Abstract
In shape optimization, design improvements significantly depend on the dimension and variability of the design space. High dimensional and variability spaces are more difficult to explore, but also usually allow for more significant improvements. The assessment and breakdown of design-space dimensionality and variability are therefore key elements to shape optimization. A linear method based on the principal component analysis (PCA) has been developed in earlier research to build a reduced-dimensionality design-space, resolving the 95% of the original geometric variance. The present work introduces an extension to more efficient nonlinear approaches. Specifically the use of Kernel PCA, Local PCA, and Deep Autoencoder (DAE) is discussed. The methods are demonstrated for the design-space dimensionality reduction of the hull form of a USS Arleigh Burke-class destroyer. Nonlinear methods are shown to be more effective than linear PCA. DAE shows the best performance overall.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Diez, M., Campana, E.F., Stern, F.: Design-space dimensionality reduction in shape optimization by Karhunen-Loève expansion. Comput. Method. Appl. Mech. Eng. 283, 1525–1544 (2015)
Raghavan, B., Breitkopf, P., Tourbier, Y., Villon, P.: Towards a space reduction approach for efficient structural shape optimization. Struct. Multi. Optim. 48, 9871000 (2013)
Lukaczyk, T., Palacios, F., Alonso, J.J., Constantine, P.: Active subspaces for shape optimization. In: Proceedings of the 10th AIAA Multidisciplinary Design Optimization Specialist Conference, 13–17 January 2014, National Harbor, Maryland, USA (2014)
Schölkopf, B., Smola, A., Müller, K.R.: Nonlinear component analysis as a kernel eigenvalue problem. Neural Comput. 10(5), 1299–1319 (1998)
Kambhatla, N., Leen, T.K.: Dimension reduction by local principal component analysis. Neural Comput. 9(7), 1493–1516 (1997)
Lloyd, S.: Least squares quantization in PCM. IEEE Trans. Inf. Theor. 28(2), 129–137 (1982)
Von Luxburg, U.: A tutorial on spectral clustering. Stat. Comput. 17(4), 395–416 (2007)
Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)
Bishop, C.M.: Pattern Recognition and Machine Learning (Information Science and Statistics). Springer, New York (2006)
Smola, A.J., Schölkopf, B.: Learning with Kernels. Citeseer (1998)
Bakır, G.H., Weston, J., Schölkopf, B.: Learning to find pre-images. Adv. Neural Inf. Process. Syst. 16, 449–456 (2004)
Ng, A.Y., Jordan, M.I., Weiss, Y., et al.: On spectral clustering: analysis and an algorithm. In: NIPS, vol. 14, pp. 849–856 (2001)
Aggarwal, C.C., Reddy, C.K.: Data Clustering: Algorithms and Applications. Chapman and Hall/CRC (2013)
Bourlard, H., Kamp, Y.: Auto-association by multilayer perceptrons and singular value decomposition. Biol. Cybern. 59(4), 291–294 (1988)
Baldi, P., Hornik, K.: Neural networks and principal component analysis: learning from examples without local minima. Neural Netw. 2(1), 53–58 (1989)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)
Stern, F., Longo, J., Penna, R., Olivieri, A., Ratcliffe, T., Coleman, H.: International collaboration on benchmark CFD validation data for surface combatant DTMB model 5415. In: Proceedings of the Twenty-Third Symposium on Naval Hydrodynamics, 17–22 September 2000, Val de Reuil, France (2000)
Serani, A., Fasano, G., Liuzzi, G., Lucidi, S., Iemma, U., Campana, E.F., Stern, F., Diez, M.: Ship hydrodynamic optimization by local hybridization of deterministic derivative-free global algorithms. Appl. Ocean Res. 59, 115–128 (2016)
Kingma, D., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Diez, M., Serani, A., Stern, F., Campana, E.F.: Combined geometry and physics based method for design-space dimensionality reduction in hydrodynamic shape optimization. In: Proceedings of the 31st Symposium on Naval Hydrodynamics, Monterey, CA, USA (2016)
Serani, A., Campana, E.F., Diez, M., Stern, F.: Towards augmented design-space exploration via combined geometry and physics based Karhunen-Loève expansion. In: 18th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference (MA&O), AVIATION 2017, 5–9 June 2017, Denver, USA (2017)
Acknowledgments
The work is supported by the US Office of Naval Research Global, NICOP grant N62909-15-1-2016, under the administration of Dr. Woei-Min Lin, Dr. Salahuddin Ahmed, and Dr. Ki-Han Kim, and by the Italian Flagship Project RITMARE. The research is performed within NATO STO Task Group AVT-252 Stochastic Design Optimization for Naval and Aero Military Vehicles. The authors wish to thank Prof. Frederick Stern and Dr. Manivannan Kandasamy of The University of Iowa for inspiring the current research on nonlinear dimensionality reduction methods.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
D’Agostino, D., Serani, A., Campana, E.F., Diez, M. (2018). Nonlinear Methods for Design-Space Dimensionality Reduction in Shape Optimization. In: Nicosia, G., Pardalos, P., Giuffrida, G., Umeton, R. (eds) Machine Learning, Optimization, and Big Data. MOD 2017. Lecture Notes in Computer Science(), vol 10710. Springer, Cham. https://doi.org/10.1007/978-3-319-72926-8_11
Download citation
DOI: https://doi.org/10.1007/978-3-319-72926-8_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-72925-1
Online ISBN: 978-3-319-72926-8
eBook Packages: Computer ScienceComputer Science (R0)