TY - JOUR ID - 1851 TI - An Investigation of Friction Angle Correlation with Geotechnical Properties for Granular Soils Using GMDH Type Neural Networks JO - Scientia Iranica JA - SCI LA - en SN - 1026-3098 AU - Shooshpasha, Issa AU - Amiri, Iman AU - MolaAbasi, Hossein AD - Department of Civil Engineering, Babol University of Technology, Iran AD - Department of Civil Engineering, Mazandaran Institute of Technology, Iran Y1 - 2015 PY - 2015 VL - 22 IS - 1 SP - 157 EP - 164 KW - Standard penetration test KW - Friction angle KW - Correlation KW - GMDH KW - sensitivity analysis DO - N2 - Standard Penetration Test (SPT) is one of the most effective tests for quick and inexpensive evaluation of the mechanical properties of soil layers. Numerous studies have been conducted to evaluate correlations between SPT blow counts (NSPT) and the soil properties such as friction angle (). In this paper, the relation between and in situ parameters of soil including NSPT, effective stress and fine content is investigated for granular soils. In order to demonstrate the relevancy of and corrected SPT blow count (N60), a new polynomial model based on Group Method of Data Handling (GMDH) type neural networks (NN) was used based on a 195 data sets including three soil parameters. That has been recorded after two major earthquakes in Turkey and Taiwan in 1999. This study addresses the question of whether GMDH-type NN is capable to estimate based on specified variables. Results confirm that GMDH-type NN Provide an effective way to recognize data pattern and predict performance over granular soils accurately. Finally, the effect of fine content and effective overburden stress on the correlation of N60 and has been studied by sensitivity analysis. UR - https://scientiairanica.sharif.edu/article_1851.html L1 - https://scientiairanica.sharif.edu/article_1851_30481b732d3e93b8ca7865785ea1d52b.pdf ER -