Determination of preconsolidation pressure with artificial neural network

İngilizce (OpenAlex)

The correct determination of preconsolidation pressure is significantly important for settlement analysis in clay deposits. Many graphical methods have been developed by researchers for determining of preconsolidation pressure up to date. Some of these methods are Casagrande, Tavenas, Butterfield, Schmertmann and Janbu. Over the last few years, the use of artificial neural network (ANN) has increased in many areas of engineering. In particular, ANNs have been applied to many geotechnical engineering problems and have demonstrated some degree of success. In this study, using professional software called Statistica, an ANN model was developed to determine preconsolidation pressures in clay soils. Results from the model and graphical methods (Casagrande, Tavenas, and Butterfield) were compared with actual (experimental) preconsolidation pressures and each other. In comparison with the statistical results of the graphical methods, the ANN model yielded larger determination coefficient (R 2=0.961), lower standard deviation ratio (0.198), lower mean absolute error (36.933) and lower root mean square error (48.169).