High dimensional Kriging metamodelling utilising gradient information

被引:28
|
作者
Ulaganathan, S. [1 ]
Couckuyt, I. [1 ]
Dhaene, T. [1 ]
Degroote, J. [2 ]
Laermans, E. [1 ]
机构
[1] Ghent Univ iMINDS, Dept Informat Technol INTEC, Gaston Crommenlaan 8, B-9050 Ghent, Belgium
[2] Univ Ghent, Dept Flow, Heat & Combust Mech, Sint Pietersnieuwstr 41, B-9000 Ghent, Belgium
关键词
Metamodelling; Kriging; Gradient enhancement; LOLA-Voronoi; HDMR; FSI; REPRESENTATION RS-HDMR; MODEL REPRESENTATION; DESIGN; SIMULATION; TOOLBOX; OUTPUT;
D O I
10.1016/j.apm.2015.12.033
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Kriging-based metamodels are popular for approximating computationally expensive black box simulations, but suffer from an exponential growth of required training samples as the dimensionality of the problem increases. While a Gradient Enhanced Kriging meta model with less training samples is able to approximate more accurately than a Kriging-based metamodel, it is prohibitively expensive to build for high dimensional problems. This limits the applicability of Gradient Enhanced Kriging for high dimensional meta-modelling. In this work, this limitation is alleviated by coupling Gradient Enhanced Kriging with High Dimensional Model Representation. The approach, known as Gradient Enhanced Kriging based High Dimensional Model Representation, is accompanied by a highly efficient sequential sampling scheme LOLA-Voronoi and is applied to various high dimensional benchmark functions and one real-life simulation problem of varying dimensionality (10D-100D). Test results show that the combination of inexpensive gradient information and the high dimensional model representation can break or at least loosen the limitations associated with high dimensional Kriging metamodelling. (C) 2015 Elsevier Inc. All rights reserved.
引用
收藏
页码:5256 / 5270
页数:15
相关论文
共 50 条
  • [21] Faster Kriging: Facing High-Dimensional Simulators
    Lu, Xuefei
    Rudi, Alessandro
    Borgonovo, Emanuele
    Rosasco, Lorenzo
    OPERATIONS RESEARCH, 2020, 68 (01) : 233 - 249
  • [22] Approach for designing and modelling of nanoscale DG MOSFET devices using Kriging metamodelling technique
    Bentrcia, Toufik
    Djeffal, Faycal
    Chebaki, Elasaad
    IET CIRCUITS DEVICES & SYSTEMS, 2017, 11 (06) : 618 - 623
  • [23] Gradient Extrapolated Stochastic Kriging
    Qu, Huashuai
    Fu, Michael C.
    ACM TRANSACTIONS ON MODELING AND COMPUTER SIMULATION, 2014, 24 (04):
  • [24] An efficient gradient-enhanced kriging modeling method assisted by fast kriging for high-dimension problems
    He, Youwei
    Tan, Kuan
    Fu, Chunming
    Luo, Jinliang
    INTERNATIONAL JOURNAL OF NUMERICAL METHODS FOR HEAT & FLUID FLOW, 2023, 33 (12) : 3967 - 3993
  • [25] Incorporating gradient information into dimension perturbation mutation for high-dimensional expensive optimization
    Yang, Zan
    Chu, Sheng
    Liu, Jiansheng
    Qiu, Haobo
    Xiao, Mi
    Gao, Liang
    SWARM AND EVOLUTIONARY COMPUTATION, 2024, 84
  • [26] High-dimensional Bayesian optimization with a combination of Kriging models
    Appriou, Tanguy
    Rulliere, Didier
    Gaudrie, David
    STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION, 2024, 67 (11)
  • [27] ProMISE: A Process Metamodelling Method for Information Systems Engineering
    Hug, Charlotte
    Front, Agnes
    Rieu, Dominique
    EVALUATION OF NOVEL APPROACHES TO SOFTWARE ENGINEERING, 2011, 230 : 89 - +
  • [28] Metamodelling techniques in dimensional optimality analysis for linear programming
    Johnson, KE
    Bauer, KW
    Moore, JT
    Grant, M
    MATHEMATICAL AND COMPUTER MODELLING, 1996, 23 (05) : 45 - 60
  • [29] An enhanced Kriging surrogate modeling technique for high-dimensional problems
    Zhou, Yicheng
    Lu, Zhenzhou
    MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2020, 140
  • [30] Kriging-based multi-objective optimization on high-speed train aerodynamics using sequential infill criterion with gradient information
    Dai, Zhiyuan
    Li, Tian
    Krajnovic, Sinisa
    Zhang, Weihua
    PHYSICS OF FLUIDS, 2024, 36 (03)