strength for Recy- cled coarse aggregate concrete using Genetic Programming. M.E Thesis, Thapar University.
Bhattacharya B, Solomatine P (2005). Neural networks and M5 model trees in modeling water-level- discharge relationship. Neurocom- puting, 63, 381-396.
Deshpande NK, Londhe SN, Kulkarni SS (2014). Modeling compressive strength of recycled aggregate concrete by Artificial Neural Net- work, Model Tree and Non-linear Regression. International Journal of Sustainable Built Environment, 3, 187–198.
Dias WPS, Pooliyadda SP (2001). Neural networks for predicting prop- erties of concretes with admixtures. Construction and Building Ma- terials. 15, 371-379.
Gorphade VG, Sudarsana HR, Beulah M (2014). Development of Genetic Algorithm based Neural Network Model for Predicting Workability and Strength of High Performance Concrete. International Journal of Inventive Engineering and Sciences, 2(6), 1-8.
Gandomia AH, Mohammadzadeh D, Pérez-Ordó ̃nezc JL, Alavi AH (2014). Linear genetic programming for shear strength prediction of reinforced concrete beams without stirrups. Applied Soft Compu- ting, 19, 112–120.
Khademi F, Jamal SM, Deshpande N, Londhe S (2016). Predicting strength of recycled aggregate concrete using artificial neural net- work, adaptive neuro-fuzzy inference system and multiple linear regression. International Journal of Sustainable Built Environment, 5(2), 355-369.
Khademi F, Akbari M, Nikoo M (2017). Displacement determination of concrete reinforcement building using data-driven models. Inter- national Journal of Sustainable Built Environment, 6(2), 400-411.
Kahramanli K, Allahverdi N (2001). Rule extraction from trained adap- tive neural networks using artificial immune systems. Expert Sys- tems with Applications, 36(2), Part 1, 1513–1522.
Koza J (1992). Genetic Programming: On the Programming of Comput- ers by Means of Natural Selection. A Bradford Book. MIT Press, 1992.
Kumar P, Kumar A (2015). Prediction of compressive strength using genetic programming involving NDT results. BTech thesis, National Institute of Technology, Rourkela, 2015.
Londhe SN, Shah S (2016). Knowledge extraction from artificial neural network models developed for evaporation. 20th IAHR-APD, August 28-31, Colombo, 2016.
Londhe SN, Dixit PR (2012). Genetic Programming: A Novel Computing Approach in Modeling Water Flows Genetic Programming – New Approaches and Successful Applications. Chapter 9. Licensee InTech. 2012.
Londhe SN (2009). Towards predicting water levels using artificial neu- ral network. IEEE Xplore Oceans 2009, 11-14 May 2009, Europe, 1- 6.
Lee KM, Lee HK, Lee SH, Kim GY (2006). Autogenous shrinkage of con- crete containing granulated blast-furnace slag. Cement and Con- crete Research, 36(7), 1279–1285.
Legates DR, McCabe GJ (1999). Evaluating the use of “goodness of fit” measures in hydrological and hydro climatic model validation. Wa- ter Resources Research, 35(1), 233-24.
Mukherjee A, Sudip NB (1997). Artificial neural networks in prediction of mechanical behavior of concrete at high temperature. Nuclear Engineering and Design, 178(1), 1-11.
Meltem O, Birgül K, Turan O (2008). Comparison of concrete strength prediction techniques with artificial neural network approach. Building Research journal, 56, 23-36.
Ni HG, Wang JZ (2000). Prediction of compressive strength of concrete by neural networks. Cement and Concrete Research, 30, 1245-1250. Neville AM (2012). Properties of Concrete. Pearson Education, USA and UK.
Oner A, Akyuz S (2007). An experimental study on optimum usage of GGBS for the compressive strength of concrete. Cement and Con- crete Composites. 29(6), 505–514.
Phukoetphim P, Shamseldin AY, Melville BV (2014). Knowledge Extrac- tion from Artificial Neural Networks for Rainfall-Runoff Model Combination Systems. Journal of Hydrologic Engineering, 19(7), 1422-1429.
Shetty MS (2005). Concrete Technology, 17th edition. S. Chand and Company, New Delhi.
Sarıdemir M (2010). Genetic programming approach for prediction of compressive strength of concretes containing rice husk ash. Con- struction and Building Materials, 24, 1911–1919.