Abstract
Bayesian optimization (BO) is a popular method for solving optimization problems involving expensive objective functions. Although BO has been applied across various fields, its use in structural optimization area is in its early stages. Origami folding structures provide a complex design space where the use of an efficient optimizer is critical. In this work for the first time we demonstrate the ability of BO to solve origami-inspired design problems. We use a Gaussian process (GP) as the surrogate model that is trained to mimic the response of the expensive finite element (FE) objective function. The ability of this BO-FE framework to find optimal designs is verified by applying it to well-known origami design problems. We compare the performance of the proposed approach to traditional gradient-based optimization techniques and genetic algorithm methods in terms of ability to discover designs and computational efficiency. BO has many user-defined components/parameters and intuitions for these for structural optimization are currently limited. In this work, we study the role of hyperparameter tuning and the sensitivity of Bayesian optimization to the quality and size of the initial training set. Taking a holistic view of the computational expense, we propose various heuristic approaches to reduce the overall cost of optimization. Our results show that Bayesian optimization is an efficient alternative to traditional methods. It allows for the discovery of optimal designs using fewer finite element solutions, which makes it an attractive choice for the non-convex design space of origami fold mechanics.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Abt M, Welch WJ (2008) Fisher information and maximum-likelihood estimation of covariance parameters in Gaussian stochastic processes. Can J Stat 26(1):127–137
Benassi R, Bect J, Vazquez E (2011) Robust Gaussian Process-Based Global Optimization Using a Fully Bayesian Expected Improvement Criterion. In: Coello CAC (ed) Learning and Intelligent Optimization. Springer, Berlin, p 176–190
Bergstra J, Bardenet R, Bengio Y, Kégl B (2011) Algorithms for hyper-parameter optimization
Betrò B (1991) Bayesian methods in global optimization. J Glob Optim 1:1–14. https://doi.org/10.1007/BF00120661
Bhosekar A, Ierapetritou M (2018) Advances in surrogate based modeling, feasibility analysis, and optimization: A review. Comput Chem Eng 108:250–267. https://doi.org/10.1016/j.compchemeng.2017.09.017
Breiman L (October 2001) Random Forests. Mach Learn 45(1):5–32. https://doi.org/10.1023/A:1010933404324
Brochu E, Cora VM, de Freitas N (2010) A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning. arXiv:1012.2599
Bull AD (2011) Convergence rates of efficient global optimization algorithms. J Mach Learn Res 12:2879–2904. 1101.3501
Butler J, Bowen L, Wilcox E, Shrager A, Frecker MI, von Lockette P, Simpson TW, Lang RJ, Howell LL, Magleby SP (2018) A Model for Multi-Input Mechanical Advantage in Origami-Based Mechanisms. J Mech Robot 10(6). https://doi.org/10.1115/1.4041199.061007
Byrd RH, Gilbert JC, Nocedal J (2000) A trust region method based on interior point techniques for nonlinear programming. Math Programm Ser B 89(1):149–185. https://doi.org/10.1007/PL00011391
Choffin B, Ueda N (2018) Scaling Bayesian Optimization up to Higher Dimensions: A Review and Comparison of Recent Algorithms. 2018 IEEE 28th International Workshop on Machine Learning for Signal Processing (MLSP), pp 1–6
Cox DD, John S (1997) SDO: A Statistical Method for Global Optimization. Multidisciplinary Design Optimization: State-of-the-Art, pp 315–329. http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.52.4169
Criminisi A, Shotton J, Konukoglu E (2011) Decision forests: A unified framework for classification, regression, density estimation, manifold learning and semi-supervised learning, vol 7. NOW Publishers. https://doi.org/10.1561/0600000035
Dominguez S, Nigam N, Shahriari B (2017) A combined finite element and Bayesian optimization framework for shape optimization in spectral geometry. Comput Math Appl 74(11):2874–2896. https://doi.org/10.1016/j.camwa.2017.08.044
Edmondson B, Bowen L, Grames C, Magleby S, Howell L, Bateman T (2013) Oriceps: Origami-Inspired Forceps. Smart Mater Adapt Struct Intell Syst 1. https://doi.org/10.1115/SMASIS2013-3299
Efron B, Hinkley DV (1978) Assessing the accuracy of the maximum likelihood estimator: Observed versus expected fisher information. Biometrika 65(3):457–483. https://doi.org/10.1093/biomet/65.3.457
Elder J (1992) Global Rd optimization when probes are expensive: the GROPE algorithm. In: [Proceedings] 1992 IEEE International Conference on Systems, Man, and Cybernetics, pp 577–582 vol.1
