Inelastic lateral-torsional buckling capacity of corroded web opening steel beams using artificial neural networks

Steel beams are extensively used as main structural in various building infrastructures such as bridge girders. Steel structures are prone to suffer various types of damage as they get older. Corrosion may be one of the most important types of damage in ageing steel structures. In a pessimistic state, an area of opening may be created along the bottom zone of the beam's web due to corrosion. The existence of opening in the web of a beam can reduce the resistance of the beam to shear, bending or buckling. This study deals with the stability of damaged steel I-beams with web opening. A three-dimensional finite element (FE) model using ABAQUS for inelastic analysis of beams has been developed to assess the effect of web opening on the lateral-torsional buckling (LTB) capacity. Artificial neural network approach has also been employed to derive empirical formula for predicting the residual ultimate LTB moment of damaged steel I-beams using obtained FE results. It is found out that the proposed formula can accurately predict ultimate capacities of doubly symmetric steel I-beams with different sizes of web opening. Hence, the results of this study can be used for better prediction of residual ultimate LTB moment of corrosion damaged girders of steel existing structures by practice engineers.