1
Return

A novel multi-fidelity Kriging modeling method with deep shared latent mapping

delete2026-07-31
delete0
PRE
AI
Z
Zongrui Tian
C
Chen Wang
W
Wanxin He
G
Gang Li *
DOI：10.1016/j.knosys.2026.116709delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• A deep shared latent map Kriging model is proposed for multi-fidelity modeling. • Deep latent spaces are used to characterize nonlinear fidelity relationships. • A layer-wise likelihood strategy is designed for stable parameter estimation. • Numerical and engineering tests confirm accuracy, robustness, and generalization.
Keywords:
Multi-fidelity model
Latent map
Non-hierarchical data
Data fusion
Motor hanger

Journal

K
Knowledge-Based Systems
IF:
7.6
Papers:
1.2W
Citations:
4.5W

Organization

D
Dalian University of Technology
Scholars:
5.7W
Papers: 4.3W
Citations: 5.5W
Cited Papers

Cited Papers

Citing Papers

Citing Papers