Abstract
In this paper, we present the concept of a “shape manifold” designed for reduced order representation of complex “shapes” encountered in mechanical problems, such as design optimization, springback or image correlation. The overall idea is to define the shape space within which evolves the boundary of the structure. The reduced representation is obtained by means of determining the intrinsic dimensionality of the problem, independently of the original design parameters, and by approximating a hyper surface, i.e. a shape manifold, connecting all admissible shapes represented using level set functions. Also, an optimal parameterization may be obtained for arbitrary shapes, where the parameters have to be defined a posteriori. We also developed the predictor-corrector optimization manifold walking algorithms in a reduced shape space that guarantee the admissibility of the solution with no additional constraints. We illustrate the approach on three diverse examples drawn from the field of computational and applied mechanics.
Similar content being viewed by others
References
Alfaro I, Yvonnet J, Cueto E, Chinesta F, Doblare M (2006) Meshless methods with application to metal forming. Comput Methods Appl Mech Eng 195(48-49):6661-6675 (Computational Metal Forming)
Alkorta J, Martinez-Esnaola J, Sevillano JG (2005) Absence of one-to-one correspondence between elastoplastic properties and sharp-indentation load-penetration data. J Mater Res 20(02):432–437
Allaire G, Jouve F, Toader AM (2004) Structural optimization using sensitivity analysis and a level-set method. J Comput Phys 194(1):363–393
Audouze C, De Vuyst F, Nair P (2009) Reduced-order modeling of parameterized PDEs using time-space-parameter principal component analysis. Int J Numer Methods Eng 80(8):1025–1057
Balasubramanian M, Schwartz EL (2002) The isomap algorithm and topological stability. Science 295(5552):7–7
Benamara T, Breitkopf P, Lepot I, Sainvitu C (2016) Adaptive infill sampling criterion for multi-fidelity optimization based on Gappy-POD. Struct Multidiscip Optim. doi:10.1007/s00158-016-1440-3
Berkooz G, Holmes P, Lumley JL (1993) The proper orthogonal decomposition in the analysis of turbulent flows. Annu Rev Fluid Mech 25(1):539–575
Bocciarelli M, Bolzon G, Maier G (2005) Parameter identification in anisotropic elastoplasticity by indentation and imprint mapping. Mech Mater 37(8):855–868
Bolzon G, Maier G, Panico M (2004) Material model calibration by indentation, imprint mapping and inverse analysis. Int J Solids Struct 41(11):2957–2975
Breitkopf P, Kleiber M (1987) Knowledge engineering enhancement of finite element analysis. Commun Appl Numer Methods 3(5):359–366
Breitkopf P, Naceur H, Rassineux A, Villon P (2005) Moving least squares response surface approximation: formulation and metal forming applications. Comput Struct 83(17–18):1411–1428
Breitkopf P, Rassineux A, Villon P (2002) An introduction to moving least squares meshfree methods. Revue Europeenne des Elements 11(7–8):825–867
Camastra F (2003) Data dimensionality estimation methods: a survey. Pattern Recognit 36(12):2945–2954
Castanier MP, Ottarsson G, Pierre C (1997) A reduced order modeling technique for mistuned bladed disks. J Vib Acoust 119(3):439–447
Chen X, Ogasawara N, Zhao M, Chiba N (2007) On the uniqueness of measuring elastoplastic properties from indentation: the indistinguishable mystical materials. J Mech Phys Solids 55(8):1618–1660
Cheng YT, Cheng CM (2004) Scaling, dimensional analysis, and indentation measurements. Mater Sci Eng R Rep 44(4):91–149
Chinesta F, Ammar A, Cueto E (2010) Proper generalized decomposition of multiscale models. Int J Numer Methods Eng 83(8–9):1114–1132
Chinesta F, Ladeveze P, Cueto E (2011) A short review on model order reduction based on proper generalized decomposition. Arch Comput Methods Eng 18(4):395–404
Coelho RF, Breitkopf P, Knopf-Lenoir C (2009) Bi-level model reduction for coupled problems. Struct Multidiscip Optim 39(4):401–418
Cordier L, El Majd BA, Favier J (2010) Calibration of pod reduced order models using tikhonov regularization. Int J Numer Methods Fluids 63(2):269–296
Cortes C, Vapnik V (1995) Support vector machine. Mach Learn 20(3):273–297
