Neural Networks for Assessing Shear Strength of Soils

Over the last few years or so, the use of artificial neural networks (ANNs) has increased in many areas of engineering. In particular, ANNs have been applied to many geotechnical engineering problems such as to predict pile capacity, settlement, liquefaction etc. The correlations between shear strength parameters and other soil properties individually are common among Geotechnical engineers. But establishing a correlation by assessing the shear strength parameters of any type of soil using all other soil properties is as such impossible generally. The existing correlations are mostly one to one in nature or at the most two only. Attempts were made to assess strength parameters of soils using various other engineering and physical properties using the ANN approach. A model has been created using a set of data and the same has been validated. The paper presents the model for assessing the strength parameters modelled with the optimal input physical parameters viz. Grain Size Distribution, Plasticity Index and Dry Density. Keywords— Angle of Shearing Resistance, Artificial Neural Networks, Cohesion, Correlations, Shear Strength