An adaptive optimization strategy based on mixture of experts for wing aerodynamic design optimization

Bartoli, Nathalie; Lefèbvre, Thierry; Dubreuil, Sylvain; Olivanti, Romain; Bons, Nicolas; Martins, Joaquim R. R. A.; Bouhlel, Mohamed-Amine; Morlier, Joseph

doi:10.2514/6.2017-4433

Cited by 21 publications

(13 citation statements)

References 36 publications

(38 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We extend the EGO algorithm to work with multiple fidelities. In practice as the SEGOMOE framework proposed by Bartoli et al [11,12,13] is capable of handling both unconstrained and constrained problems and this with or without MOE, we choose to note in this paper the unconstrained version of SEGOMOE without MOE as EGO. The multi-fidelity is defined as MFEGO.…”

Section: B Ego Extension To Multi-fidelity: Mfegomentioning

confidence: 99%

“…In 2002, EGO was extended to constrained problems with the development of SEGO [10]). More recently SEGO was coupled to MOE (mixture of experts) methodology in order to solve high dimensional variables and constrained optimization problems such as wing shape aerodynamic optimization in the SEGOMOE framework [11][12][13]. SEGOMOE will be used in this work as a reference for surrogate based constrained optimizer with a single high fidelity (HF).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-fidelity efficient global optimization: Methodology and application to airfoil shape design

Meliani

Bartoli²,

Lefèbvre³

et al. 2019

AIAA Aviation 2019 Forum

Self Cite

View full text Add to dashboard Cite

Section: B Ego Extension To Multi-fidelity: Mfegomentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Multi-fidelity efficient global optimization: Methodology and application to airfoil shape design

Meliani

Bartoli²,

Lefèbvre³

et al. 2019

AIAA Aviation 2019 Forum

Self Cite

View full text Add to dashboard Cite

“…They were deployed as disciplinary workflows and provided as remote services. Furthermore, the deployed "workflow of workflows" has been provided as "service of services" and coupled to a surrogate based optimization strategy, named SEGOMOE, developed by ONERA [7]. An MDO problem was therefore formulated for the optimization of the reference aircraft using an MDF formulation resulting in an improved design.…”

Section: A Design Campaignmentioning

confidence: 99%

“…the MDAO Data and Process Graphs for the two-step approach) is provided in Figure 13. Each DOE study only exposes from 7 to 11 independent variables, including wing design parameters (7) and aircraft masses (e.g. Operating Empty Mass (OEM)) as coupling variables (0 to 4) that will be provided by the other clusters.…”

Section: A Doementioning

confidence: 99%

“…In NOESIS Optimus framework, EGO [41] and standard Particle Swarm Optimization (sPSO) algorithms [42] were tested. In addition, ONERA's optimization algorithm, SEGOMOE [7,43,44], used in DC-1 (see Section II), and relying on ONERA's MOE surrogate models III was also benchmarked. Table 4 presents some examples of the results obtained for MDF and IDF formulations.…”

Section: Mdo Formulationsmentioning

confidence: 99%

See 1 more Smart Citation

A clustered and surrogate-based MDA use case for MDO scenarios in AGILE project

Lefebre¹,

Bartoli²,

Dubreuil³

et al. 2018

2018 Multidisciplinary Analysis and Optimization Conference

Self Cite

View full text Add to dashboard Cite

Disciplinary proper orthogonal decomposition and interpolation for the resolution of parameterized multidisciplinary analysis

Berthelin

Dubreuil

Salaün

et al. 2022

Numerical Meth Engineering

Self Cite

View full text Add to dashboard Cite

This article proposes a new method for the resolution of parameterized coupled systems of equations, such as typical in multidisciplinary analysis (MDA).It is based on the use of disciplinary surrogate models within a multi-query context. The main idea is to replace the costly disciplinary solvers of the MDA by Proper Orthogonal Decomposition and Interpolation models. The main challenge we address is the high-dimensional coupling variables whose ranges are unknown. To overcome this issue, a training strategy is developed by uncoupling the disciplinary solvers from the MDA context. This new surrogate MDA called Disciplinary Proper Orthogonal Decomposition and Interpolation is iteratively enriched to solve the analysis with an estimation of the error made by the surrogate models. The disciplinary surrogate model which has the most influence on this error is determined by a sensitivity analysis and thus enriched. This approach allows to uncouple the disciplinary solvers during the training and enrichment phases. The approach is applied to various aeroelastic problems of an aircraft wing and allows to reduce by a factor of 5 the mean number of disciplinary solver calls needed for the resolution of the MDA.

show abstract

An adaptive optimization strategy based on mixture of experts for wing aerodynamic design optimization

Cited by 21 publications

References 36 publications

Multi-fidelity efficient global optimization: Methodology and application to airfoil shape design

Multi-fidelity efficient global optimization: Methodology and application to airfoil shape design

A clustered and surrogate-based MDA use case for MDO scenarios in AGILE project

Disciplinary proper orthogonal decomposition and interpolation for the resolution of parameterized multidisciplinary analysis

Contact Info

Product

Resources

About