×

Kernel parameter optimization for kriging based on structural risk minimization principle. (English) Zbl 1426.62105

Summary: An improved kernel parameter optimization method based on Structural Risk Minimization (SRM) principle is proposed to enhance the generalization ability of traditional Kriging surrogate model. This article first analyses the importance of the generalization ability as an assessment criteria of surrogate model from the perspective of statistics and proves the applicability to Kriging. Kernel parameter optimization method is used to improve the fitting precision of Kriging model. With the smoothness measure of the generalization ability and the anisotropy kernel function, the modified Kriging surrogate model and its analysis process are established. Several benchmarks are tested to verify the effectiveness of the modified method under two different sampling states: uniform distribution and nonuniform distribution. The results show that the proposed Kriging has better generalization ability and adaptability, especially for nonuniform distribution sampling.

MSC:

62G05 Nonparametric estimation
68T05 Learning and adaptive systems in artificial intelligence
90C31 Sensitivity, stability, parametric optimization

Software:

DACE
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Ma, M.; Wang, C.; ZHang, J.; Huang, Z., Multidisciplinary Design Optimization for Complex Product Review, Chinese Journal of Mechanical Engineering, 44, 06, 15-26, (2008) · doi:10.3901/JME.2008.06.015
[2] de Weck, O.; Agte, J.; Sobieszczanski-Sobieski, J.; Arendsen, P.; Morris, A.; Spieck, M., State-of-the-Art and Future Trends in Multidisciplinary Design Optimization, Proceedings of the 48th AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics, and Materials Conference · doi:10.2514/6.2007-1905
[3] Ullman, D. G., Toward the ideal mechanical engineering design support system, Research in Engineering Design, 13, 2, 55-64, (2002) · doi:10.1007/s00163-001-0007-4
[4] Vapnik, V. N., Statistical Learning Theory, (1998), Wiley · Zbl 0935.62007
[5] Vapnik, V. N., The Nature of Statistical Learning Theory, (1995), New York, NY, USA: Springer, New York, NY, USA · Zbl 0833.62008 · doi:10.1007/978-1-4757-2440-0
[6] Van Beers, W. C. M., Kriging metamodeling in discrete-event simulation: An overview, Proceedings of the 2005 Winter Simulation Conference · doi:10.1109/WSC.2005.1574252
[7] Simpson, T. W.; Mauery, T. M.; Korte, J. J.; Mistree, F., Kriging models for global approximation in simulation-based multidisciplinary design optimization, AIAA Journal, 39, 12, 2233-2241, (2001) · doi:10.2514/2.1234
[8] Cressie, N., Spatial prediction and ordinary kriging, Mathematical Geology, 21, 4, 493-494, (1989) · doi:10.1007/BF00897332
[9] Kleijnen, J. P., Kriging metamodeling in simulation: a review, European Journal of Operational Research, 192, 3, 707-716, (2009) · Zbl 1157.90544 · doi:10.1016/j.ejor.2007.10.013
[10] Jeong, S.; Murayama, M.; Yamamoto, K., Efficient optimization design method using kriging model, Journal of Aircraft, 42, 2, 413-420, (2005) · doi:10.2514/1.6386
[11] Kleijnen, J. P., Simulation-optimization via Kriging and bootstrapping: a survey, Journal of Simulation, 8, 4, 241-250, (2014) · doi:10.1057/jos.2014.4
[12] Chen, Z.; Qiu, H.; Gao, L.; Li, X.; Li, P., A local adaptive sampling method for reliability-based design optimization using Kriging model, Structural and Multidisciplinary Optimization, 49, 3, 401-416, (2014) · doi:10.1007/s00158-013-0988-4
[13] Ulaganathan, S.; Couckuyt, I.; Dhaene, T.; Degroote, J.; Laermans, E., Performance study of gradient-enhanced Kriging, Engineering with Computers, 32, 1, 15-34, (2016) · doi:10.1007/s00366-015-0397-y
[14] Goovaerts, P., Ordinary Cokriging Revisited, Mathematical Geology, 30, 1, 21-40, (1998) · doi:10.1023/A:1021757104135
[15] Han, Z.-H.; Görtz, S., Hierarchical kriging model for variable-fidelity surrogate modeling, AIAA Journal, 50, 9, 1885-1896, (2012) · doi:10.2514/1.J051354
[16] Xiao, J.; Yu, L.; Bai, Y. F., Survey of the Selection of Kernels and Hyper-parameters in Support Vector Regression, Journal of Southwest Jiaotong University, 43, 3, 297-303, (2008) · Zbl 1199.68243
[17] Liu, X.; Zhou, S.; Xiong, Z.; Chen, L.; Yan, C., Research on Identifying TS Fuzzy Model Based on Structural Risk Minimization, Journal of Guizhou University, (2016)
[18] Berestin, D.; Zimin, M.; Gavrilenko, T.; Chernikov, N., Determination of an object as chaotic system on the basis of structural risk minimization, Complexity. Mind. Postnonclassic, 3, 4, 73-87, (2014) · doi:10.12737/7654
[19] Zhu, X.; Luo, W.; Wei, Y.; Chen, X., Structural Risk Minimization Based Radial Basis Function Surrogate Mode, Journal of Projectiles, Rockets, Missile and Guidance, 31, 5, 169-173, (2011)
[20] Wei, C.; Qian, L. I.; Wei, T., Radial Basis Function Networks Based on Structural Risk Minimization Principle, Control and Instruments in Chemical Industry, 36, 3, 34-37, (2009)
[21] Alexander, I. J. F.; Andras, S.; Andy, J. K., Engineering Design via Surrogate Modelling, (2008), Wiley
[22] Zhu, X. F., Surrogate Model Theory and Application in the Aircraft MDO, (2010), National University of Defense Technology
[23] Lophaven, S. N.; Nielsen, H. B.; Søndergaard, J., DACE A MATLAB Kriging Toolbox, (2002), Technical University of Denmark
[24] Xiong, Z. C., Some Problems in Approximation Theory with Radial Basis Function, (2007), Fudan University
[25] Glaz, B., Active/passive optimization of helicopter rotor blades for improved vibration, noise, and performance characteristics, (2008), University of Michigan
[26] Zhang, D.; Gao, Z.; Li, J.; Huang, L., Study of Metamodel Sampling Criterion, Acta Aerodynamica Sinica, 29, 6, 719-725, (2011)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.