Spatial Aerodynamic Parameters Prediction for Wide-Incidence Turbines Using Small-Scale Experimental Data-Driven Graph Neural Networks
Journal of Turbomachinery · 01.09.2026 · 148 (9)
DOI: 10.1115/1.4072201 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Turbomachinery, online erschienen am 10.07.2026. Verfasst von Tianyou Chen und 4 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben.
Abstract (Originalsprache)
Accurate performance prediction across a wide operating range remains challenging for high-performance power turbine blades. To address this issue, a graph-attention network model, GAT-5s, was developed using small-scale experimental data to predict aerodynamic parameters of rotor blade profiles over a wide-incidence range. On the validation profile, GAT-5s achieved mean relative errors (MREs) of 1.6% for the total pressure loss coefficient, 0.2% for the outlet Mach number, and 2.7% for the deviation angle. These errors were lower than those of the back-propagation neural network baseline and the GAT-5s-CFD model trained on RANS under the same tested conditions. However, direct use of GAT-5s for surface pressure prediction produced training and testing losses above 1 × 10−3, indicating limited capability to describe spatial pressure distributions. To address this limitation, GAT-5G was developed by integrating pressure-point position information and a bidirectional gated recurrent unit (BIGRU) module into GAT-5s. The model reduced the training and testing MSE losses to below 1.0 × 10−4, and the prediction errors for both the test and validation profiles remained within 10%. Although GAT-5G did not always yield the minimum local error among all models, it provided balanced agreement with experimental pressure distributions across the tested incidence range. For wake-loss prediction on the validation profile, the MRE also remained below 10% for the tested incidence cases. These results indicate that GAT can serve as useful surrogate models for aerodynamic prediction of wide-incidence rotor blade profiles.
Zitieren
APA
Chen, T., Hu, X., Cai, L., Wang, J., & Wang, S. (2026). Spatial Aerodynamic Parameters Prediction for Wide-Incidence Turbines Using Small-Scale Experimental Data-Driven Graph Neural Networks. Journal of Turbomachinery, 148(9). https://doi.org/10.1115/1.4072201
Vancouver
Chen T, Hu X, Cai L, Wang J, Wang S. Spatial Aerodynamic Parameters Prediction for Wide-Incidence Turbines Using Small-Scale Experimental Data-Driven Graph Neural Networks. Journal of Turbomachinery. 2026;148(9). doi:10.1115/1.4072201
BibTeX
@article{Chen2026,
author = {Chen, Tianyou and Hu, Xinlei and Cai, Le and Wang, Jiahui and Wang, Songtao},
title = {Spatial Aerodynamic Parameters Prediction for Wide-Incidence Turbines Using Small-Scale Experimental Data-Driven Graph Neural Networks},
journal = {Journal of Turbomachinery},
year = {2026},
volume = {148},
number = {9},
doi = {10.1115/1.4072201}
}
EUVIMED