Research Papers

Co-Evolutionary Optimization for Multi-Objective Design Under Uncertainty

[+] Author and Article Information
Rajan Filomeno Coelho

Associate Professor
Building, Architecture & Town
planning (BATir) Department,
Brussels School of Engineering/École
polytechnique de Bruxelles,
Université libre de Bruxelles,
Avenue Franklin Roosevelt, 50 (CP 194/2),
Brussels B-1050, Belgium
e-mail: rfilomen@ulb.ac.be

Contributed by the Design Automation Committee of ASME for publication in the JOURNAL OF MECHANICAL DESIGN. Manuscript received April 19, 2012; final manuscript received October 22, 2012; published online January 7, 2013. Assoc. Editor: David Gorsich.

J. Mech. Des 135(2), 021006 (Jan 07, 2013) (8 pages) Paper No: MD-12-1212; doi: 10.1115/1.4023184 History: Received April 19, 2012; Revised October 22, 2012

This paper focuses on multi-objective optimization under uncertainty for mechanical design, through a reliability-based formulation referring to the concept of probabilistic nondominance. To address this problem, the implementation of a co-evolutionary strategy is advocated, consisting of the concurrent evolution of two intertwined populations optimized according to coupled subproblems: the upper level optimizer handles the design variables, whereas the corresponding values of the probabilistic thresholds for the objectives (namely the reliable nondominated front) are retrieved at the lower stage. The proposed methodology is successfully applied to six analytical test cases, as well as to the sizing optimization of two truss structures, demonstrating an improved capacity to cover wider ranges of the reliable nondominated front in comparison with all-at-once strategies tackling all types of variables simultaneously.

Copyright © 2013 by ASME
Your Session has timed out. Please sign back in to continue.