Fan X, Wang P, Hao F (2019) Reliability-based design optimization of crane bridges using Kriging-based surrogate models. Struct Multidiscip Optim 59(3):993–1005. https://doi.org/10.1007/s00158-018-2183-0
Fuchi K, Buskohl PR, Bazzan G, Durstock MF, Reich GW, Vaia RA, Joo JJ (2015) Origami Actuator Design and Networking Through Crease Topology Optimization. J Mech Des Trans ASME 137(9):1–10. https://doi.org/10.1115/1.4030876
Fuchi K, Buskohl PR, Bazzan G, Durstock MF, Reich GW, Vaia RA, Joo JJ (2016) Design optimization challenges of origami-based mechanisms with sequenced folding. J Mech Robot 8(5):1–6. https://doi.org/10.1115/1.4032442
Gill PE, Murray W, Wright M (1991) Numerical linear algebra and optimization, vol 1. Addison-Wesley
Gillman A, Fuchi K, Buskohl PR (2018) Truss-based nonlinear mechanical analysis for origami structures exhibiting bifurcation and limit point instabilities. Int J Solids Struct 147:80–93. https://doi.org/10.1016/j.ijsolstr.2018.05.011
Gillman AS, Fuchi K, Buskohl PR (2019) Discovering Sequenced Origami Folding Through Nonlinear Mechanics and Topology Optimization. J Mech Des Trans ASME 141(4):1–11. https://doi.org/10.1115/1.4041782
Ginsbourger D, Le Riche R, Carraro L (2008) A Multi-points Criterion for Deterministic Parallel Global Optimization based on Gaussian Processes. https://hal.archives-ouvertes.fr/hal-00260579
Greco M, Gesualdo FAR, Venturini WS, Coda HB (2006) Nonlinear positional formulation for space truss analysis. Finite Elem Anal Des 42(12):1079–1086. https://doi.org/10.1016/j.finel.2006.04.007
Guirguis D, Hamza K, Aly mohamed M, Hegazi H, Saitou K (2014) Multi-objective topology optimization of multi-component continuum structures via a Kriging-interpolated level set approach. Struct Multidiscip Optim 51:733–748. https://doi.org/10.1007/s00158-014-1154-3
Huang D, Allen T, Notz W, Zeng N (2006) Global Optimization of Stochastic Black-Box Systems via Sequential Kriging Meta-Models. J Glob Optim 34:441–466. https://doi.org/10.1007/s10898-005-2454-3
Im J, Park J (2013) Stochastic structural optimization using particle swarm optimization, surrogate models and Bayesian statistics. Chin J Aeronaut 26(1):112–121. https://doi.org/10.1016/j.cja.2012.12.022
Jones DR, Schonlau M, Welch WJ (1998) Efficient Global Optimization of Expensive Black-Box Functions. J Glob Optim 13:455–492. https://link.springer.com/article/10.1023/A:1008306431147
Kandasamy K, Schneider J, Póczos B (2015) High dimensional Bayesian Optimisation and bandits via additive models. 32nd Int Conf Mach Learn ICML 2015 1:295–304. 1503.01673
Kushner HJ (1964) A New Method of Locating the Maximum Point of an Arbitrary Multipeak Curve in the Presence of Noise. J Basic Eng 86(1):97–106. https://doi.org/10.1115/1.3653121. https://asmedigitalcollection.asme.org/fluidsengineering/article-pdf/86/1/97/5763745/97_1.pdf
Lee D-Y, Kim S-R, Kim J-S, Park J-J, Cho K-J (2017) Origami wheel transformer: A variable-diameter wheel drive robot using an origami structure. Soft Robot 4(2):163–180 (English)
Li C, Gupta S, Rana S, Nguyen V, Venkatesh S, Shilton A (2017) High dimensional Bayesian optimization using dropout. IJCAI International Joint Conference on Artificial Intelligence:2096–2102. https://doi.org/10.24963/ijcai.2017/291. 1802.05400
Liu K, Paulino GH (2017) Nonlinear mechanics of non-rigid origami: An efficient computational approach. Proc R Soc A Math Phys Eng Sci 473(2206). https://doi.org/10.1098/rspa.2017.0348
Liu K, Wu T, Detwiler D, Panchal J, Tovar A (2019) Design for Crashworthiness of Categorical Multimaterial Structures Using Cluster Analysis and Bayesian Optimization. J Mech Des 141(12):1–15. https://doi.org/10.1115/1.4044838
Lizotte DJ (2008) Practical Bayesian Optimization. Ph.D. Thesis, University of Alberta
Lizotte DJ, Greiner R, Schuurmans D (2012) An experimental methodology for response surface optimization methods. J Glob Optim 53(4):699–736. https://doi.org/10.1007/s10898-011-9732-z
Locatelli M (1997) Bayesian Algorithms for One-Dimensional Global Optimization. J Glob Optim 10:57–76. https://doi.org/10.1023/A:1008294716304
MATLAB (2016) version 9.0.0 (r2016a). The MathWorks Inc., Natick
MATLAB Genetic Algorithm Toolbox (2016) Matlab genetic algorithm toolbox. The MathWorks, Natick
Miyashita S, Guitron S, Ludersdorfer M, Sung C, Rus D (2015) An untethered miniature origami robot that self-folds, walks, swims, and degrades. 2015 IEEE International Conference on Robotics and Automation (ICRA), pp 1490–1496
