Estimation of lateral wall movements in braced excavations using neural networks

TLDR

Neural networks are increasingly used in geotechnical engineering because they excel at modeling nonlinear multivariate problems. The study shows that neural networks can synthesize finite element data on braced excavations in clays to capture nonlinear variable interactions. The neural network produced reasonably accurate wall displacement predictions and offers an advantage over conventional methods by being easily retrained with new finite element and field data. Keywords: braced excavation, finite element analysis, neural networks, retaining walls, soft clay, wall displacement.

Abstract

The growing interest in neural networks among geotechnical engineers is due to its excellent performance in modelling nonlinear multivariate problems. This paper demonstrates that neural networks can synthesize data derived from finite element studies on braced excavations in clays and capture the nonlinear interactions between the variables in the system. The neural network was able to produce reasonably accurate wall displacement predictions after "learning" from examples derived from finite element analyses. This method has the advantage over other more conventional methods in that it can be readily retrained as additional data from finite element studies and actual field records are acquired. Key words : braced excavation, finite element analysis, neural networks, retaining walls, soft clay, wall displacement.