Couplet M, Basdevant C, Sagaut P (2005) Calibrated reduced-order pod-galerkin system for fluid flow modeling. J Comput Phys 207(1):192–220
Cox TF, Cox MA (2000) Multidimensional scaling. CRC Press, Boca Raton
D’Acquisto L, Fratini L (2001) An optical technique for springback measurement in axisymmetrical deep drawing operations. J Manuf Process 3(1):29–37
Dulong JL, Druesne F, Villon P (2007) A model reduction approach for real-time part deformation with nonlinear mechanical behavior. Int J Interact Des Manuf 1(4):229–238
Duvigneau R (2006) Adaptive parameterization using free-form deformation for aerodynamic shape optimization. INRIA Research Report RR-5949
Eggertsen PA, Mattiasson K (2009) On the modelling of the bendingunbending behaviour for accurate springback predictions. Int J Mech Sci 51(7):547–563
Forrester AIJ, Keane AJ (2009) Recent advances in surrogate-based optimization. Prog Aerosp Sci 45:50–79
Freund Y, Mason L (1999) The alternating decision tree learning algorithm. In: icml, vol 99, pp 124-133
Furey TS, Cristianini N, Duffy N, Bednarski DW, Schummer M, Haussler D (2000) Support vector machine classification and validation of cancer tissue samples using microarray expression data. Bioinformatics 16(10):906–914
Gao T, Zhang W, Duysinx P (2012) A bi-value coding parameterization scheme for the discrete optimal orientation design of the composite laminate. Int J Numer Methods Eng 91(1):98–114
Geuzaine C, Remacle JF (2009) Gmsh: a three-dimensional finite element mesh generator with built-in pre- and post-processing facilities. Int J Numer Methods Eng 79(11):1309–1331
Ghnatios C, Chinesta F, Cueto E, Leygue A, Breitkopf P, Villon P (2011) Methodological approach to efficient modeling and optimization of thermal processes taking place in a die: application to pultrusion. Compos Part A 42:1169–1178
Ghnatios C, Masson F, Huerta A, Cueto E, Leygue A, Chinesta F (2012) Proper generalized decomposition based dynamic data-driven control of thermal processes. Comput Methods Appl Mech Eng 213:29–41
Gibson RF (2014) A review of recent research on nanoindentation of polymer composites and their constituents. Compos Sci Technol 105:51–65
Goldberg DE, Holland JH (1988) Genetic algorithms and machine learning. Mach Learn 3(2):95–99
Golub GH, Reinsch C (1970) Singular value decomposition and least squares solutions. Numer Math 14(5):403–420
Gonzalez D, Cueto E, Chinesta F (2015) Computational patient avatars for surgery planning. Ann Biomed Eng. doi:10.1007/s10439-015-1362-z
Hagan MT, Demuth HB, Beale MH, De Jesús O (1996) Neural network design, vol 20. PWS Publishing Company, Boston
Hoang K, Kerfriden P, Bordas S (2016) A fast, certified and tuning free two-field reduced basis method for the metamodelling of affinely-parametrised elasticity problems. Comput Methods Appl Mech Eng 298:121–158
Hou Y, Sapanathan T, Dumon A, Culière P, Rachik M (2016) A novel artificial dual-phase microstructure generator based on topology optimization. Comput Mater Sci 123:188–200
Hurtado JE (2013) Structural reliability: statistical learning perspectives, vol 17. Springer Science & Business Media, Berlin
Ibrahimbegovic A, Knopf-Lenoir C, Kucerova A, Villon P (2008) Optimal design and optimal control of elastic structures undergoing finite rotations and deformations. Int J Numer Methods Eng 61:2428–2460
Ito K, Ravindran S (1998) A reduced-order method for simulation and control of fluid flows. J Comput Phys 143(2):403–425
Jan S, Zolesio J (1992) Shape sensitivity analysis. Introduction to shape optimization, Springer, Berlin
Jolliffe I (2002) Principal component analysis. Wiley Online Library, New York
Lassila T, Rozza G (2010) Parametric free-form shape design with PDE models and reduced basis method. Comput Methods Appl Mech Eng 199(23–24):1583–1592
Le Quilliec G, Raghavan B, Breitkopf P (2015) A manifold learning-based reduced order model for springback shape characterization and optimization in sheet metal forming. Comput Methods Appl Mech Eng 285:621–638
Legrain G, Cartraud P, Perreard I, Moes N (2011) An x-fem and level set computational approach for image-based modelling: application to homogenization. Int J Numer Methods Eng 86(7):915–934