Mockus J (1994) Application of Bayesian approach to numerical methods of global and stochastic optimization. J Glob Optim 4(4):347–365. https://doi.org/10.1007/BF01099263
Osborne M, Garnett R, Roberts S (2009) Gaussian Processes for Global Optimization. 3rd International Conference on Learning and Intelligent Optimization (LION3), pp 1–15. http://www.robots.ox.ac.uk/~mosb/OsborneGarnettRobertsGPGO.pdf
Peraza-Hernandez EA, Hartl DJ, Malak RJ, Lagoudas DC (2014) Origami-inspired active structures: A synthesis and review. Smart Mater Struct 23(9). https://doi.org/10.1088/0964-1726/23/9/094001
Rana S, Li C, Gupta S, Nguyen V, Venkatesh S (2017) High dimensional Bayesian optimization with elastic Gaussian process. 34th Int Conf Mach Learn ICML 2017 6:4407–4415
Raponi E, Bujny M, Olhofer M, Aulig N, Boria S, Duddeck F (2019) Kriging-assisted topology optimization of crash structures. Comput Methods Appl Mech Eng 348:730–752. https://doi.org/10.1016/j.cma.2019.02.002, http://www.sciencedirect.com/science/article/pii/S0045782519300726
Rasmussen CE, Williams CKI (2006) Gaussian Processes for Machine Learning. MIT Press
Sasena MJ (2002) Flexibility and Efficiency Enhancements for Constrained Global Design Optimization with Kriging Approximations. Ph.D. Thesis, University of Michigan
Shahriari B, Swersky K, Wang Z, Adams RP, Freitas ND (2015) Taking the Human Out of the Loop: A Review of Bayesian Optimization. Clim Change 2013 - Phys Sci Basis 104(1):1–30. https://doi.org/10.1017/CBO9781107415324.004, arXiv:1011.1669v3
Shawe-Taylor J, Cristianini N (2004) Kernel methods for pattern analysis. Cambridge University Press
Snoek J, Larochelle H, Adams RP (2012) Practical Bayesian Optimization of Machine Learning Algorithms. Advances in Neural Information Processing Systems:2951–2959
Song J, Chen Y, Lu G (2012) Axial crushing of thin-walled structures with origami patterns. Thin-Walled Struct 54:65–71. https://doi.org/10.1016/j.tws.2012.02.007
Streltsov S, Vakili P (1999) A Non-myopic Utility Function for Statistical Global Optimization Algorithms. J Glob Optim 14(3):283–298. https://doi.org/10.1023/A:1008284229931
Svanberg K (1987) The method of moving asymptotes - a new method for structural optimization. Int J Numer Methods Eng 24(2):359–373
Swersky K, Snoek J, Adams RP (2013) Multi-task Bayesian optimization. Advances in Neural Information Processing Systems: 1–9
Tachi T (2009a) Simulation of Rigid Origami. Origami 4:175–187. https://doi.org/10.1201/b10653-20
Tachi T (2009b) 3D Origami Design Based on Tucking Molecules. Origami 4:259–272. https://doi.org/10.1201/b10653-27
Turner N, Goodwine B, Sen M (2016) A review of origami applications in mechanical engineering. Proc Inst Mech Eng C J Mech Eng Sci 230(14):2345–2362. https://doi.org/10.1177/0954406215597713
Vemaganti K, Madireddy S, Kedari S (2019) On the inference of viscoelastic constants from stress relaxation experiments. Mechanics of Time-Dependent Materials. https://doi.org/10.1007/s11043-018-09403-y
Wang J, Clark S, Liu E, Frazier P (2020) Parallel Bayesian Global Optimization of Expensive Functions. Oper Res
Wang Z, Zoghiy M, Hutterz F, Matheson D, De Freitas N (2013) Bayesian optimization in high dimensions via random embeddings. IJCAI International Joint Conference on Artificial Intelligence:1778–1784
Wang Z, de Freitas N (2014) Theoretical Analysis of Bayesian Optimisation with Unknown Gaussian Process Hyper-Parameters. arXiv:1406.7758
Zhang Y, Gao L, Xiao M (2020) Maximizing natural frequencies of inhomogeneous cellular structures by Kriging-assisted multiscale topology optimization. Comput Struct 230:106197. https://doi.org/10.1016/j.compstruc.2019.106197
Zhang Y, Li H, Xiao M, Gao L, Chu S, Zhang J (April 2019) Concurrent Topology Optimization for Cellular Structures with Nonuniform Microstructures Based on the Kriging Metamodel. Struct Multidiscip Optim 59(4):1273–1299. https://doi.org/10.1007/s00158-018-2130-0
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Responsible Editor: Palaniappan Ramu
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Replication of results
The MATLAB code for solving origami problems using gradient-based methods can be downloaded from MATLAB Central. The MATLAB code for the integration of Bayesian optimization to solve origami problems can be made available to interested parties upon request to the authors.
Rights and permissions
About this article
Cite this article
Shende, S., Gillman, A., Yoo, D. et al. Bayesian topology optimization for efficient design of origami folding structures. Struct Multidisc Optim 63, 1907–1926 (2021). https://doi.org/10.1007/s00158-020-02787-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00158-020-02787-x