Prediction of the strength of concrete radiation shielding based on LS-SVM

Abstract Radiation-shielding concrete (RSC) and conventional concrete differ in strength because of their distinct constituents. Predicting the strength of RSC with different constituents plays a vital role in radiation shielding (RS) engineering design. In this study, a model to predict the strength of RSC is established using a least squares-support vector machine (LS-SVM) through grid search algorithm. The algorithm is used to optimize the parameters of the LS-SVM on the basis of traditional prediction methods for conventional concrete. The predicted results of the LS-SVM model are compared with the experimental data. The results of the prediction are stable and consistent with the experimental results. In addition, the studied parameters exhibit significant effects on the simulation results. Therefore, the proposed method can be applied in predicting the strength of RSC, and the predicted results can be adopted as an important reference for RS engineering design.

[1]  Halil Ibrahim Erdal.  Two-level and hybrid ensembles of decision trees for high performance concrete compressive strength prediction , 2013, Eng. Appl. Artif. Intell..

[2]  Leonardo Vanneschi,et al.  Prediction of high performance concrete strength using Genetic Programming with geometric semantic genetic operators , 2013, Expert Syst. Appl..

[3]  Jui-Sheng Chou,et al.  Concrete compressive strength analysis using a combined classification and regression technique , 2012 .

[4]  Iskender Akkurt,et al.  Radiation shielding of concrete containing zeolite , 2010 .

[5]  Krešimir Trontl,et al.  Support vector regression model for the estimation of γ -ray buildup factors for multi-layer shields , 2007 .

[6]  Osman Gencel,et al.  Comparison of artificial neural networks and general linear model approaches for the analysis of abrasive wear of concrete , 2011 .

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

[8]  Dimitri P. Bertsekas,et al.  Nonlinear Programming , 1997 .

[9]  Ali Akbar Ramezanianpour,et al.  Hybrid support vector regression – Particle swarm optimization for prediction of compressive strength and RCPT of concretes containing metakaolin , 2012 .

[10]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

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

[12]  Behrouz Ahmadi-Nedushan,et al.  Prediction of elastic modulus of normal and high strength concrete using ANFIS and optimal nonlinear regression models , 2012 .

[13]  Gökhan Budak,et al.  Radiation transmission of heavyweight and normal-weight concretes containing colemanite for 6 MV and 18 MV X-rays using linear accelerator , 2010 .

[14]  F. Koksal,et al.  Modeling of Thermal Conductivity of Concrete with Vermiculite by Using Artificial Neural Networks Approaches , 2013 .

[15]  Johan A. K. Suykens,et al.  Benchmarking Least Squares Support Vector Machine Classifiers , 2004, Machine Learning.

[16]  Jui-Sheng Chou,et al.  Enhanced artificial intelligence for ensemble approach to predicting high performance concrete compressive strength , 2013 .

[17]  Jui-Sheng Chou,et al.  Machine learning in concrete strength simulations: Multi-nation data analytics , 2014 .

[18]  Seung-Chang Lee,et al.  Prediction of concrete strength using artificial neural networks , 2003 .