Non-myopic multipoint multifidelity Bayesian framework for multidisciplinary design.

Journal

Scientific reports

ISSN: 2045-2322

Titre abrégé: Sci Rep

Pays: England

ID NLM: 101563288

Informations de publication

Date de publication:
18 Dec 2023

Historique:

received: 25 07 2023

accepted: 29 11 2023

medline: 19 12 2023

pubmed: 19 12 2023

entrez: 18 12 2023

Statut: epublish

Résumé

The adoption of high-fidelity models in multidisciplinary design optimization (MDO) permits to enhance the identification of superior design configurations, but would prohibitively rise the demand for computational resources and time. Multifidelity Bayesian Optimization (MFBO) efficiently combines information from multiple models at different levels of fidelity to accelerate the MDO procedure. State-of-the-art MFBO methods currently meet two major limitations: (i) the sequential adaptive sampling precludes parallel computations of high-fidelity models, and (ii) the search scheme measures the utility of new design evaluations only at the immediate next iteration. This paper proposes a Non-Myopic Multipoint Multifidelity Bayesian Optimization (NM3-BO) algorithm to sensitively accelerate MDO overcoming the limitations of standard methods. NM3-BO selects a batch of promising design configurations to be evaluated in parallel, and quantifies the expected long-term improvement of these designs at future steps of the optimization. Our learning scheme leverages an original acquisition function based on the combination of a two-step lookahead policy and a local penalization strategy to measure the future utility achieved evaluating multiple design configurations simultaneously. We observe that the proposed framework permits to sensitively accelerate the MDO of a space vehicle and outperforms popular algorithms.

Identifiants

DOI: 10.1038/s41598-023-48757-3 PMID: 38110463

pubmed: 38110463

doi: 10.1038/s41598-023-48757-3

pii: 10.1038/s41598-023-48757-3

doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

Pagination

22531

Informations de copyright

Références

Sobieszczanski-Sobieski, J. Multidisciplinary design optimization: An emerging new engineering discipline. In Advances in Structural Optimization (ed. Sobieszczanski-Sobieski, J.) 483–496 (Springer, 1995).

doi: 10.1007/978-94-011-0453-1_14

Alexandrov, N. M. et al. Multidisciplinary Design Optimization: State of the Art (SIAM, 1997).

Agte, J. et al. Mdo: Assessment and direction for advancement-an opinion of one international group. Struct. Multidiscip. Optim. 40, 17–33 (2010).

doi: 10.1007/s00158-009-0381-5

Martins, J. R. & Lambe, A. B. Multidisciplinary design optimization: A survey of architectures. AIAA J. 51, 2049–2075 (2013).

doi: 10.2514/1.J051895

Benaouali, A. & Kachel, S. Multidisciplinary design optimization of aircraft wing using commercial software integration. Aerosp. Sci. Technol. 92, 766–776 (2019).

doi: 10.1016/j.ast.2019.06.040

Fazeley, H., Taei, H., Naseh, H. & Mirshams, M. A multi-objective, multidisciplinary design optimization methodology for the conceptual design of a spacecraft bi-propellant propulsion system. Struct. Multidiscip. Optim. 53, 145–160 (2016).

doi: 10.1007/s00158-015-1304-2

Brevault, L., Balesdent, M. & Hebbal, A. Multi-objective multidisciplinary design optimization approach for partially reusable launch vehicle design. J. Spacecr. Rockets 57, 373–390 (2020).

doi: 10.2514/1.A34601

Gerber, D. J. & Lin, S.-H.E. Designing in complexity: Simulation, integration, and multidisciplinary design optimization for architecture. Simulation 90, 936–959 (2014).

doi: 10.1177/0037549713482027

Wang, W., Gao, F., Cheng, Y. & Lin, C. Multidisciplinary design optimization for front structure of an electric car body-in-white based on improved collaborative optimization method. Int. J. Automot. Technol. 18, 1007–1015 (2017).

doi: 10.1007/s12239-017-0098-1

Wang, S. et al. Multidisciplinary design optimization of underwater glider for improving endurance. Struct. Multidiscip. Optim. 63, 2835–2851 (2021).

doi: 10.1007/s00158-021-02844-z

Yan, J. et al. Multidisciplinary design optimization of distributed energy generation systems: The trade-offs between life cycle environmental and economic impacts. Appl. Energy 284, 116197 (2021).

