Prediction of rapid chloride permeability of self-compacting concrete using Multivariate Adaptive Regression Spline and Minimax Probability Machine Regression

This paper presents new models to predict chloride penetration into self-compacting concrete (SCC) using the rapid chloride penetration test (RCPT). The research mainly focuses on the effect of supplementary cementitious material (i.e., fly ash and silica fume) and elevated temperature curing of SCC on results of the RCPT. Models are developed to predict the value of RCPT using two statistical algorithms, namely Multivariate Adaptive Regression Spline (MARS) and Minimax Probability Machine Regression (MPMR). Both models incorporate the combined effect of fly ash, silica fume and elevated temperature curing on the RCPT, and a comparative study between the models is also discussed. The analysis confirms that both MARS and MPMR are promising models for the prediction of RCPT results.