APPLICATION OF ARTIFICIAL NEURAL NETWORKS TO PREDICT SOIL RECOMPRESSION INDEX AND RECOMPRESSION RATIO

Abstract

Overconsolidated soils are widely encountered in practice where settlement calculations are crucial. The recompression index (Cr) and the recompression ratio (Cr) are considered as one of the most important parameters used in settlement calculations. To achieve this purpose, expensive and time-consuming laboratory tests are usually conducted using undisturbed specimens to obtain the values of these parameters. Various equations derived from regression analysis were proposed to predict consolidation parameters from the physical properties of a soil. In this paper, however, an artificial neural network model (ANN) is proposed to predict Cr and Cr using natural water content, initial void ratio, total unit weight and effective overburden pressure. The proposed ANN model achieved good agreement with the results of one hundred seventy-nine standard one-dimensional consolidation tests collected from previous geotechnical investigations in Baghdad.

Keywords

• Recompression Index
• Recompression Ratio
• Overconsolidated Soil
• Artificial Neural Network