Local update of support vector machine decision boundaries

This paper presents a new adaptive sampling technique for the construction of locally reflned explicit decision functions. The decision functions can be used for both deterministic and probabilistic optimization, and may represent a constraint or a limit-state function. In particular, the focus of this paper is on reliability-based design optimization (RBDO). Instead of approximating the responses, the method is based on explicit design space decomposition (EDSD), in which an explicit boundary separating distinct regions in the design space is constructed. A statistical learning tool known as support vector machine (SVM) is used to construct the boundaries. A major advantage of using an EDSD-based method lies in its ability to handle discontinuous responses. A separate adaptive sampling scheme for calculating the probability of failure is also developed, which is used within the RBDO process. The update methodology is validated through several test examples with analytical decision functions.

[1]  Bruno Sudret,et al.  Handling Bifurcations in the Optimal Design of Transient Dynamic Problems , 2004 .

[2]  Achintya Haldar,et al.  Probability, Reliability and Statistical Methods in Engineering Design (Haldar, Mahadevan) , 1999 .

[3]  B. Youn,et al.  Adaptive probability analysis using an enhanced hybrid mean value method , 2005 .

[4]  Nikolaos V. Sahinidis,et al.  Global optimization of mixed-integer nonlinear programs: A theoretical and computational study , 2004, Math. Program..

[5]  Kyung K. Choi,et al.  Reliability-based design optimization for crashworthiness of vehicle side impact , 2004 .

[6]  Kyung K. Choi,et al.  Selecting probabilistic approaches for reliability-based design optimization , 2004 .

[7]  Vicente J. Romero,et al.  Comparison of pure and "Latinized" centroidal Voronoi tessellation against various other statistical sampling methods , 2006, Reliab. Eng. Syst. Saf..

[8]  Rohan Shiloh Shah,et al.  Support Vector Machines for Classiflcation and Regression , 2007 .

[9]  Liqun Wang,et al.  Reliability Assessment Using Discriminative Sampling and Metamodeling , 2005 .

[10]  A. Basudhar,et al.  Adaptive explicit decision functions for probabilistic design and optimization using support vector machines , 2008 .

[11]  M. Eldred,et al.  Multimodal Reliability Assessment for Complex Engineering Applications using Efficient Global Optimization , 2007 .

[12]  R. A. Miller,et al.  Sequential kriging optimization using multiple-fidelity evaluations , 2006 .

[13]  S. Gunn.  Support Vector Machines for Classification and Regression , 1998 .

[14]  Jorge E. Hurtado,et al.  An examination of methods for approximating implicit limit state functions from the viewpoint of statistical learning theory , 2004 .

[15]  Robert E. Melchers,et al.  Structural Reliability: Analysis and Prediction , 1987 .

[16]  Antonio Harrison Sánchez,et al.  Limit state function identification using Support Vector Machines for discontinuous responses and disjoint failure domains , 2008 .

[17]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[18]  Michael S. Eldred,et al.  OVERVIEW OF MODERN DESIGN OF EXPERIMENTS METHODS FOR COMPUTATIONAL SIMULATIONS , 2003 .

[19]  Nello Cristianini,et al.  Kernel Methods for Pattern Analysis , 2003, ICTAI.

[20]  Raphael T. Haftka,et al.  A convex hull approach for the reliability-based design optimization of nonlinear transient dynamic problems , 2007 .

[21]  Julius T. Tou,et al.  Pattern Recognition Principles , 1974 .

[22]  G. Kharmanda,et al.  Efficient reliability-based design optimization using a hybrid space with application to finite element analysis , 2002 .

[23]  J. A. Hartigan,et al.  A k-means clustering algorithm , 1979 .

[24]  R. H. Myers,et al.  Response Surface Methodology: Process and Product Optimization Using Designed Experiments , 1995 .

[25]  G. Gary Wang,et al.  Review of Metamodeling Techniques in Support of Engineering Design Optimization , 2007 .