Coello Coello, C. A., Van Veldhuizen, D. A., and Lamont, G. B., 2002, Evolutionary Algorithms for Solving Multi-Objective Problems, Kluwer Academic/Plenum Publishers, New York.
Marler, R. T., and Arora, J. S., 2004, “Survey of Multi-Objective Optimization Methods for Engineering,” Struct. Multidiscip. Optim., 26, pp. 369–395. [CrossRef]
Breitkopf, P., and Filomeno Coelho, R., eds., 2010, Multidisciplinary Design Optimization in Computational Mechanics, ISTE/John Wiley & Sons, Chippenham, UK.
Beyer, H.-G., and Sendhoff, B., 2007, “Robust Optimization—A Comprehensive Survey,” Comput. Methods Appl. Mech. Eng., 196, pp. 3190–3218. [CrossRef]
Der Kiureghian, A., and Ditlevsen, O., 2009, “Aleatory or Epistemic? Does it Matter?,” Struct. Saf., 31, pp. 105–112. [CrossRef]
Achenie, L. E. K., and Ostrovsky, G. M., 2005, “Multicriteria Optimization Under Parametric Uncertainty,” Applied Research in Uncertainty Modeling and Analysis, Springer, USA.
Barakat, S., Bani-Hanib, K., and Taha, M. Q., 2004, “Multi-Objective Reliability-Based Optimization of Prestressed Concrete Beams,” Struct. Saf., 26, pp. 311–342. [CrossRef]
Sinha, K., 2007, “Reliability-Based Multiobjective Optimization for Automotive Crashworthiness and Occupant Safety,” Struct. Multidiscip. Optim., 33, pp. 255–268. [CrossRef]
Kumar, A., Nair, P. B., Keane, A. J., and Shahpar, S., 2008, “Robust Design Using Bayesian Monte Carlo,” Int. J. Numer. Methods Eng., 73, pp. 1497–1517. [CrossRef]
Mourelatos, Z. P., and Liang, J., 2006, “A Methodology for Trading-Off Performance and Robustness Under Uncertainty,” ASME J. Mech. Des., 128(4), pp. 856–863. [CrossRef]
Deb, K., and Gupta, H., 2006, “Introducing Robustness in Multi-Objective Optimization,” Evol. Comput., 14(4), pp. 463–494. [CrossRef] [PubMed]
Deb, K., Pratap, A., Agarwal, S., and Meyarivan, T., 2002, “A Fast and Elitist Multiobjective Genetic Algorithm: NSGA-II,” IEEE Trans. Evol. Comput., 6(2), pp. 182–197. [CrossRef]
Basseur, M., and Zitzler, E., 2006, “Handling Uncertainty in Indicator-Based Multiobjective Optimization,” Int. J. Comput. Intell. Res., 2(3), pp. 255–272. Available at http://www.ripublication.com/ijcirv2/ijcirv2n3_3
Köppen, M., Vicente-Garcia, R., and Nickolay, B., 2005, “Fuzzy-Pareto-Dominance and Its Application in Evolutionary Multi-Objective Optimization,” Evolutionary Multi-Criterion Optimization, 3rd International Conference, EMO 2005, Guanajuato, Mexico, March 9–11, pp. 399–412.
Limbourg, P., 2005, “Multi-Objective Optimization of Problems With Epistemic Uncertainty,” Evolutionary Multi-Criterion Optimization, 3rd International Conference, EMO 2005, Guanajuato, Mexico, March 9–11, pp. 413–427.
Filomeno Coelho, R., Lebon, J., and Bouillard, Ph., 2011, “Hierarchical Stochastic Metamodels Based on Moving Least Squares and Polynomial Chaos Expansion—Application to the Multiobjective Reliability-Based Optimization of 3D Truss Structures,” Struct. Multidiscip. Optim., 43(5), pp. 707–729. [CrossRef]
Filomeno Coelho, R., and Bouillard, Ph., 2011, “Multi-Objective Reliability-Based Optimization With Stochastic Metamodels,” Evol. Comput., 19(4), pp. 525–560. [CrossRef] [PubMed]
Zou, T., and Mahadevan, S., 2006, “Versatile Formulation for Multiobjective Reliability-Based Design Optimization,” ASME J. Mech. Des., 128(6), pp. 1217–1226. [CrossRef]
Haldar, A., and Mahadevan, S., 2000, Reliability Assessment Using Stochastic Finite Element Analysis, John Wiley & Sons, Chichester, UK.
Deb, K., Padmanabhan, D., Gupta, S., and Mall, A. K., 2007, “Reliability-Based Multi-Objective Optimization Using Evolutionary Algorithms,” Evolutionary Multi-Criterion Optimization, Springer, Berlin/Heidelberg.
Deb, K., Gupta, S., Jaum, D., Branke, J., Mall, A. K., and Padmanabhan, D., 2009, “Reliability-Based Optimization Using Evolutionary Algorithms,” IEEE Trans. Evol. Comput., 13(5), pp. 1054–1074. [CrossRef]
Levi, F., Gobbi, M., and Mastinu, G., 2005, “An Application of Multi-Objective Stochastic Optimisation to Structural Design,” Struct. Multidiscip. Optim., 29, pp. 272–284. [CrossRef]
Caballero, R., Cerdá, E., Muñoz, M. M., Rey, L., and Stancu-Minasian, I. M., 2001, “Efficient Solution Concepts and Their Relations in Stochastic Multiobjective Programming,” J. Optim. Theory Appl., 110(1), pp. 53–74. [CrossRef]
Wang, Z., Huang, H.-Z., and Liu, Y., 2010, “A Unified Framework for Integrated Optimization Under Uncertainty,” ASME J. Mech. Des., 132(5), p. 051008. [CrossRef]
Rangavajhala, S., and Mahadevan, S., 2011, “Joint Probability Formulation for Multiobjective Optimization Under Uncertainty,” ASME J. Mech. Des., 133, p. 051007. [CrossRef]
Tichý, M., 1993, Applied Methods of Structural Reliability, Kluwer Academic Publishers, The Netherlands.
Teich, J., 2001, “Pareto-Front Exploration With Uncertain Objectives,” Evolutionary Multi-Criterion Optimization, Vol. 1993 (Lecture Notes in Computer Science), Springer, New York, pp. 314–328.
Eiben, A. E., Hinterding, R., and Michalewicz, Z., 1999, “Parameter Control in Evolutionary Algorithms,” IEEE Trans. Evol. Comput., 3(2), pp. 124–141. [CrossRef]
Paredis, J., 1995, “Coevolutionary Computation,” Artif. Life, 2(4), pp. 355–375. [CrossRef] [PubMed]
Michalewicz, Z., and Nazhiyath, G., 1995, “Genocop III: A Co-Evolutionary Algorithm for Numerical Optimization Problems With Nonlinear Constraints,” 2nd IEEE International Conference on Evolutionary Computation, Perth, Australia, November 29–December 1, pp. 647–651.
Schaffer, J. D., 1985, “Multiple Objective Optimization With Vector Evaluated Genetic Algorithms,” Proceedings of the 1st International Conference on Genetic Algorithms, Pittsburgh, PA, July 24–26, pp. 93–100.
Parmee, I. C., and Watson, A. H., 1999, “Preliminary Airframe Design Using Co-Evolutionary Multiobjective Genetic Algorithms,” Genetic and Evolutionary Computation Conference—GECCO 1999, Orlando, Florida, July 13–17, pp. 1657–1665.
Greiner, D., and Hajela, P., 2012, “Truss Topology Optimization for Mass and Reliability Considerations–Co-Evolutionary Multiobjective Formulations,” Struct. Multidiscip. Optim., 45, pp. 589–613. [CrossRef]
Nash, J., 1951, “Non-Cooperative Games,” Ann. Math., 54(2), pp. 286–295. [CrossRef]
Barbosa, H. J. C., and Barreto, A. M. S., 2001, “An Interactive Genetic Algorithm With Co-Evolution of Weights for Multiobjective Problems,” Genetic and Evolutionary Computation Conference (GECCO-2001), San Francisco, California, July 7–11, pp. 203–210.
Cabrera, J., Ortiz, A., Estebanez, B., Nadal, F., and Simon, A., 2010, “A Coevolutionary Algorithm for Tyre Model Parameters Identification,” Struct. Multidiscip. Optim., 41(5), pp. 749–763. [CrossRef]
Deb, K., Gupta, S., Dutta, J., and Ranjan, B., 2011, “Solving Dual Problems Using a Coevolutionary Optimization Algorithm,” Kanpur Genetic Algorithms Laboratory, Indian Institute of Technology, Kanpur, KanGAL Technical Report No. 2011009.
Nema, S., Goulermas, J., Sparrow, G., and Helman, P., 2011, “A Hybrid Cooperative Search Algorithm for Constrained Optimization,” Struct. Multidiscip. Optim., 43(1), pp. 107–119. [CrossRef]
Zitzler, E., Thiele, L., Laumanns, M., Fonseca, C. M., and Grunert da Fonseca, V., 2003, “Performance Assessment of Multiobjective Optimizers: An Analysis and Review,” IEEE Trans. Evol. Comput., 7(2), pp. 117–132. [CrossRef]
Haftka, R. T., and Gürdal, Z., 1992, Elements of Structural Optimization, Kluwer Academic Publishers, Dordrecht.
Greco, M., Gesualdo, F. A. R., Venturini, W. S., and Coda, H. B., 2006, “Nonlinear Positional Formulation for Space Truss Analysis,” Finite Elem. Anal. Des., 42, pp. 1079–1086. [CrossRef]
Knowles, J. D., and Corne, D. W., 2000, “Approximating the Nondominated Front Using the Pareto Archived Evolution Strategy,” Evol. Comput., 8(2), pp. 149–172. [CrossRef] [PubMed]
Gunawan, S., and Papalambros, P. Y., 2006, “A Bayesian Approach to Reliability-Based Optimization With Incomplete Information,” ASME J. Mech. Des., 128, pp. 909–918. [CrossRef]
Mahadevan, S., and Rebba, R., 2006, “Inclusion of Model Errors in Reliability-Based Optimization,” ASME J. Mech. Des., 128, pp. 936–944. [CrossRef]


