Developing Prediction Model on Workability Parameters of Ultrasonicated Nano Silica (n-SiO2) and Fly Ash Added Cement-Based Grouts by Using Artificial Neural Networks

Abstract

Abstract In this experimental study, the workability and bleeding properties of cement-based grout mixes combined with fly ash (FA) and nano silica (n-SiO2) as colloidal nanopowder were investigated, and some prediction models were developed with the artificial neural network. The Marsh cone flow time, mini slump spreading diameter, and plate cohesion meter values of samples prepared in different concentrations have been measured and analyzed experimentally to investigate the workability properties. Moreover, bleeding tests were carried out on the grout mixtures prepared within the scope of this experimental study. Test results showed that the usage of FA as a mineral additive in the grout samples positively contributed to an increase on the fluidity of the grout samples as expected. Although the increase in n-SiO2 content in the grout mixes resulted in an increase in the Marsh cone flow time of the grout mixes, it resulted in a decrease in the mini slump spreading diameter of the samples. The increase in the plate cohesion values of the grout mixtures was also observed in the n-SiO2 added grout mixtures. At the same time, the bleeding values of the grout mixes with and without mineral additives of 0.9 % or more with n-SiO2 additives remained above 900 ml (below 10 % bleeding rate). The artificial neural network model can predict the workability properties of cement-based grouts containing n-SiO2 nanoparticle-doped FA with high accuracy.