Artificial neutral networks to predict design properties for cemented embankment layers of high speed train rail ways
MetadataShow full item record
I. EGELI, G. TAYFUR, E. YILMAZ, H. USUN ARTIFICIAL NEURAL NETWORKS TO PREDICT DESIGN PROPERTIES FOR CEMENTED EMBANKMENT LAYERS OF HIGH SPEED TRAIN RAILWAYS Cement-Wapno-Beton, Vol. XVIII/LXXX, 2013, No 1, p. 10 High-speed train railway (HSTR) embankment is a complicated process, as it deals with high geometric design standards and material properties. In this study the replaceability of fill strata without cement prepared subgrade layer and with cement addition one is investigated. In the experiments the specimens composed of natural sand with different cement additions and two w/c ratios were used. The Plaxis-FEM (2D) program was employed to find the maximum expected total settlements of HSTR embankments with cemented subgrade layer. Furthermore, the artificial neural networks model was constructed to predict the failure stress, elasticity modulus and strains. The sensivity analysis has revealed that cement content was the most sensitive for stress and elasticity modulus predictions, while the curing age of specimens was for the strain forecast.