Grahic Jump Location
Fig. 1

Example of probability of nondominance in a bicriterion problem (joint probability): the dark region illustrates the region of the objective space dominating ζ

Grahic Jump Location
Fig. 2

Example of probability of nondominance in a bicriterion problem (objective space): the shaded area illustrates the region of the objective space dominating ζ, while the contours depict isoprobability values for the objective vectors

Grahic Jump Location
Fig. 3

All quantile vectors ζ  ∈  {ζA,…,ζB} are dominated by the objectives (sampled with respect to the random variables θ for a fixed value of the design vector x) with the same probability αf; the quadrants (in dashed lines) represent two regions of the objective space with identical probability of dominating each point ζ, according to the isoprobability contours of {f1(xfixed,θ),f2(xfixed,θ)}

Grahic Jump Location
Fig. 4

Schematic view of the co-evolutionary framework for multi-objective reliability-based optimization

Grahic Jump Location
Fig. 5

Quantile nondominated front (ζ) for test case TC1: optimization with respect to {x,ζ} (left), with respect to {x,η} (middle), and co-evolutionary optimization (right)

Grahic Jump Location
Fig. 6

Quantile nondominated front (ζ) for test case TC5: optimization with respect to {x,ζ} (left), with respect to {x,η} (middle), and co-evolutionary optimization (right)

Grahic Jump Location
Fig. 7

Deterministic trade-off set (left) versus co-evolutionary reliability-based trade-off set for test case TC5 (right), showing the discrepancy in the design solutions obtained by accounting or not for probabilistic nondominance

Grahic Jump Location
Fig. 8

Truss configuration for test case t25b

Grahic Jump Location
Fig. 9

Truss configuration for test case dome

Grahic Jump Location
Fig. 10

Results obtained for test case dome: nondominated Pareto front (left), deterministic nondominated set (middle), and reliability-based nondominated set (right)



Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In