Nonlinear Methods for Design-Space Dimensionality Reduction in Shape Optimization
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.
KeywordsShape optimization Hull-form design Nonlinear dimensionality reduction Kernel methods Deep autoencoder
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.
- 3.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)Google Scholar
- 10.Smola, A.J., Schölkopf, B.: Learning with Kernels. Citeseer (1998)Google Scholar
- 11.Bakır, G.H., Weston, J., Schölkopf, B.: Learning to find pre-images. Adv. Neural Inf. Process. Syst. 16, 449–456 (2004)Google Scholar
- 12.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)Google Scholar
- 13.Aggarwal, C.C., Reddy, C.K.: Data Clustering: Algorithms and Applications. Chapman and Hall/CRC (2013)Google Scholar
- 17.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)Google Scholar
- 19.Kingma, D., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
- 20.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)Google Scholar
- 21.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)Google Scholar