Surrogate-based optimization for the worst-case prediction regarding a flexible structure impacted by wind gusts

Abstract

The paper is a follow-up of the recent study on the assessment of discrete wind gust parameters impacting a flexible lightweight structure as a first step towards the evaluation of the worst-case scenario caused by strong wind gusts (JWEIA 231, 105207, 2022). The present study goes beyond by suggesting an optimization framework which allows to determine the worst-case scenario automatically. For this purpose, a stochastic response surface algorithm with a surrogate model based on radial basis functions is chosen. The algorithm relies on costly evaluations of the objective function, which consist of CPU-time intensive fully coupled fluid–structure interaction (FSI) high-fidelity simulations including the pre- and post-processing of the results. Besides the parallelization of the coupled FSI solver, a parallel version of the optimization algorithm allows to carry out several costly evaluations simultaneously. The Metric Stochastic Response Surface algorithm determines the worst case fast. Then, it continues to explore the optimization space to ensure that the global extremum is reached. A sensitivity study on relevant parameters of the optimization algorithm is conducted. Typically, for the present FSI setup, an optimization run takes one week with 6 evaluations in parallel to compute 100 different configurations. The worst case is found after about one third of the evaluations. The increase of parallel evaluations drastically reduces the wall-clock time, but the worst case is found later after half of the evaluations. This later finding is due to the parallel nature of the algorithm. Finally, the various sources of uncertainties that arise throughout the entire procedure are assessed and discussed.