Modelling Non-Linear Aeroelastic Loads in Long-Span Bridges with Extreme Learning Machines

This study focuses on the structural and aeroelastic behavior of long-span bridges, where aerodynamic loads are important for predicting instabilities and ensuring safety. It introduces extreme learning machines as single-layer feedforward neural networks for modelling aerodynamic self-excited forces in bridge-deck cross-sections. The methodology is trained or evaluated using forced-oscillation datasets generated through computational fluid dynamics or wind-tunnel experiments.