doi: 10.1016/j.apenergy.2020.116197

Hwang, J. T., Jain, A. V. & Ha, T. H. Large-scale multidisciplinary design optimization-review and recommendations. AIAA Aviat. 2019 Forum https://doi.org/10.2514/6.2019-3106 (2019).

doi: 10.2514/6.2019-3106

Simpson, T. W. & Martins, J. R. Multidisciplinary design optimization for complex engineered systems design: State of the research and state of the practice-report from a national science foundation workshop. Int. Des. Eng. Tech. Conf. Comput. Inf. Eng. Conf. 54822, 835–845 (2011).

Dubreuil, S., Bartoli, N., Gogu, C. & Lefebvre, T. Towards an efficient global multidisciplinary design optimization algorithm. Struct. Multidiscip. Optim. 62, 1739–1765 (2020).

doi: 10.1007/s00158-020-02514-6

Peherstorfer, B., Willcox, K. & Gunzburger, M. Survey of multifidelity methods in uncertainty propagation, inference, and optimization. SIAM Rev. 60, 550–591 (2018).

doi: 10.1137/16M1082469

Piperni, P., DeBlois, A. & Henderson, R. Development of a multilevel multidisciplinary-optimization capability for an industrial environment. AIAA J. 51, 2335–2352 (2013).

doi: 10.2514/1.J052180

Mifsud, M., MacManus, D. G. & Shaw, S. A variable-fidelity aerodynamic model using proper orthogonal decomposition. Int. J. Numer. Methods Fluids 82, 646–663 (2016).

doi: 10.1002/fld.4234

Liem, R. P., Mader, C. A. & Martins, J. R. Surrogate models and mixtures of experts in aerodynamic performance prediction for aircraft mission analysis. Aerosp. Sci. Technol. 43, 126–151 (2015).

doi: 10.1016/j.ast.2015.02.019

Goertz, S. et al. Overview of collaborative multi-fidelity multidisciplinary design optimization activities in the DLR project Victoria. AIAA Aviat. 2020 Forum https://doi.org/10.2514/6.2020-3167 (2020).

doi: 10.2514/6.2020-3167

Fernández-Godino, M. G., Park, C., Kim, N.-H. & Haftka, R. T. Review of multi-fidelity models. Preprint at http://arxiv.org/abs/1609.07196 (2016).

Mosca, V., Karpuk, S., Sudhi, A., Badrya, C. & Elham, A. Multidisciplinary design optimisation of a fully electric regional aircraft wing with active flow control technology. Aeronaut. J. 126, 730–754 (2022).

doi: 10.1017/aer.2021.101

Wu, N., Mader, C. A. & Martins, J. R. A gradient-based sequential multifidelity approach to multidisciplinary design optimization. Struct. Multidiscip. Optim. 65, 1–20 (2022).

doi: 10.1007/s00158-022-03204-1

Van Nguyen, N., Tyan, M., Jin, S. & Lee, J.-W. Adaptive multifidelity constraints method for efficient multidisciplinary missile design framework. J. Spacecr. Rockets 53, 184–194 (2016).

doi: 10.2514/1.A33312

Shi, R., Liu, L., Long, T., Wu, Y. & Gary Wang, G. Multi-fidelity modeling and adaptive co-kriging-based optimization for all-electric geostationary orbit satellite systems. J. Mech. Des. 142, 021404 (2020).

doi: 10.1115/1.4044321

Pellegrini, R., Serani, A., Broglia, R., Diez, M. & Harries, S. Resistance and payload optimization of a sea vehicle by adaptive multi-fidelity metamodeling. In 2018 AIAA/ASCE/AHS/ASC Structures, Structural Dynamics, and Materials Conference, 1904 (2018).

