Stochastic kriging for random simulation metamodeling with known uncertainty

Bo Wang, Haechang Gea, Junqiang Bai, Yudong Zhang, Jian Gong, Weimin Zhang

Research output: Contribution to journalArticlepeer-review

1 Scopus citations


Uncertainty-based design has been widely carried out these years. In order to deal with the problems with large amount of calculation, a stochastic kriging for random simulation metamodeling with known uncertainty was derived, which firstly included intrinsic uncertainty in metamodel initial formulation to fully account for inputs uncertainty, and then incorporated the correlationships of intrinsic uncertainty among all observed points. Several examples with known uncertainty were also conducted, in which the proposed method shows much better variance predictions than other similar methods. Simulation results show the proposed method is a more general form of kriging, which can also widely deal with the uncertainty-based problems with heterogeneous variances as a stochastic metamodel.

Original languageEnglish (US)
Pages (from-to)1261-1272
Number of pages12
JournalXitong Fangzhen Xuebao / Journal of System Simulation
Issue number6
StatePublished - Jun 8 2016

All Science Journal Classification (ASJC) codes

  • Modeling and Simulation
  • Aerospace Engineering
  • Computer Science Applications


  • Kriging method
  • Metamodeling
  • Stochastic problems
  • Uncertainty estimation


Dive into the research topics of 'Stochastic kriging for random simulation metamodeling with known uncertainty'. Together they form a unique fingerprint.

Cite this