An enhanced RBF-HDMR integrated with an adaptive sampling method for approximating high dimensional problems in engineering design

Metamodels are often used in engineering design optimization problems with expensive simulations to save computational cost. But these metamodels often face “curse-of-dimensionality” when used in approximating high dimensional problems. Therefore, a new high dimensional model representation (HDMR) by combining Cut-HDMR with an enhanced RBF based on ensemble model is proposed. The developed HDMR, termed as ERBF-HDMR, sufficiently utilizes advantages of RBF and ensemble model in the modeling process. It can naturally explore and exploit the linearity/nonlinearity and correlations among variables of underlying problems, which are unknown or computationally expensive. Besides, to improve the efficiency of the ERBF-HDMR, an adaptive sampling method is proposed to add new sample points. Moreover, a mathematical function is used to illustrate the modeling principles and procedures of the adaptive ERBF-HDMR. And a comprehensive comparison between the adaptive ERBF-HDMR and other different Cut-HDMRs in literature has been made on eleven numerical examples with a wide scope of dimensionalities to show the prediction ability of different HDMRs. Finally, the proposed HDMR is used in the structural design optimization of the bearings of an all-direction propeller with the aim of reducing vibration.

[1]  Roman M. Balabin,et al.  Support vector machine regression (SVR/LS-SVM)--an alternative to neural networks (ANN) for analytical chemistry? Comparison of nonlinear methods on near infrared (NIR) spectroscopy data. , 2011, The Analyst.

[2]  M. Rais-Rohani,et al.  Ensemble of metamodels with optimized weight factors , 2008 .

[3]  David J. J. Toal,et al.  Performance of an ensemble of ordinary, universal, non-stationary and limit Kriging predictors , 2013 .

[4]  Rajib Chowdhury,et al.  Hybrid High Dimensional Model Representation for reliability analysis , 2009 .

[5]  T. Ziehn,et al.  A global sensitivity study of sulfur chemistry in a premixed methane flame model using HDMR , 2008 .

[6]  G. G. Wang,et al.  Mode-pursuing sampling method for global optimization on expensive black-box functions , 2004 .

[7]  Guangyao Li,et al.  Advanced high strength steel springback optimization by projection-based heuristic global search algorithm , 2013 .

[8]  K. Yamazaki,et al.  Sequential Approximate Optimization using Radial Basis Function network for engineering optimization , 2011 .

[9]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[10]  Songqing Shan,et al.  Turning Black-Box Functions Into White Functions , 2011 .

[11]  Donald R. Jones,et al.  Efficient Global Optimization of Expensive Black-Box Functions , 1998, J. Glob. Optim..

[12]  Hans-Martin Gutmann,et al.  A Radial Basis Function Method for Global Optimization , 2001, J. Glob. Optim..

[13]  Dirk Gorissen,et al.  A Novel Hybrid Sequential Design Strategy for Global Surrogate Modeling of Computer Experiments , 2011, SIAM J. Sci. Comput..

[14]  Franz Aurenhammer,et al.  Voronoi diagrams—a survey of a fundamental geometric data structure , 1991, CSUR.

[15]  Colin H. Hansen,et al.  Power transmission from a vibrating body to a circular cylindrical shell through passive and active isolators , 1997 .

[16]  Ruichen Jin,et al.  On Sequential Sampling for Global Metamodeling in Engineering Design , 2002, DAC 2002.

[17]  Erik Kjeang,et al.  Modification of DIRECT for high-dimensional design problems , 2014 .

[18]  Marianthi G. Ierapetritou,et al.  Parametric process synthesis for general nonlinear models , 2003, Comput. Chem. Eng..

[19]  Liang Gao,et al.  An adaptive SVR-HDMR model for approximating high dimensional problems , 2015 .

[20]  Rajib Chowdhury,et al.  Probabilistic Analysis Using High Dimensional Model Representation and Fast Fourier Transform , 2008 .

[21]  Christine A. Shoemaker,et al.  Constrained Global Optimization of Expensive Black Box Functions Using Radial Basis Functions , 2005, J. Glob. Optim..

[22]  H. Rabitz,et al.  Practical Approaches To Construct RS-HDMR Component Functions , 2002 .

[23]  Hu Wang,et al.  Adaptive MLS-HDMR metamodeling techniques for high dimensional problems , 2011, Expert Syst. Appl..

[24]  Jing Tang Xing,et al.  A general linear mathematical model of power flow analysis and control for integrated structure-control systems , 2003 .

[25]  H. Rabitz,et al.  Efficient input-output model representations , 1999 .

[26]  Christine A. Shoemaker,et al.  Global Convergence of Radial Basis Function Trust-Region Algorithms for Derivative-Free Optimization , 2013, SIAM Rev..

[27]  Herschel Rabitz,et al.  Efficient Implementation of High Dimensional Model Representations , 2001 .

[28]  Songqing Shan,et al.  Development of Adaptive RBF-HDMR Model for Approximating High Dimensional Problems , 2009, DAC 2009.

[29]  R. Haftka,et al.  Ensemble of surrogates , 2007 .

[30]  G. Gary Wang,et al.  Survey of modeling and optimization strategies to solve high-dimensional design problems with computationally-expensive black-box functions , 2010 .

[31]  G. Gary Wang,et al.  Trust Region Based Mode Pursuing Sampling Method for Global Optimization of High Dimensional Design Problems , 2015 .

[32]  Salvador Pintos,et al.  An Optimization Methodology of Alkaline-Surfactant-Polymer Flooding Processes Using Field Scale Numerical Simulation and Multiple Surrogates , 2005 .

[33]  N. Cressie.  The origins of kriging , 1990 .

[34]  C. D. Perttunen,et al.  Lipschitzian optimization without the Lipschitz constant , 1993 .

[35]  W. Cleveland,et al.  Locally Weighted Regression: An Approach to Regression Analysis by Local Fitting , 1988 .

[36]  T. Simpson,et al.  Computationally Inexpensive Metamodel Assessment Strategies , 2002 .

[37]  H. Rabitz,et al.  General foundations of high‐dimensional model representations , 1999 .

[38]  Rommel G. Regis,et al.  An Initialization Strategy for High-Dimensional Surrogate-Based Expensive Black-Box Optimization , 2013 .