Alam, K., Ray, T. & Anavatti, S. G. Design optimization of an unmanned underwater vehicle using low-and high-fidelity models. IEEE Trans. Syst. Man Cybern. Syst. 47, 2794–2808 (2015).

doi: 10.1109/TSMC.2015.2390592

Wang, X., Liu, Y., Sun, W., Song, X. & Zhang, J. Multidisciplinary and multifidelity design optimization of electric vehicle battery thermal management system. J. Mech. Des. 140, 094501 (2018).

doi: 10.1115/1.4040484

Anselma, P., Niutta, C. B., Mainini, L. & Belingardi, G. Multidisciplinary design optimization for hybrid electric vehicles: component sizing and multi-fidelity frontal crashworthiness. Struct. Multidiscip. Optim. 62, 2149–2166 (2020).

doi: 10.1007/s00158-020-02603-6

Sykes, V., Collu, M. & Coraddu, A. A flexible, multi-fidelity levelised cost of energy model for floating offshore wind turbines multidisciplinary design, analysis and optimisation approaches. J. Phys. Conf. Ser. 2265, 042029 (2022).

doi: 10.1088/1742-6596/2265/4/042029

Jasa, J., Bortolotti, P., Zalkind, D. & Barter, G. Effectively using multifidelity optimization for wind turbine design. Wind Energy Sci. 7, 991–1006 (2022).

doi: 10.5194/wes-7-991-2022

Huang, D., Allen, T. T., Notz, W. I. & Miller, R. A. Sequential Kriging optimization using multiple-fidelity evaluations. Struct. Multidiscip. Optim. 32, 369–382 (2006).

doi: 10.1007/s00158-005-0587-0

Takeno, S. et al. Multi-fidelity Bayesian optimization with max-value entropy search and its parallelization. In International Conference on Machine Learning (eds Takeno, S. et al.) 9334–9345 (PMLR, 2020).

Ruan, X., Jiang, P., Zhou, Q., Hu, J. & Shu, L. Variable-fidelity probability of improvement method for efficient global optimization of expensive black-box problems. Struct. Multidiscip. Optim. 62, 3021–3052 (2020).

doi: 10.1007/s00158-020-02646-9

Charayron, R., Lefebvre, T., Bartoli, N. & Morlier, J. Multi-fidelity Bayesian optimization strategy applied to overall drone design. In AIAA SCITECH 2023 Forum, 2366 (2023).

Serani, A. et al. Adaptive multi-fidelity sampling for CFD-based optimisation via radial basis function metamodels. Int. J. Comput. Fluid Dyn. 33, 237–255 (2019).

doi: 10.1080/10618562.2019.1683164

Reisenthel, P. H. & Allen, T. T. Application of multifidelity expected improvement algorithms to aeroelastic design optimization. In 10th AIAA multidisciplinary design optimization conference, 1490 (2014).

Tran, A., Tranchida, J., Wildey, T. & Thompson, A. P. Multi-fidelity machine-learning with uncertainty quantification and Bayesian optimization for materials design: Application to ternary random alloys. J. Chem. Phys. 153, 074705 (2020).

pubmed: 32828092 doi: 10.1063/5.0015672

Shahriari, B., Swersky, K., Wang, Z., Adams, R. P. & De Freitas, N. Taking the human out of the loop: A review of Bayesian optimization. Proc. IEEE 104, 148–175 (2015).

doi: 10.1109/JPROC.2015.2494218

Frazier, P. I. A tutorial on bayesian optimization. Preprint at http://arxiv.org/abs/1807.02811 (2018).

Ginsbourger, D. & Le Riche, R. Towards Gaussian process-based optimization with finite time horizon. In mODa 9-Advances in Model-Oriented Design and Analysis (eds Ginsbourger, D. & Le Riche, R.) 89–96 (Springer, 2010).

doi: 10.1007/978-3-7908-2410-0_12

Osborne, M. A., Garnett, R. & Roberts, S. J. Gaussian processes for global optimization. In 3rd International Conference on Learning and Intelligent Optimization (LION3), 1–15 (Citeseer, 2009).

Lam, R., Willcox, K. & Wolpert, D. H. Bayesian optimization with a finite budget: An approximate dynamic programming approach. Adv. Neural Inf. Process. Syst. 29, 883–891 (2016).

González, J., Osborne, M. & Lawrence, N. Glasses: Relieving the myopia of Bayesian optimisation. In Artificial Intelligence and Statistics (eds González, J. et al.) 790–799 (PMLR, 2016).

Wu, J. & Frazier, P. Practical two-step lookahead Bayesian optimization. Adv. Neural Inf. Process. Syst. 32, 9813–9823 (2019).

