EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Conditioned Hybrid Transformer Surrogate for Propeller Surface Flow Field Prediction

Xiangjie Yao, Xu Chen, Fangwen Hong

Journal of Marine Science and Engineering · 10.11.2026 · 14 (22) · 2132

DOI: 10.3390/jmse14222132 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Marine Science and Engineering, online erschienen am 10.11.2026. Verfasst von Xiangjie Yao und 2 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: development and application project of ship CAE software.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study develops a conditioned hybrid transformer surrogate to rapidly predict the surface flow fields of marine propellers. The model adopts a CNN-transformer-CNN backbone with a four-layer transformer bottleneck. The CNN encoder and decoder are uniformly conditioned via adaptive instance normalization (AdaIN), and three conditioning paradigms—token-prepend, adaptive layer normalization with zero-initialized gating (AdaLN-Zero), and cross-attention—are systematically compared within the transformer bottleneck. The discrete blade number and the continuous advance coefficient are jointly embedded as conditioning inputs. Model training and evaluation are conducted on a dataset of 2710 operating cases covering 560 propeller samples with three-, four-, and five-bladed configurations. The three conditioning paradigms achieve comparable accuracy, with the AdaLN-Zero scheme yielding the lowest validation loss; ablation results indicate that the CNN-level AdaIN conditioning, rather than the bottleneck paradigm, dominates the conditioning effect. On the test set, the proposed model achieves relative errors within 10% for flow field distributions and mean absolute percentage errors within 3.1% for the derived thrust and torque coefficients. The minimum pressure coefficient and the low-pressure region are also accurately captured. The proposed model achieves a speedup of two to three orders of magnitude over CFD simulations, and thus serves as a promising tool for fast hydrodynamic assessment in propeller optimization iterations.

Förderung

  • development and application project of ship CAE software

Zitieren

APA

Yao, X., Chen, X., & Hong, F. (2026). A Conditioned Hybrid Transformer Surrogate for Propeller Surface Flow Field Prediction. Journal of Marine Science and Engineering, 14(22), 2132. https://doi.org/10.3390/jmse14222132

Vancouver

Yao X, Chen X, Hong F. A Conditioned Hybrid Transformer Surrogate for Propeller Surface Flow Field Prediction. Journal of Marine Science and Engineering. 2026;14(22):2132. doi:10.3390/jmse14222132

BibTeX
@article{Yao2026,
  author = {Yao, Xiangjie and Chen, Xu and Hong, Fangwen},
  title = {A Conditioned Hybrid Transformer Surrogate for Propeller Surface Flow Field Prediction},
  journal = {Journal of Marine Science and Engineering},
  year = {2026},
  volume = {14},
  number = {22},
  pages = {2132},
  doi = {10.3390/jmse14222132}
}
Kostenlos starten →