Prediction Of Mechanical Characteristics Of Soilcrete Materials Using Artificial Neural Networks

In this paper, the application of soft computing techniques such as surrogate models for the prediction of the soilcrete materials' properties has been investigated. Specifically, the application of Artificial Neural Networks (ANNs) models for the prediction of mechanical properties such as the 28-day compressive strength has been studied. To this end, a new normalization technique for the pre-processing of data is proposed. The comparison of the derived results with the available experimental data demonstrates the capability of ANNs to predict with pinpoint accuracy the compressive strength. Furthermore, the proposed normalization technique has been proven effective and robust compared to the available ones.