Surrogate ELM framework for predicting vortex-induced vibration of inverted cantilever plates

The prediction of large-amplitude wind-induced vibrations in lightweight flexible structures remains challenging, as strong fluid–structure coupling and nonlinear flow physics govern the response. The aeroelastic flapping of an inverted cantilever plate is a canonical vortex-induced vibration (VIV) problem, capturing key features of flapping behaviour, unsteady wake dynamics, and the narrow wind-speed range in which limit-cycle oscillations occur. It therefore provides a suitable benchmark for the development of new modelling approaches. This work proposes a data-driven framework for modelling the aerodynamic forces around oscillating inverted cantilever plates using high-resolution flow simulations with prescribed oscillations. These simulations provide training data capturing the relationship between structural motion and the resulting aerodynamic forces. An Extreme Learning Machine (ELM) is employed to efficiently learn this nonlinear mapping. Due to the strong wake dependency of the aerodynamic response, the proposed framework also allows consideration of temporal motion information in the aerodynamic force prediction. The resulting surrogate model is intended to be coupled with a geometrically nonlinear structural solver to enable computationally efficient fluid–structure interaction simulations while retaining essential nonlinear aerodynamic effects. Preliminary investigations demonstrate promising agreement between the ELM-predicted and high-fidelity aerodynamic forces under different structural motion conditions and wind speeds. Ongoing work focuses on refinement of the temporal input representation and assessment of the capability of the proposed framework to reproduce key VIV characteristics and coupled aeroelastic response.