Advertisement

D-optimality of non-regular design spaces by using a Bayesian modification and a hybrid method

  • Magnus HofwingEmail author
  • Niclas Strömberg
Research Paper

Abstract

In this work a hybrid method of a genetic algorithm and sequential linear programming is suggested to obtain a D-optimal design of experiments. Regular as well as non-regular design spaces are considered. A D-optimal design of experiments maximizes the determinant of the information matrix, which appears in the normal equation. It is known that D-optimal design of experiments sometimes include duplicate design points. This is, of course, not preferable since duplicates do not add any new information to the response surface approximation and the computational effort is therefore wasted. In this work a Bayesian modification, where higher order terms are added to the response surface approximation, is used in case of duplicates in the design of experiments. In such manner, the draw-back with duplicates might be eliminated. The D-optimal problem, which is obtained by using the Bayesian modification, is then solved by a hybrid method. A hybrid method of a genetic algorithm that generates a starting point for sequential linear programming is developed. The genetic algorithm performs genetic operators such as cross-over and mutation on a binary version of the design of experiments, while the real valued version is used to evaluate the fitness. Next, by taking the gradient of the objective, a LP-problem is formulated which is solved by an interior point method that is available in Matlab. This is repeated in a sequence until convergence is reached. The hybrid method is tested for five numerical examples. Results from the numerical examples show a very robust convergence to a global optimum. Furthermore, the results show that the problem with duplicates is eliminated by using the Bayesian modification.

Keywords

D-optimality Design of experiments (DoE) Sequential linear programming (SLP)  Genetic algorithms (GA) Response surface methodology (RSM) Bayesian modification (BM) 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Bäck T (1996) Evolutionary algorithms in therory and practice. Oxford University Press, New YorkGoogle Scholar
  2. Broudiscou A, Leardi R, Phan-Tan-Luu R (1996) Genetic algorithm as a tool for selection of d-optimal design. Chemometr Intell Lab Syst 35:105–116CrossRefGoogle Scholar
  3. DuMouchel W, Jones B (1994) A simple bayesian modification of D-optimal designs to reduce dependence on an assumed model. Technometrics 36:37–47zbMATHCrossRefGoogle Scholar
  4. Engelbrecht AP (2002) Computational intelligence. Wiley, ChichesterGoogle Scholar
  5. Fedorov VV (1972) Theory of experiments. Academic, New YorkGoogle Scholar
  6. Goel T, Haftka RT, Shyy W, Watson LT (2008) Pitfalls of using a single criterion for selecting experimental designs. Int J Numer Method Eng 75(2):127–155CrossRefGoogle Scholar
  7. Goel T, Haftka RT, Shyy W (2009) Comparing error estimation measures for polynomial and kriging approximation of noise-free functions. Struct Multidisc Optim 38:429–442CrossRefGoogle Scholar
  8. Goldenberg DE (1989) Genetic algorithms in search, optimization, & machine learning. Addison-Wesley, ReadingGoogle Scholar
  9. Griffith RE, Stewart RA (1960–1961) A nonlinear programming technique for the optimization of continuous processing systems. Manage Sci 7:379–392CrossRefMathSciNetGoogle Scholar
  10. Gustafsson E, Strömberg N (2007) Successive response surface methodology by using neural networks. In: The proceedings of the 7th world congress on structural and multidisciplinary optimization, Seoul, Korea, 21–25 MayGoogle Scholar
  11. Gustafsson E, Strömberg N (2008) Shape optimization of castings by using successive response surface methodology. Struct Multidisc Optim 35:11–28CrossRefGoogle Scholar
  12. Hofwing M, Strömberg N (2009) D-optimality of non-regular design spaces by using a genetic algorithm. In: The proceedings of the 8th world congress on structural and multidisciplinary optimization, Lisbon, Portugal, 1–5 JuneGoogle Scholar
  13. Holland JH (1975) Adaption in natural and artifical systems. University of Michigan Press, Ann ArborGoogle Scholar
  14. Jansson T, Nilsson LG, Redhe M (2006) Using surrogate models and response surfaces in structural optimization. Struct Multidisc Optim 31:320–332CrossRefGoogle Scholar
  15. Jiang Z, Liu B, Dai LK, Wu TJ (2003) A hybrid genetic algorithm integrated with sequential linear programming. In: International conference on machine learning and cybernetics, vol 2, pp 1030–1033Google Scholar
  16. Lamberti L, Pappalettere C (2004) Improved sequential linear programming formulation for structural weight minimization. Computational Methods in Applied Mechanical Engineering 193:3493–3521zbMATHCrossRefGoogle Scholar
  17. Mathworks (2006) MATLAB: the language of technical computing. MathworksGoogle Scholar
  18. Meyer RK, Nachtsheim CJ (1995) The coordinate-exchange algorithm for constructing exact optimal experimental designs. Technometrics 37:60-69zbMATHCrossRefMathSciNetGoogle Scholar
  19. Myers RH, Montgomery DC (2002) Response surface methodology, 2nd edn. Wiley-Interscience, New YorkzbMATHGoogle Scholar
  20. Strömberg N, Klarbring A (2009) Topology optimization of structures in unilateral contact. Struct Multidisc Optim. doi: 10.1007/s00158-009-0407-z zbMATHGoogle Scholar
  21. Todoroki A, Ishikawa T (2004) Design of experiments for stacking sequence optimazations with genetic algorithm using response surface approximation. Compos Struct 64:349–357CrossRefGoogle Scholar
  22. Zhang Y (1995) Solving large-scale linear programs by interior-point methods under the matlab environment. Technical report, Department of Mathematics and Statistics, University of Maryland, Baltimore County, BaltimoreGoogle Scholar

Copyright information

© Springer-Verlag 2009

Authors and Affiliations

  1. 1.Department of Mechanical EngineeringJönköping UniversityJönköpingSweden

Personalised recommendations