A new idea is presented for efficiently training a low-dimensional, neural network (NN)-based surrogate of a high-fidelity, high-dimensional computational model (HDM). It consists in training the NN by adaptively sampling the parameter space of interest using the acquisition function of a Gaussian Process and exercising the HDM at the sampled parameter points. This approach, which can be described as an active learning approach, is explained and illustrated with numerical experiments associated with the prediction of the lift-over-drag ratio of a cambered NACA airfoil in a large, five-dimensional parameter space of flight conditions and shape design variables. The obtained numerical results demonstrate the superior efficiency as well as accuracy delivered by the proposed training over standard alternatives based on uniform and random parameter samplings. The surrogate models constructed and trained using the proposed approach are suitable for time-critical applications such as design optimization and uncertainty quantification.
|Original language||English (US)|
|Title of host publication||AIAA Scitech 2021 Forum|
|Publisher||American Institute of Aeronautics and Astronautics Inc. (AIAA)|
|Number of pages||9|
|State||Published - 2021|
|Event||AIAA Science and Technology Forum and Exposition, AIAA SciTech Forum 2021 - Virtual, Online|
Duration: Jan 11 2021 → Jan 15 2021
|Name||AIAA Scitech 2021 Forum|
|Conference||AIAA Science and Technology Forum and Exposition, AIAA SciTech Forum 2021|
|Period||01/11/21 → 01/15/21|
Bibliographical noteFunding Information:
All authors acknowledge partial support by a research grant from the King Abdulaziz City for Science and Technology (KACST). Radek Tezaur and Charbel Farhat also acknowledge partial support by the Air Force Office of Scientific Research under grant FA9550-20-1-0286. This document however does not necessarily reflect the position of any of these institutions and therefore no official endorsement should be inferred. References  Buragohain, M., and Mahanta, C., “A novel approach for ANFIS modelling based on full factorial design,” Applied soft computing, Vol. 8, No. 1, 2008, pp. 609–625.
© 2021, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.
ASJC Scopus subject areas
- Aerospace Engineering