Robust design optimization by polynomial dimensional decomposition

Research Paper


This paper introduces four new methods for robust design optimization (RDO) of complex engineering systems. The methods involve polynomial dimensional decomposition (PDD) of a high-dimensional stochastic response for statistical moment analysis, a novel integration of PDD and score functions for calculating the second-moment sensitivities with respect to the design variables, and standard gradient-based optimization algorithms. New closed-form formulae are presented for the design sensitivities that are simultaneously determined along with the moments. The methods depend on how statistical moment and sensitivity analyses are dovetailed with an optimization algorithm, encompassing direct, single-step, sequential, and multi-point single-step design processes. Numerical results indicate that the proposed methods provide accurate and computationally efficient optimal solutions of RDO problems, including an industrial-scale lever arm design.


Design under uncertainty ANOVA dimensional decomposition Orthogonal polynomials Score functions Optimization 


  1. Browder A (1996) Mathematical analysis: an introduction. Undergraduate texts in mathematics. Springer, New YorkCrossRefGoogle Scholar
  2. Busbridge I (1948) Some integrals involving hermite polynomials. J Lond Math Soc 23:135–141MathSciNetMATHCrossRefGoogle Scholar
  3. Chen W, Allen J, Tsui K, Mistree F (1996) Procedure for robust design: minimizing variations caused by noise factors and control factors. J Mech Des, Trans ASME 118(4):478–485CrossRefGoogle Scholar
  4. DOT (2001) Dot—designoptimization tools, user’s manual. Vanderplaats Research and Development, Inc., Colorado Springs, COGoogle Scholar
  5. Du XP, Chen W (2000) Towards a better understanding of modeling feasibility robustness in engineering design. J Mech Des 122(4):385–394CrossRefGoogle Scholar
  6. Efron B, Stein C (1981) The jackknife estimate of variance. Ann Stat 9(3):586–596MathSciNetMATHCrossRefGoogle Scholar
  7. Gautschi W (2004) Orthogonal polynomials: computation and approximation. Numerical mathematics and scientific computation. Oxford University Press, OxfordGoogle Scholar
  8. Huang B, Du X (2007) Analytical robustness assessment for robust design. Struct Multidisc Optim 34(2):123–137MathSciNetCrossRefGoogle Scholar
  9. Lee I, Choi KK, Du L, Gorsich D (2008) Dimension reduction method for reliability-based robust design optimization. Comput Struct 86(13–14):1550–1562CrossRefGoogle Scholar
  10. Lee S, Chen W, Kwak B (2009) Robust design with arbitrary distributions using gauss-type quadrature formula. Struct Multidisc Optim 39(3):227–243MathSciNetCrossRefGoogle Scholar
  11. Mourelatos Z, Liang J (2006) A methodology for trading-off performance and robustness under uncertainty. J Mech Des 128(4):856–863CrossRefGoogle Scholar
  12. Park G, Lee T, Kwon H, Hwang K (2006) Robust design: an overview. AIAA J 44(1):181–191CrossRefGoogle Scholar
  13. Rahman S (2008) A polynomial dimensional decomposition for stochastic computing. Int J Numer Methods Eng 76(13):2091–2116MATHCrossRefGoogle Scholar
  14. Rahman S (2009a) Extended polynomial dimensional decomposition for arbitrary probability distributions. J Eng Mech ASCE 135(12):1439–1451CrossRefGoogle Scholar
  15. Rahman S (2009b) Stochastic sensitivity analysis by dimensional decomposition and score functions. Probab Eng Mech 24(3):278–287CrossRefGoogle Scholar
  16. Rahman S (2010) Statistical moments of polynomial dimensional decomposition. J Eng Mech ASCE 136(7):923–927CrossRefGoogle Scholar
  17. Rahman S (2011) Decomposition methods for structural reliability analysis revisited. Probab Eng Mech 26(2):357–363CrossRefGoogle Scholar
  18. Rahman S (2012) Approximation errors in truncated dimensional decompositions. Math Comput, submittedGoogle Scholar
  19. Rahman S, Xu H (2004) A univariate dimension-reduction method for multi-dimensional integration in stochastic mechanics. Probab Eng Mech 19(4):393–408CrossRefGoogle Scholar
  20. Ramakrishnan B, Rao S (1996) A general loss function based optimization procedure for robust design. Eng Optim 25(4):255–276CrossRefGoogle Scholar
  21. Rubinstein R, Shapiro A (1993) Discrete event systems: sensitivity analysis and stochastic optimization by the score function method. Wiley series in probability and mathematical statistics. Wiley, New YorkGoogle Scholar
  22. Sobol I (2003) Theorems and examples on high dimensional model representation. Reliab Eng Syst Saf 79(2):187–193MathSciNetCrossRefGoogle Scholar
  23. Stephens R, Fuchs H (2001) Metal fatigue in engineering. Wiley-Interscience, New YorkGoogle Scholar
  24. Taguchi G (1993) Taguchi on robust technology development: bringing quality engineering upstream. ASME Press series on international advances in design productivity. ASME Press, New YorkCrossRefGoogle Scholar
  25. Toropov V, Filatov A, Polynkin A (1993) Multiparameter structural optimization using FEM and multipoint explicit approximations. Struct Multidisc Optim 6(1):7–14CrossRefGoogle Scholar
  26. Wang H, Kim N (2006) Robust design using stochastic response surface and sensitivities. In: 11th AIAA/ISSMO multidisciplinary analysis and optimization conferenceGoogle Scholar
  27. Xu H, Rahman S (2004) A generalized dimension-reduction method for multidimensional integration in stochastic mechanics. Int J Numer Methods Eng 61(12):1992–2019MATHCrossRefGoogle Scholar
  28. Youn B, Xi Z, Wang P (2008) Eigenvector dimension reduction (EDR) method for sensitivity-free probability analysis. Struct Multidisc Optim 37(1):13–28MathSciNetCrossRefGoogle Scholar
  29. Zaman K, McDonald M, Mahadevan S, Green L (2011) Robustness-based design optimization under data uncertainty. Struct Multidisc Optim 44(2):183–197CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  1. 1.Department of Mechanical & Industrial EngineeringThe University of IowaIowa CityUSA

Personalised recommendations