Development of two models for estimation of rapid chloride penetration and investigation on effective parameters using Artificial Neural Networks (ANNs)

Abstract

In this paper Artificial Neural Networks (ANNs) are employed to develop a model which could estimate the RCPT value of various mixtures according to the mix design parameters, age and surface resistivity of concrete specimens. Furthermore, sensitivity analysis is carried out on the best ANN model to determine the influence of each input on the concrete resistance to the rapid chloride penetration. 258 experimental datasets, resulted from 79 mix designs, were used as training data for ANN models; all of which prepared and tested in Concrete Technology and Durability Research Center of Amirkabir University of Technology (CTDRC). Another simplified model is proposed using linear regression analysis; which estimates the RCPT value simply according to surface resistivity measure. Finally, eight mixtures prepared in Building and Housing Research Center (BHRC) and six mixtures obtained from real-life projects, are employed to compare and validate the proposed models.