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

• Published in: Annals of nuclear energy Vol. 85; pp. 296 - 300
• Main Authors: Juncai, Xu, Qingwen, Ren, Zhenzhong, Shen
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.11.2015
• Subjects: Concretes; Constituents; Engineering design; Grid search algorithm; Least squares method; LS-SVM; Mathematical models; Nuclear engineering; Radiation shielding; Radiation-shielding concrete; Strength; Strength prediction; Radiation-shielding concrete; Strength prediction; LS-SVM; Grid search algorithm
• ISSN: 0306-4549; 1873-2100
• DOI: 10.1016/j.anucene.2015.05.030

•LS-SVM was introduced for prediction of the strength of RSC.•A model for prediction of the strength of RSC was implemented.•The grid search algorithm was used to optimize the parameters of the LS-SVM.•The performance of LS-SVM in predicting the strength of RSC was evaluated. 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.