Affiliations: [a] Department of Civil Engineering, Tezpur University, Tezpur, Assam, India
| [b] Department of Civil Engineering, Assam Engineering College, Guwahati, Assam, India
Corresponding author: Arunav Chakraborty, Department of Civil Engineering, Tezpur University, Tezpur, Assam, India. E-mail: email@example.com.
Abstract: The estimation of slope stability is an engineering problem that involves many parameters. The impact of these parameters on the stability of slopes can be understood by the use of computational tools like regression analysis, neural networks, etc. These computational tools are highly sophisticated modelling techniques which are capable of modelling very complex functions. They act as a powerful tool for modelling, especially when the relationships between the underlying data is unknown. It can identify and understand the correlated patterns present between the input data sets and corresponding target values. In this paper, the input data for the three dimensional slope stability estimation includes the geotechnical and geometrical input parameters and the 3-D critical safety factor (Fcs) as the output data. On successful completion of the model, the performance of the same is measured and the results are compared to those obtained by means of standard analytical methods. The results showed that the predicted values are very close to the analytical values and provide good correlation between the input variables.
Keywords: Neural networks, back propagation, factor of safety, geotechnical parameters