Experimentally and numerically verified behaviour of splice joints under multiple loading conditions and their capacity predictions using artificial neural networks

Abstract

Splicing steel beams is a widely adopted practice, necessitated by span constraints that arise from challenges in transporting and handling longer beams, which may jeopardize the safety of the onsite workforce. The spliced joint must possess adequate strength and stiffness while effectively distributing the design loads without compromising the structural stability of the system. In this paper, an experimental study was carried out on various spliced joints, followed by finite element-based simulations on the validated girders. Extensive finite element analyses were conducted to investigate the influence of the width and thickness parameters of the splice plates under both three-point and four-point loading. Under both these loading conditions, superior performance was attained when a thicker flange splice and a thinner web splice were adopted. Strength improvements of 10% and 4% were achieved when the width of the flange splice (WFS) was dropped from 140 mm to 50 mm while maintaining a constant width of the web splice (WWS) at 270 mm, under three-point and four-point loading conditions respectively. Capacity enhancements of 16% and 23% were noted when WWS was raised from 60 mm to 270 mm while maintaining a constant WFS at 140 mm, under the above mentioned loading conditions, respectively. Lastly, the feasibility of artificial neural networks (ANNs) to predict the ultimate capacity of the splice joints was assessed, and it was verified that they could predict the ultimate load capacity with reasonable accuracy. The predicted load capacity of the splice joint outside the training set revealed that an appropriately trained and optimized ANN network could reliably estimate the strengths with a mean absolute error of less than 2%.