Wang, H., van Stein, B., Emmerich, M. & Back, T. A new acquisition function for Bayesian optimization based on the moment-generating function. In 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 507–512 (IEEE, 2017).

de Winter, R., van Stein, B. & Bäck, T. Multi-point acquisition function for constraint parallel efficient multi-objective optimization. In Proceedings of the Genetic and Evolutionary Computation Conference, 511–519 (2022).

Grassi, F., Manganini, G., Garraffa, M. & Mainini, L. Raal: Resource aware active learning for multifidelity efficient optimization. AIAA J. 61, 2744–2753 (2023).

doi: 10.2514/1.J061383

Meliani, M. et al. Multi-fidelity efficient global optimization: Methodology and application to airfoil shape design. AIAA Aviat. 2019 Forum https://doi.org/10.2514/6.2019-3236 (2019).

doi: 10.2514/6.2019-3236

Brevault, L., Balesdent, M. & Hebbal, A. Overview of gaussian process based multi-fidelity techniques with variable relationship between fidelities, application to aerospace systems. Aerosp. Sci. Technol. 107, 106339 (2020).

doi: 10.1016/j.ast.2020.106339

Williams, C. K. & Rasmussen, C. E. Gaussian Processes for Machine Learning Vol. 2 (MIT press Cambridge, 2006).

Kennedy, M. C. & O’Hagan, A. Predicting the output from a complex computer code when fast approximations are available. Biometrika 87, 1–13 (2000).

doi: 10.1093/biomet/87.1.1

Forrester, A., Sobester, A. & Keane, A. Engineering Design via Surrogate Modelling: A Practical Guide (Wiley, 2008).

doi: 10.1002/9780470770801

Kontogiannis, S. G., Demange, J., Savill, A. M. & Kipouros, T. A comparison study of two multifidelity methods for aerodynamic optimization. Aerosp. Sci. Technol. 97, 105592 (2020).

doi: 10.1016/j.ast.2019.105592

Puterman, M. L. Markov decision processes. Handb. Oper. Res. Manag. Sci. 2, 331–434 (1990).

Papadimitriou, C. H. & Tsitsiklis, J. N. The complexity of Markov decision processes. Math. Oper. Res. 12, 441–450 (1987).

doi: 10.1287/moor.12.3.441

Bellman, R. Dynamic programming. Science 153, 34–37 (1966).

pubmed: 17730601 doi: 10.1126/science.153.3731.34

Eddy, S. R. What is dynamic programming?. Nat. Biotechnol. 22, 909–910 (2004).

pubmed: 15229554 doi: 10.1038/nbt0704-909

Wilson, J., Hutter, F. & Deisenroth, M. Maximizing acquisition functions for Bayesian optimization. Adv. Neural Inf. Process. Syst. 31, 1–12 (2018).

Di Fiore, F. & Mainini, L. Non-myopic multifidelity bayesian optimization. Preprint at http://arxiv.org/abs/2207.06325 (2022).

González, J., Dai, Z., Hennig, P. & Lawrence, N. Batch Bayesian optimization via local penalization. In Artificial Intelligence and Statistics (eds González, J. et al.) 648–657 (PMLR, 2016).

Beran, P. S., Bryson, D., Thelen, A. S., Diez, M. & Serani, A. Comparison of multi-fidelity approaches for military vehicle design. AIAA Aviat. 2020 Forum https://doi.org/10.2514/6.2020-3158 (2020).

doi: 10.2514/6.2020-3158

Mainini, L. et al. Analytical benchmark problems for multifidelity optimization methods. Preprint at http://arxiv.org/abs/2204.07867 (2022).

Steward, D. The design structure matrix: A method for managing the design of complex systems. IEEE Trans. Eng. Manag. 28, 71–74 (1981).

doi: 10.1109/TEM.1981.6448589

Di Fiore, F., Maggiore, P. & Mainini, L. Multifidelity domain-aware learning for the design of re-entry vehicles. Struct. Multidiscip. Optim. 64, 3017–3035 (2021).

doi: 10.1007/s00158-021-03037-4

Harris, R., Stewart, M. & Koenig, W. Thermal protection systems technology transfer from apollo and space shuttle to the orion program. In 2018 AIAA SPACE and Astronautics Forum and Exposition, 5134 (2018).

Jones, D. R., Schonlau, M. & Welch, W. J. Efficient global optimization of expensive black-box functions. J. Glob. Optim. 13, 455–492 (1998).

doi: 10.1023/A:1008306431147