Li K, Carden W, Wagoner R (2002) Simulation of springback. Int J Mech Sci 44(1):103–122
Lopez E, Gonzalez D, Aguado J, Abisset-Chavanne E, Cueto E, Binetruy C, Chinesta F (2016) A manifold learning approach for integrated computational materials engineering. Arch Comput Methods Eng. doi:10.1007/s11831-016-9172-5
Lucia DJ, Beran PS, Silva WA (2004) Reduced-order modeling: new approaches for computational physics. Prog Aerosp Sci 40(1):51–117
Manzoni A, Quarteroni A, Rozza G (2012) Shape optimization for viscous flows by reduced basis methods and free-form deformation. Int J Numer Methods Fluids 70(5):646–670
Marteau J, Bouvier S, Bigerelle M (2015) Review on numerical modeling of instrumented indentation tests for elastoplastic material behavior identification. Arch Comput Methods Eng 22(4):577–593
Meng L, Zhang WH, Zhu JH, Xia L (2014) A biarc-based shape optimization approach to reduce stress concentration effects. Acta Mechanica Sinica 30(3):370–382
Meng L, Breitkopf P, Raghavan B, Mauvoisin G, Bartier O, Hernot X (2015) Identification of material properties using indentation test and shape manifold learning approach. Comput Methods Appl Mech Eng 297:239–257
Meng L, Zhang WH, Zhu JH, Xu Z, Cai SY (2016) Shape optimization of axisymmetric solids with the finite cell method using a fixed grid. Acta Mechanica Sinica 32(3):510–524
Millan D, Rosolen A, Arroyo M (2013) Nonlinear manifold learning for meshfree finite deformation thin-shell analysis. Int J Numer Methods Eng 93(7):685–713
Millan D, Rosolen A, Arroyo M (2013) Nonlinear manifold learning for model reduction in finite elastodynamics. Comput Methods Appl Mech Eng 261(7):118–131
Minsky M (1961) Steps toward artificial intelligence. Proc IRE 49(1):8–30
Moes N, Stolz C, Bernard P, Chevaugeon N (2011) A level set based model for damage growth: The thick level set approach. Int J Numer Methods Eng 86(3):358–380
Montgomery DC, Peck EA, Vining GG (2006) Introduction to linear regression. Wiley, New Jersey
Moon Y, Kang S, Cho J, Kim T (2003) Effect of tool temperature on the reduction of the springback of aluminum sheets. J Mater Process Technol 132(1–3):365–368
Moussa C, Hernot X, Bartier O, Delattre G, Mauvoisin G (2014) Identification of the hardening law of materials with spherical indentation using the average representative strain for several penetration depths. Mater Sci Eng A 606:409–416
Murat F, Simon J (1976) Sur le controle par un domaine geometrique. Pre-publication du Laboratoire d’Analyse Numerique, no 76015, Universite de Paris 6
Nayroles B, Touzot G, Villon P (1992) Generalizing the finite element method: diffuse approximation and diffuse elements. Comput Mech 10(5):307–318
Oshier S, Sethian JA (1988) Fronts propagating with curvature-dependent speed: algorithms based on Hamilton-Jacobi formulations. J Comput Phys 79:12–49
Olof Persson P, Strang G (2004) A simple mesh generator in Matlab. SIAM Rev 46(2):329–345
Peterson JS (1989) The reduced basis method for incompressible viscous flow calculations. SIAM J Sci Stat Comput 10(4):777–786
Prud’homme C, Rovas DV, Veroy K, Machiels L, Maday Y, Patera AT, Turinici G (2002) Reliable real-time solution of parametrized partial differential equations: reduced-basis output bound methods. J Fluids Eng Trans ASME 124(1):70–80
Quarteroni A, Rozza G, Manzoni A (2011) Certified reduced basis approximation for parametrized partial differential equations and applications. J Math Ind 1(1):1–49
Raghavan B, Breitkopf P, Tourbier Y, Villon P (2013) Towards a space reduction approach for structural shape optimization. Struct Multidiscip Optim. doi:10.1007/s00158-013-0942-5
Raghavan B, Hamdaoui M, Xiao M, Breitkopf P, Villon P (2012) A bi-level meta-modeling approach for structural optimization using modified POD bases and diffuse approximation. Comput Struct 127:19–28
Raghavan B, Le Quilliec G, Breitkopf P, Rassineux A, Roelandt JM, Villon P (2014) Numerical assessment of springback for the deep drawing process by level set interpolation using shape manifolds. Int J Mater Form 7(4):487–501
Raghavan B, Xia L, Breitkopf P, Rassineux A, Villon P (2013) Towards simultaneous reduction of both input and output spaces for interactive simulation-based structural design. Comput Methods Appl Mech Eng 265:174–185
