Appraisal of long-term effects of fly ash and silica fume on compressive strength of concrete by neural networks

This study focuses on studying the effects of fly ash and silica fume replacement content on the strength of concrete cured for a long-term period of time by neural networks (NNs). Applicability of NNs to evaluate the effects of FA and SF for a long period of time is investigated. The investigations covered concrete mixes at different water cementitious materials ratio, which contained low and high volumes of FA, and with or without the additional small amount of SF. 24 different mixes with 144 different samples were gathered form the literature for this purpose. These samples consist concretes that were cured for 3, 7, 28, 56 and 180 days. A NN model is constructed trained and tested using these data. The data used in the NN model are arranged in a format of eight input parameters that cover the fly ash replacement ratio (FA), silica fume replacement ratio (SF), total cementitious material (TCM), fine aggregate (ssa), coarse aggregate (ca), water content (W), high rate water reducing agent (HRWRA) and age of samples (AS) and an output parameter which is compressive strength of concrete (fc). A NN program was devised in MATLAB and the NN model was constructed in this program. The results showed that NNs have strong potential as a feasible tool for evaluation of the effect of cementitious material on the compressive strength of concrete. It was found that FA content contributed little at early ages but much at later ages to the strength of concrete. It can also be concluded that the enhancement effect of low content of SF on compressive strength was not significant.