Abstract
For most engineering design optimization problems, it is difficult or even impossible to find the global optimum due to the unaffordable computational cost. To overcome this difficulty, a global optimization method that integrates the ensemble of metamodels and fuzzy clustering is proposed to deal with the optimization problems involving the computation-intensive, black-box computer analysis and simulation. The ensemble of metamodels combining three representative metamodeling techniques with optimized weight factors is used to decrease the computational expense during the optimization procedure and the fuzzy clustering technique is applied to obtain the reduced design space. In this way, the efficiency and capability of capturing the global optimum will be improved in the reduced design space. To demonstrate the superior performance of the proposed global optimization method over existing methods, it is examined using various benchmark optimization problems and applied to solve an engineering design optimization problem. The results show that the proposed global optimization method is robust and efficient in capturing the global optimum.
Similar content being viewed by others
Abbreviations
- x :
-
Vector of the design variable
- x k :
-
Vector of the kth sampling point
- m :
-
Number of metamodels in the ensemble
- n :
-
Number of design variables
- N :
-
Number of sampling points
- \(\tilde{y}_{e} (\varvec{x})\) :
-
Predicted response of the ensemble of metamodels
- \(\tilde{y}_{i} (\varvec{x})\) :
-
Predicted response of the ith metamodel
- \(y(\varvec{x}_{k} )\) :
-
True response at the kth sampling point
- \(\tilde{y}_{e} (\varvec{x}_{k} )\) :
-
Predicted response of the ensemble of metamodels at the kth sampling point
- \(\omega_{i} (\varvec{x})\) :
-
Corresponding weight factor of the ith metamodel
- α :
-
Control the importance of averaging metamodels
- β :
-
Control the importance of individual metamodels
- k :
-
An index of iteration
- m ini :
-
Initial number of sampling points
- m_s :
-
Number of all sampling points in the sample
- m max :
-
Maximum number of expensive function evaluations allowed
References
Koch PN, Simpson TW, Allen JK, Mistree F (1999) Statistical approximations for multidisciplinary design optimization: the problem of size. J Aircr 36(1):275–286
Gu L (2001) A comparison of polynomial based regression models in vehicle safety analysis. In: ASME design engineering technical conferences-design automation conference, ASME, Pittsburgh, PA, pp DETC2001/DAC-21063
Simpson TW, Peplinski J, Koch PN, Allen JK (2001) Metamodels for computer-based engineering design: survey and recommendations. Eng Comput 17(2):129–150
Paiva R, Carvalho A, Crawford C, Suleman A (2010) Comparison of surrogate models in a multidisciplinary optimization framework fir wing design. AIAA J 48(5):995–1006
Carrese R, Sobester A, Winarto H, Li X (2011) Swarm heuristic for identifying preferred solutions in surrogate-based multi-objective engineering design. AIAA J 49:1437–1449
Jones DR, Schonlau M, Welch WJ (1998) Efficient global optimization of expensive black-box functions. J Glob Optim 13(4):455–492
Jin R, Chen W, Simpson TW (2001) Comparative studies of metamodeling techniques under multiple modeling criteria. Struct Multidiscip Optim 23:1–13
Wang GG, Shan S (2007) Review of metamodeling techniques in support of engineering design optimization. J Mech Des 129:370–380
Forrester AIJ, Keane AJ (2009) Recent advances in surrogate-based optimization. Prog Aerosp Sci 45:50–79
Box GEP, Draper NR (1969) Evolutionary operation: a statistical method for process management. Wiley, New York
Balabanov VO, Giunta AA, Golovidov O, Grossman B, Mason WH, Watson LT (1999) Reasonable design space approach to response surface approximation. J Aircr 36(1):308–315
Viswanath A, Forrester AIJ, Keane AJ (2011) Dimension reduction for aerodynamic design optimization. AIAA J 49(6):1256–1266
Chen W, Allen JK, Schrage DP, Mistree F (1997) Statistical experimentation methods for achieving affordable concurrent systems design. AIAA J 35(5):893–900
Wang GG, Simpson TW (2004) Fuzzy clustering based hierarchical metamodeling for design space reduction and optimization. Eng Optim 36(3):313–335
Bezdek JC, Dunn JC (1975) Optimal fuzzy partitions: a heuristic for estimating the parameters in a mixture of normal distributions. IEEE Trans Comput 100(8):835–838
Bezdek JC (1981) Pattern recognition with fuzzy objective function algorithms. Plenum Press, New York
Myers RH, Montgomery DC (1995) Response surface methodology: process and product optimization using designed experiments. Wiley, New York
Makadia AJ, Nanavati JI (2013) Optimisation of machining parameters for turning operations based on response surface methodology. Measurement 46(4):1521–1529
Babu GS, Suresh S (2013) Sequential projection-based metacognitive learning in a radial basis function network for classification problems. IEEE Trans Neural Netw Learn Syst 24(2):194–206
Yao W, Chen XQ, Huang YY, Tooren MV (2014) A surrogate-based optimization method with RBF neural network enhanced by linear interpolation and hybrid infill strategy. Optim Methods Softw 29(2):406–429
Martin JD, Simpson TW (2005) Use of kriging models to approximate deterministic computer models. AIAA J 43(4):853–863
Couckuyt I, Koziel S, Dhaene T (2013) Surrogate modeling of microwave structures using kriging, co-kriging, and space mapping. Int J Numer Model Electron Netw Devices Fields 26(1):64–73
Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, New York
Goel T, Haftka RT, Shyy W, Queipo NV (2007) Ensemble of surrogates. Struct Multidiscip Optim 33(3):199–216
Viana FAC (2011) SURROGATES toolbox user’s guide, version 3.0 ed. Gainesville, FL, USA. http://sites.google.com/site/felipeacviana/surrogatestoolbox
Wang G, Dong Z, Aitchison P (2001) Adaptive response surface method—a global optimization scheme for computation-intensive design problems. Eng Optim 33(6):707–734
Wang LQ, Shan SQ, Wang GG (2004) Mode-pursuing sampling method for global optimization on expensive black-box functions. Eng Optim 36:419–438
Gu J, Li GY, Dong Z (2012) Hybrid and adaptive meta-model-based global optimization. Eng Optim 44(1):87–104
Li YL, Liu L, Long T, Dong WL (2013) Metamodel-based global optimization using fuzzy clustering for design space reduction. Chin J Mech Eng 26(5):928–939
Younis A, Xu R, Dong Z, (2007) Approximated unimodal region elimination based global optimization method for engineering design. In: Proceedings of the ASME 2007 international design engineering technical conferences and computers and information in engineering conference, pp 4–7
Adorio EP (2005) MVF-multivariate test functions library in c for unconstrained global optimization. http://www.geocities.ws/eadorio/mvf.pdf
Wang GG (2003) Adaptive response surface method using inherited latin hypercube design points. J Mech Des 125(2):210–220
Gandomi AH, Yang XS, Alavi AH (2013) Cuckoo search algorithm: a metaheuristic approach to solve structural optimization problems. Eng Comput 29(1):17–35
Acknowledgments
Authors would like to thank everybody for their encouragement and support. The grant support from Innovation Foundation for Doctor Dissertation of Northwestern Polytechnical University (Grant No. CX201603) are greatly acknowledged.
Author information
Authors and Affiliations
Corresponding author
Appendix: Description of selected metamodeling techniques
Appendix: Description of selected metamodeling techniques
1.1 Response surface method, RSM
Response surface method is one of the most popular established metamodeling techniques. The standard RSM first employs an experimental strategy to generate design points in the design space, then applies either a first-order model or a second-order model to approximate the unknown system. The most commonly used RSM model is the second-order model in the form of a second-degree algebraic polynomial function as:
where n is the number of variables in the input vector x; \(\tilde{f}(\varvec{x})\) is the response surface approximation of the actual function. \(\beta_{0} , \;\beta_{i} ,\;\beta_{ii} ,\;\beta_{ij}\) represent unknown regression coefficients which can be calculated by the least squares technique.
1.2 Radial basis function, RBF
The approximate method RBF is originally developed by Hardy in 1971 to fit irregular topographic contours of geographical data. It has been known tested and verified for several decades and many positive properties have been identified.
For a data set consisting of the values of design variables and response values at N sampling points, the true function \(f(\varvec{x})\) can be approximated as
where x is a vector of the design variables, x i is a vector of the design variables at the ith sampling point, \(\varvec{x} - \varvec{x}_{i} = \sqrt {\left( {\varvec{x} - \varvec{x}_{i} } \right)^{T} \left( {\varvec{x} - \varvec{x}_{i} } \right)}\) is the Euclidean norm, representing the radial distance r, from design point x to the sampling point x i , \(\phi\) is a basis function and λ i is the coefficient for the ith basis function. The approximation function \(\tilde{f}(\varvec{x})\) is actually a linear combination of some basis functions with weight coefficients λ i . The most commonly used basis functions are listed in Table 5. In this study, the basis function multiquadrics are chosen because of its prediction accuracy and its commonly linear and possibly exponential rate of convergence with increased sampling points. Besides, the choice of c 1 = 1 is found to be suitable for most function approximations which is used in this paper.
1.3 Kriging
Kriging is named after the original work of South African engineer D.G. Krige. It estimates the value of a function as a combination of a known function \(\tilde{f}_{i} (\varvec{x})\) (e.g., a linear model such as a polynomial trend) and departures (representing low and high frequency variation components, respectively,) of the form:
where \(\beta_{i}\) is an unknown constant estimated, Z(x) is assumed to be a realization of a stochastic process with zero mean and a nonzero covariance. The i, jth element of covariance matrix of Z(x) is given by
where \(\sigma_{z}^{2}\) is the process variance, and R ij is the correlation function between the ith and jth data points; The Gaussian function is used as the correlation function in this study, defined by
where \(\theta_{k}\) is distinct for each dimension, and these unknown parameters are generally determined by solving a nonlinear optimization problem.
Rights and permissions
About this article
Cite this article
Ye, P., Pan, G. Global optimization method using ensemble of metamodels based on fuzzy clustering for design space reduction. Engineering with Computers 33, 573–585 (2017). https://doi.org/10.1007/s00366-016-0490-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00366-016-0490-x