Development of Artificial Neural Network Models for Predicting Strength Properties of Tropical Clay Stabilized with Calcium Carbide Residue and Zeolite ‒ A Review

Abstract

The paper presents a literature review on the development of models for predicting strength properties of tropical clay stabilize with Calcium Carbide Residue (CCR) and zeolite. Application of Artificial Neural Networks (ANNs) in geotechnical analysis of tropical clay stabilised with CCR and zeolite, have been evaluated. Chemical treatment of expansive clays involves development of optimum binder mix proportions or improvement of a specific soil property using additives. These procedures often generate large data, requiring regression analysis in order to correlate experimental data and model the performance of the soil in the field. These analyses often involve large datasets and tedious mathematical procedures to correlate the variables and develop required models using traditional regression analysis. The findings from this study shows that ANNs is becoming well known in dealing with the problem of mathematical modelling involving nonlinear functions due to their robust data analysis and correlation capabilities, which has enabled them to be successfully applied, and with high performance, to the stabilisation process of clays. The study also shows that the supervised ANN model is well adapted to dealing with stabilisation of clays with high performance as indicated by high R2 and low Mean Average Error (MAE), Root Mean Square Error (RMSE), and Mean Square Error (MSE) values. The Levenberg–Marquardt algorithm is effective in shortening the convergence time during model training.