Hierarchical Clustering Weighted Gaussian Process Regression Low-Fidelity Model and Application in Airfoil Drag Coefficients Prediction
IEEE Transactions on Aerospace and Electronic Systems · 2026 · 62 · 9070-9081
DOI: 10.1109/taes.2026.3678593 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Aerospace and Electronic Systems, 2026. Verfasst von Lichao Jiang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 55 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Heilongjiang Province of China, HEU CISSE Decanal Innovation Fund for Ph.D. Students.
Abstract (Originalsprache)
Multifidelity (MF) modeling is a common approach for predicting the drag coefficient of airfoil, offering high accuracy and low computational cost. Low-fidelity (LF) data are acquired by simplifying high-fidelity models. However, existing MF modeling techniques fail to consider the relative importance of different LF samples and treat them uniformly, which reduces the accuracy of MF models. To effectively utilize different LF samples, this article proposes a hierarchical clustering weighted Gaussian process regression (HCWGPR) LF model and applies it to the MF modeling of the airfoil drag coefficient. First, principal component analysis is used to extract the key information of LF samples. Then, empirical mode decomposition is employed to decompose the key information into high-frequency energy fluctuations and low-frequency feature vectors. Next, a hierarchical clustering weight calculation algorithm based on high-frequency energy differences and low-frequency feature similarity is proposed to assign weights to LF samples. Finally, a weighted Gaussian process regression (GPR) framework is used to construct the HCWGPR. A GPR is also adopted as a discrepancy model. The effectiveness of the proposed method is verified by nine sets of analytical test cases and the drag coefficient prediction of six airfoils.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Heilongjiang Province of China
- HEU CISSE Decanal Innovation Fund for Ph.D. Students
Zitieren
APA
Jiang, L., Fang, H., Shang, X., & Zhang, Z. (2026). Hierarchical Clustering Weighted Gaussian Process Regression Low-Fidelity Model and Application in Airfoil Drag Coefficients Prediction. IEEE Transactions on Aerospace and Electronic Systems, 62, 9070-9081. https://doi.org/10.1109/taes.2026.3678593
Vancouver
Jiang L, Fang H, Shang X, Zhang Z. Hierarchical Clustering Weighted Gaussian Process Regression Low-Fidelity Model and Application in Airfoil Drag Coefficients Prediction. IEEE Transactions on Aerospace and Electronic Systems. 2026;62:9070-9081. doi:10.1109/taes.2026.3678593
BibTeX
@article{Jiang2026,
author = {Jiang, Lichao and Fang, Hai and Shang, Xiaobing and Zhang, Zhi},
title = {Hierarchical Clustering Weighted Gaussian Process Regression Low-Fidelity Model and Application in Airfoil Drag Coefficients Prediction},
journal = {IEEE Transactions on Aerospace and Electronic Systems},
year = {2026},
volume = {62},
pages = {9070--9081},
doi = {10.1109/taes.2026.3678593}
}
EUVIMED