New hybrid support vector regression methods for predicting fresh and hardened properties of self-compacting concrete

Abstract

Most of the published literature on concrete containing fly ash was limited to predicting the hardened properties of concrete. It is understood that exist so restricted studies focusing on forecasting both hardened and fresh features of self-compacting concrete (SCC). Hence, it is goaled for developing models for predicting the fresh and hardened properties of SCC by the support vector regression method (SVR). This study aims to specify SVR method key parameters using Ant lion optimization (ALO) and Biogeography-based optimization (BBO) algorithms. The considered properties of SCC in the fresh phase are the L-box test, V-funnel test, slump flow, and in the hardened phase is CS. Results demonstrate powerful potential in the learning section for all considered properties as well as approximating in the testing phase. It can be seen that the proposed models have R2 incredible value in the learning and testing phase. It means that the correlation between observed and predicted properties of SCC from hybrid models is acceptable so that it represents high accuracy in the training and approximating process. All in all, in most of the cases, the SVR model developed by ALO outperforms BBO-SVR, which depicts the capability of the ALO algorithm for determining the optimal parameters of the considered method.