Data-Driven Multi-Fidelity Modelling of Large Aspect Ratio Wings with Distributed Propellers

Strut-braced large aspect ratio wings (LARW) with distributed hybrid-electric propulsion (DHEP) show promise in reducing noise and emissions from aircraft, this furthers aviation sustainability and improves the quality of life of communities near to airports. However, low-fidelity models used for optimizing these configurations often neglect crucial flow physics, limiting their accuracy. The work presented explores two methods to enhance prediction capabilities: correcting the low-fidelity model using an error-based approach and developing a model solely based on high-fidelity Reynolds-Averaged Navier-Stokes (RANS) simulations. An error-based model aims to correct outputs from the low-fidelity surrogate, while a pure high-fidelity surrogate is constructed using the same samples. We evaluate both methods by predicting the performance of an untrained configuration within the training space to determine which approach more effectively predicts lift and drag coefficients.