Prediction of maximum dry density and optimum moisture content of stabilised soil using RBF neural networks

Abstract

This article proposes a novel approach for the prediction of maximum dry density (MDD) and optimum moisture content (OMC) of soil-stabiliser mix by using radial basis function (RBF) neural networks. RBF neural network is utilised to construct comprehensive and accurate models to be able to relate the MDD and OMC of stabilised soil to the properties of natural soil such as particle size distribution, plasticity, linear shrinkage and the type and quantity of stabilising additives. Two separate sets of RBF prediction models, one for the MDD and the other for the OMC, have been developed. A parametric study was also conducted in this study using the results obtained from the proposed models to evaluate the sensitivity of MDD and OMC due to variation of the influencing parameters. A comprehensive set of data including a wide range of soil types obtained from previously published stabilisation test results was used for training, validation and testing the prediction models. The accuracy of the proposed models is satisfactory when compared with that of the experimental results. The results of proposed RBF models were further compared with those of the existing models found in literature and found to be more accurate.