Hostname: page-component-7dd5485656-c8zdz Total loading time: 0 Render date: 2025-10-31T07:00:10.921Z Has data issue: false hasContentIssue false
  • English
  • Français

On Diverse System-Level Design Using Manifold Learning and Partial Simulated Annealing

Published online by Cambridge University Press:  26 May 2022

A. Cobb ,
A. Roy ,
D. Elenius ,
K. Koneripalli  and
S. Jha
A. Cobb
Affiliation:
SRI International, United States of America
A. Roy
Affiliation:
SRI International, United States of America
D. Elenius
Affiliation:
SRI International, United States of America
K. Koneripalli
Affiliation:
SRI International, United States of America
S. Jha*
Affiliation:
SRI International, United States of America
*
susmit.jha@sri.com

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

The goal in system-level design is to generate a diverse set of high-performing design configurations that allow trade-offs across different objectives and avoid early concretization. We use deep generative models to learn a manifold of the valid design space, followed by Monte Carlo sampling to explore and optimize design over the learned manifold, producing a diverse set of optimal designs. We demonstrate the efficacy of our proposed approach on the design of an SAE race vehicle and propeller.

Keywords

artificial intelligence (AI)engineering designcyber-physical systems

Information

Type
Article
Information
Proceedings of the Design Society , Volume 2: DESIGN2022 , May 2022 , pp. 1541 - 1548
Creative Commons
Creative Common License - CCCreative Common License - BYCreative Common License - NCCreative Common License - ND
This is an Open Access article, distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives licence (http://creativecommons.org/licenses/by-nc-nd/4.0/), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is unaltered and is properly cited. The written permission of Cambridge University Press must be obtained for commercial re-use or in order to create a derivative work.
Copyright
The Author(s), 2022.

