Robust estimation of axial loads sustained by tie-rods in historical structures using Artificial Neural Networks

Abstract

Widely used simplified analytical methods for estimating the tensile force in tie-rods are clearly not applicable when they contain significant discontinuities or irregularities. A common example for which this fact becomes relevant in practice is the use of connectors to unify historical ties consisting of several segments. To address this challenge, a robust hybrid methodology is proposed which can be applied to any historical tie by employing a data-driven approach to a dataset generated using the finite element method. The methodology is applied to a real case study involving two historical ties.