Raghavan B, Xia L, Breitkopf P, Rassineux A, Villon P (2013) Towards simultaneous reduction of both input and output spaces for interactive simulation-based structural design. Comput Methods Appl Mech Eng. doi:10.1016/j.cma.2013.06.010
Raghavan B, Xiao M, Breitkopf P, Villon P (2012) Implicit constraint handling for shape optimization using pod-morphing. Eur J Comput Mech 21(3–6):325–336
Rokach L, Maimon O (2014) Data mining with decision trees: theory and applications. World Scientific, Singapore
Rozza G, Huynh D, Patera A (2008) Reduced basis approximation and a posteriori error estimation for affinely parametrized elliptic coercive partial differential equations. Arch Comput Methods Eng 15(3):229–275
Russell S, Norvig P, Intelligence A (1995) A modern approach. Artificial intelligence. Prentice-Hall, Egnlewood Cliffs, pp 25–27
Sahan RA, Gunes H, Liakopoulos A (1998) A modeling approach to transitional channel flow. Comput Fluids 27(1):121–136
Samuel AL (1959) Some studies in machine learning using the game of checkers. IBM J Res Dev 3(3):210–229
Saul LK, Roweis ST (2000) An introduction to locally linear embedding. Unpublished. http://www.cs.toronto.edu/~roweis/lle/publications.html
Saul LK, Weinberger KQ, Ham JH, Sha F, Lee DD (2006) Spectral methods for dimensionality reduction. Semisupervised Learn, MIT Press, Cambridge, pp 293–308
Schulz V (2012) A Riemannian view on shape optimization. Found Comput Math 14(3):483–501
Sebastiani F (2002) Machine learning in automated text categorization. ACM Comput Surv (CSUR) 34(1):1–47
Teimouri R, Baseri H, Rahmani B, Bakhshi-Jooybari M (2012) Modeling and optimization of spring-back in bending process using multiple regression analysis and neural computation. Int J Mater Form. doi:10.1007/s12289-012-1117-4
Toal DJJ, Keane AJ (2011) Efficient multipoint aerodynamic design optimization via cokriging. J Aircr 48(5):1685–1695
Tong S, Koller D (2002) Support vector machine active learning with applications to text classification. J Mach Learn Res 2:45–66
Tu J, Choi KK, Park YH (1999) A new study on reliability-based design optimization. J Mech Des 121(4):557–564
Veiz A, Egerland M (2007) Cad-parametric optimization with optiSLang-ANSYS workbench. In: 4th Weimar optimization and stochastic days
Wang S, Lim K, Khoo B, Wang M (2007) An extended level set method for shape and topology optimization. J Comput Phys 221(1):395–421
Willcox K, Peraire J (2002) Balanced model reduction via the proper orthogonal decomposition. AIAA J 40(11):2323–2330
Xia L, Raghavan B, Breitkopf P, Zhang W (2013) Numerical material representation using proper orthogonal decomposition and diffuse approximation. Appl Math Comput 224:450–462
Xiao M, Breitkopf P, Coelho RF, Knopf-Lenoir C, Sidorkiewicz M, Villon P (2009) Model reduction by CPOD and kriging. Struct Multidiscip Optim 41(4):555–574
Xie X, Mirmehdi M (2011) Radial basis function based level set interpolation and evolution for deformable modelling. Image Vis Comput 29(2–3):167–177
Yagawa G, Okuda H (1996) Neural networks in computational mechanics. Arch Comput Methods Eng 3(4):435–512
Zhang P, Breitkopf P, Knopf-Lenoir C, Zhang W (2011) Diffuse response surface model based on moving latin hypercube patterns for reliability-based design optimization of ultrahigh strength steel NC milling parameters. Struct Multidiscip Optim 44(5):613–628. doi:10.1007/s00158-011-0672-5
Zhang WH, Beckers P, Fleury C (1995) Unified parametric design approach to structural shape optimization. Int J Numer Methods Eng 38(13):2283–2292
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Funding
This study was funded by National Natural Science Foundation of China (Ref No. 11620101002) and the China scholarship Council (Ref No. 201404490062).
Conflict of interest
The authors declare that they have no conflict of interest.
Rights and permissions
About this article
Cite this article
Meng, L., Breitkopf, P., Quilliec, G.L. et al. Nonlinear Shape-Manifold Learning Approach: Concepts, Tools and Applications. Arch Computat Methods Eng 25, 1–21 (2018). https://doi.org/10.1007/s11831-016-9189-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11831-016-9189-9