Enter your keyword

2-s2.0-85044596151

[vc_empty_space][vc_empty_space]

Benchmarking multi-objective bayesian global optimization strategies for aerodynamic design

Zuhal L.R.a, Amalinadhi C.a, Dwianto Y.B.a,c, Palar P.S.b, Shimoyama K.b

a Bandung Institute of Technology, Faculty of Mechanical and Aerospace Engineering, West Java, Indonesia
b Institute of Fluid Science, Faculty of Mechanical and Aerospace Engineering, Bandung Institute of Technology, Tohoku University, Sendai Miyagi, 980-8577, Japan
c Department of Aeronautics and Astronautics, University of Tokyo, Japan

[vc_row][vc_column][vc_row_inner][vc_column_inner][vc_separator css=”.vc_custom_1624529070653{padding-top: 30px !important;padding-bottom: 30px !important;}”][/vc_column_inner][/vc_row_inner][vc_row_inner layout=”boxed”][vc_column_inner width=”3/4″ css=”.vc_custom_1624695412187{border-right-width: 1px !important;border-right-color: #dddddd !important;border-right-style: solid !important;border-radius: 1px !important;}”][vc_empty_space][megatron_heading title=”Abstract” size=”size-sm” text_align=”text-left”][vc_column_text]© 2018, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.Multi-objective Bayesian global optimization is an optimization framework that primarily relies on the Kriging surrogate model to evolve a design toward the discovery of global Pareto front. In this paper, our objective is to gain a computational insight regarding the impact and the efficiency of various multi-objective Bayesian optimization strategies for solving aerodynamic optimization problems. Three methods were investigated, that is, Euclidean-based expected improvement (EEI), expected hypervolume improvement (EHVI), and ParEGO. For this purpose, computational tests on three inviscid airfoil optimization problems and preliminary test on turbomachinery case were performed. Inviscid solver was used for airfoil problem due to its cheap computational cost, which allowed us to perform statistical analysis of the results. From the results, we observe that the EHVI method is able to provide higher quality solutions that are close to and well distributed on the Pareto front. The latter is especially one powerful aspect of the EHVI method as compared to the other two algorithms, in which EEI and ParEGO found it difficult to find a diverse set of solutions. In the light of these results, we suggest that EHVI is a potential method to be explored further for solving expensive aerodynamic design optimization problems.[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Author keywords” size=”size-sm” text_align=”text-left”][vc_column_text]Aerodynamic design optimization,Aerodynamic optimization,Airfoil optimization,Bayesian optimization,Expected improvements,Kriging surrogate model,Optimization framework,Optimization strategy[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Indexed keywords” size=”size-sm” text_align=”text-left”][vc_column_text][/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Funding details” size=”size-sm” text_align=”text-left”][vc_column_text]The first, second, and third author would like to express their gratitude to the Bandung Institute of Technology for support of this collaborative work between Bandung Institute of Technology and Tohoku University through the Riset dan Inovasi KK ITB scheme. Part of the work was carried out under the Collaborative Research Project of the Institute of Fluid Science, Tohoku University.[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”DOI” size=”size-sm” text_align=”text-left”][vc_column_text]https://doi.org/10.2514/6.2018-0914[/vc_column_text][/vc_column_inner][vc_column_inner width=”1/4″][vc_column_text]Widget Plumx[/vc_column_text][/vc_column_inner][/vc_row_inner][/vc_column][/vc_row][vc_row][vc_column][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][/vc_column][/vc_row]