Updating Kriging Surrogate Models Based on the Hypervolume Indicator in Multi-Objective Optimization

被引:32
作者
Shimoyama, Koji [1 ]
Sato, Koma [2 ]
Jeong, Shinkyu [3 ]
Obayashi, Shigeru [1 ]
机构
[1] Tohoku Univ, Inst Fluid Sci, Sendai, Miyagi 9808577, Japan
[2] Hitachi Ltd, Hitachi Res Lab, Hitachinaka, Ibaraki 3120034, Japan
[3] Kyung Hee Univ, Dept Mech Engn, Yongin 446701, South Korea
关键词
DESIGN;
D O I
10.1115/1.4024849
中图分类号
TH [机械、仪表工业];
学科分类号
0802 ;
摘要
This paper presents a comparison of the criteria for updating the Kriging surrogate models in multi-objective optimization: expected improvement (EI), expected hypervolume improvement (EHVI), estimation (EST), and those in combination (EHVI+EST). EI has been conventionally used as the criterion considering the stochastic improvement of each objective function value individually, while EHVI has recently been proposed as the criterion considering the stochastic improvement of the front of nondominated solutions in multi-objective optimization. EST is the value of each objective function estimated nonstochastically by the Kriging model without considering its uncertainties. Numerical experiments were implemented in the welded beam design problem, and empirically showed that, in an unconstrained case, EHVI maintains a balance between accuracy, spread, and uniformity in nondominated solutions for Kriging-model-based multiobjective optimization. In addition, the present experiments suggested future investigation into techniques for handling constraints with uncertainties to enhance the capability of EHVI in constrained cases.
引用
收藏
页数:7
相关论文
共 24 条
  • [1] [Anonymous], THESIS MIT CAMBRIDGE
  • [2] [Anonymous], P 42 FLUID DYN C AER
  • [3] [Anonymous], 2008, J. Fluid Sci. Technol., DOI DOI 10.1299/JFST.3.576
  • [4] [Anonymous], 1999, Evolutionary Algorithms for Multiobjective Optimization: Methods and Applications
  • [5] [Anonymous], 1998, DEP ELECT COMPUT ENG
  • [6] [Anonymous], 2012, 2012 IEEE C EVOLUTIO
  • [7] On the Complexity of Computing the Hypervolume Indicator
    Beume, Nicola
    Fonseca, Carlos M.
    Lopez-Ibanez, Manuel
    Paquete, Luis
    Vahrenhold, Jan
    [J]. IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, 2009, 13 (05) : 1075 - 1082
  • [8] Bishop CM., 1995, NEURAL NETWORKS PATT
  • [9] Emmerich MTM, 2011, IEEE C EVOL COMPUTAT, P2147
  • [10] Reducible Uncertain Interval Design by Kriging Metamodel Assisted Multi-Objective Optimization
    Hamel, Joshua M.
    Azarm, Shapour
    [J]. JOURNAL OF MECHANICAL DESIGN, 2011, 133 (01)