References

Belakaria, S., Deshwal, A., Jayakodi, N., and Doppa, J. 2020. Uncertainty-aware search framework for multi-objective Bayesian optimization. In Proceedings of the AAAI Conference on Artificial Intelligence (pp. 10044–10052).Google Scholar
Bertsekas, D. 2014. Constrained optimization and Lagrange multiplier methods. Academic press.Google Scholar
Brookes, D., and Listgarten, J. 2018. Design by adaptive sampling. arXiv preprint arXiv:1810.03714.Google Scholar
Brookes, D., Park, H., and Listgarten, J. 2019. Conditioning by adaptive sampling for robust design. In International Conference on Machine Learning (pp. 773–782).Google Scholar
Deshwal, A., Belakaria, S., and Doppa, J. 2021. Bayesian Optimization over Hybrid Spaces. arXiv preprint arXiv:2106.04682.Google Scholar
DMS 2021 Ship Design Tools At DMS. OpenProp - integrated rotor design and analysis, 2021. URL: https://dmsonline.us/openprop/Google Scholar
Duane, S., Kennedy, A., Pendleton, B., and Roweth, D. 1987. Hybrid Monte Carlo. Physics letters B, 195(2), p.216–222.Google Scholar
Epps, B., Chalfant, J., Kimball, R., Techet, A., Flood, K., and Chryssostomidis, C. 2009. OpenProp: An open-source parametric design and analysis tool for propellers. In Proceedings of the 2009 grand challenges in modeling & simulation conference (pp. 104–111).Google Scholar
Fujita, M. 2019. Basic and advanced researches in logic synthesis and their industrial contributions. In Proceedings of the 2019 International Symposium on Physical Design (pp. 109–116). 10.1145/3299902.3311069Google Scholar
Gal, Y., and Ghahramani, Z. 2016. Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. In International Conference on Machine Learning (pp. 1050–1059). https://dl.acm.org/doi/10.5555/3045390.3045502Google Scholar
Grabocka, J., Scholz, R., and Schmidt-Thieme, L. 2019. Learning surrogate losses. arXiv preprint arXiv:1905.10108.Google Scholar
Han, Z.H., Zhang, K.S., and others 2012. Surrogate-based optimization. Real-world applications of genetic algorithms, 343.Google Scholar
Kingma, D., and Welling, M. 2013. Auto-Encoding Variational Bayes. arXiv preprint arXiv:1312.6114.Google Scholar
Koziel, S., Ciaurri, D., and Leifsson, L. 2011. Surrogate-based methods. In Computational optimization, methods and algorithms (pp. 33–59). Springer.Google Scholar
Leimkuhler, B., and Reich, S. 2005. Simulating Hamiltonian Dynamics. In Cambridge Monographs on Applied and Computational Mathematics (pp. i-iv). Cambridge University Press.Google Scholar
Liu, L., Wang, M., and Deng, J. 2020. A unified framework of surrogate loss by refactoring and interpolation. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part III 16 (pp. 278–293).Google Scholar
Neal, R. 2011. MCMC using Hamiltonian dynamics. Handbook of Markov chain Monte Carlo, 2(11), p.2.Google Scholar
Notin, P., Hernández-Lobato, J., and Gal, Y. 2021. Improving black-box optimization in VAE latent space using decoder uncertainty. arXiv preprint arXiv:2107.00096.Google Scholar
Rezende, D., and Viola, F. 2018. Generalized ELBO with constrained optimization, geco. In Workshop on Bayesian Deep Learning, NeurIPS.Google Scholar
Rezende, D., Mohamed, S., and Wierstra, D. 2014. Stochastic backpropagation and approximate inference in deep generative models. In International Conference on Machine Learning (pp. 1278–1286). 10.5555/3044805.3045035Google Scholar
Rider, M. 2013. Designing with Creo Parametric 2.0. SDC Publications.Google Scholar
Sanchez-Lengeling, B., and Aspuru-Guzik, A. 2018. Inverse molecular design using machine learning: Generative models for matter engineering. Science, 361(6400), p.360–365.CrossRefGoogle ScholarPubMed
Schaltz, E., and Soylu, S. 2011. Electrical vehicle design and modeling. Electric vehicles-modelling and simulations, 1, p.1–24.Google Scholar
Seff, A., Zhou, W., Richardson, N., and Adams, R. 2021. Vitruvion: A Generative Model of Parametric CAD Sketches. arXiv preprint arXiv:2109.14124.Google Scholar
Shahriari, B., Swersky, K., Wang, Z., Adams, R., and De Freitas, N. 2015. Taking the human out of the loop: A review of Bayesian optimization. Proceedings of the IEEE, 104(1), p.148–175. https://dx.doi.org/10.1109/JPROC.2015.2494218CrossRefGoogle Scholar
Soria Zurita, N., Colby, M., Tumer, I., Hoyle, C. and Tumer, K. 2018. Design of complex engineered systems using multi-agent coordination. Journal of Computing and Information Science in Engineering, 18(1), p.011003. 10.1115/1.4038158Google Scholar
Stolarski, T., Nakasone, Y., and Yoshimoto, S. 2018. Engineering analysis with ANSYS software. Butterworth-Heinemann. 10.1016/C2016-0-01966-6Google Scholar
Sun, X., Xue, T., Rusinkiewicz, S. and Adams, R. 2021. Amortized Synthesis of Constrained Configurations Using a Differentiable Surrogate. arXiv preprint arXiv:2106.09019.Google Scholar
Tripp, A., Daxberger, E., and Hernández-Lobato, J. 2020. Sample-efficient optimization in the latent space of deep generative models via weighted retraining. Advances in Neural Information Processing Systems, 33.Google Scholar
Viquerat, J., Rabault, J., Kuhnle, A., Ghraieb, H., Larcher, A., and Hachem, E. 2021. Direct shape optimization through deep reinforcement learning. Journal of Computational Physics, 428, p.110080.CrossRefGoogle Scholar
Xu, J., Spielberg, A., Zhao, A., Rus, D., and Matusik, W. 2021. Multi-Objective Graph Heuristic Search for Terrestrial Robot Design. arXiv preprint arXiv:2107.05858.Google Scholar
Zhao, A., Xu, J., Konakovi\'c-Lukovi\'c, M., Hughes, J., Spielberg, A., Rus, D., and Matusik, W. 2020. RoboGrammar: graph grammar for terrain-optimized robot design. ACM TOG, 39(6), p.1–16. https://dl.acm.org/doi/abs/10.1145/3414685.3417831CrossRefGoogle Scholar