Volume Change Behaviour in Calcitic Soil Influenced with Sulphuric Acid using Artificial Neural Networks

This paper elucidates the methodology of applying artificial neural network model (ANNM) to predict the percent swell of calcitic soil in sulphuric acid solutions, a complex phenomenon involving many parameters. Swell data required for modelling is experimentally obtained using conventional oedometer tests under nominal surcharge. The phases in ANN include optimal design of architecture, operation and training of architecture. The designed optimal neural model (3-5-1) is a fully connected three layer feed forward network with symmetric sigmoid activation function and trained by the back propagation algorithm to minimize a quadratic error criterion. The used model requires parameters such as duration of interaction, calcite mineral content and acid concentration for prediction of swell. The observed strong correlation coefficient (R = 0.9979) between the values determined by the experiment and predicted using the developed model demonstrates that the network can provide answers to complex problems in geotechnical engineering.