The Optimization and Application of Kriging Model Based on Quantum-Behaved Particle Swarm Optimization

Abstract:

Inspired by the facts that the original Kriging model is sensitive to the initial value of its correlation model parameters and extremely easy to fall into local optimal solution, a method on Kriging correlation model optimization based on quantum-behaved particle swarm optimization (QPSO) algorithm is proposed.The QPSO algorithm is introduced to search the global optimal solution to the parameters of the Kriging correlation model, and overcome the dependence on initial values of the pattern search method. After that, the optimized Kriging model based on QPSO is applied to the establishment of surrogate model and reconstruction of flow characteristics of a low pressure compressor. It is proved that even with small sample data, surrogate model of the flow characteristics based on QPSO still has a high accuracy, and its application prospect is considerable.

• Periodical: Applied Mechanics and Materials (Volumes 599-601)
• Pages: 1772-1776
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.599-601.1772
• Online since: August 2014
• Authors: Yong Zhao*, Ben Wei Li, Yun Zhang, Ying Fu Chen
• Keywords: Compressor Characteristics, Correlation Model, Kriging, QPSO, Surrogate Model

References

[1] J. Zhang, S. Chowdhury and J.Q. Zhang, et al.: Adaptive hybird surrogate modeling for complex systems. AIAA Journal. Vol. 51-3(2013), pp.643-656.

DOI: 10.2514/1.j052008

[2] X.F. Mu, W.X. Yao and X.Q. Yu, et al.: A survey of surrogate models used in MDO. Chinese Journal of Computational Mechanics. Vol. 22-5(2005), pp.608-612.

[3] Y.H. Yu , L.G. Chen and F.R. Sun, et al.: Neural-network based analysis and prediction of a compressor's characteristic performance map. Applied Energy. Vol. 84(2007), pp.48-55.

DOI: 10.1016/j.apenergy.2006.04.005

[4] J. Zhang, S. Chowdhury and A. Messac: An adaptive hybird surrogate model. Struct Multidisc Optim. Vol. 46 (2012), pp.223-238.

DOI: 10.1007/s00158-012-0764-x

[5] A.I.J. Forrester, A.J. Keane: Recent advances in surrogated-based optimization. Progress in Aerospace Sciences. Vol. 45(2009), pp.50-79.

DOI: 10.1016/j.paerosci.2008.11.001

[6] Z.Y. Chen,Y. Ren and G.C. Bai, et al.: Particle swarm optimized Kriging approximate model and its application to reliability analysis. Journal of Aerospace Power. Vol. 26-7(2011), pp.1522-1530.

[7] M.J. Sun, H. Zhan: Synthesis airfoil optimizaiton by particle swarm optimizaiton based on global information. Acta Aeronautica et Astronautica Sinica. Vol. 31-11(2010), pp.2166-2173.

[8] M.J. Sun, H. Zhan: Application of Kriging surrogate model for aerodynamic shape optimization of wing. Acta Aerodynamic Sinica. Vol. 29-6(2011), pp.759-764.

[9] D.W. Yin, B.W. Li and Y.H. Wang, et al.: Aeroengine compressor charateristics metamodeling using Kriging method. Acta Aeronautica et Astronautica Sinica. Vol. 32-1(2011), pp.99-106.

[10] H.L. You, X.Z. Jia: The construction and optimizaiton of Kriging metamodel based on genetic algorithms. Journal of computer-aided design &computer graphics. Vol. 19-1(2007), pp.64-68.

[11] P. Chen,J. Li and T. Guan: The optimizaiton of parameters of Kriging correlation model based on patitical swarm optimizaiton. Microelectronics & computer. Vol. 26-4(2009), pp.178-185.

[12] S.N. Lophaven H.B. Nielsen and J. Sondergaard: DACE: a MATLAB kriging toolbox. IMM-TR-2002-12, pp.1-26.

[13] J. Sun: Particle swarm optimization with particles having quantum behavior. PhD thesis of Jiang Nan University, Wuxi (2009).

[14] J. Sun, B. Feng, W.B. Xu: Particle swarm optimization with particles having quantum behavior. Proc of the IEEE Congress on Evolutionary Computation, Portland(2004), pp.325-331.

DOI: 10.1109/cec.2004.1330875