EUVIMEDEUVIMED entdecken
Crossref

Data-Driven Propeller Noise Prediction Approach with Transfer and Active Learning

Beckett Y. Zhou, Liam Hanson, Shaun F. Pullin, Bin Zang, Jeremiah Hauth, Xun Huan

AIAA Journal · 2025-12 · 63 (12) · 5393-5404

DOI: 10.2514/1.j065406 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AIAA Journal, 2025-12. Verfasst von Beckett Y. Zhou und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 29 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate and efficient prediction of propeller acoustic performance is of paramount importance to the analysis and design of various urban air mobility concepts that have emerged over the last decade. Leveraging modern machine learning techniques of transfer learning (TL) and active learning (AL), we present a multifidelity data-driven framework that uses a combination of simulation and experiment data to train a neural network (NN) model for predicting the tonal noise of two-bladed propellers at multiple far-field observer locations given the airfoil profile, pitch-to-diameter ratio, forward speed, and rotational speed of the propeller. The NN model is first trained using a large number of inexpensive low-fidelity simulations and then enhanced by a small number of high-fidelity aeroacoustic wind tunnel measurements using TL. Two additional rounds of wind-tunnel experiments with new propeller designs are then suggested by an AL algorithm designed to effectively reduce the predictive error of the NN model. Results from held-out validation indicate that the NN trained with both low- and high-fidelity data based on TL delivers better performance than those trained solely with low- or high-fidelity data, and the inclusion of high-fidelity data selected by AL further improves the predictive accuracy.

Zitieren

APA

Zhou, B. Y., Hanson, L., Pullin, S. F., Zang, B., Hauth, J., & Huan, X. (2025). Data-Driven Propeller Noise Prediction Approach with Transfer and Active Learning. AIAA Journal, 63(12), 5393-5404. https://doi.org/10.2514/1.j065406

Vancouver

Zhou BY, Hanson L, Pullin SF, Zang B, Hauth J, Huan X. Data-Driven Propeller Noise Prediction Approach with Transfer and Active Learning. AIAA Journal. 2025;63(12):5393-5404. doi:10.2514/1.j065406

BibTeX
@article{Zhou2025,
  author = {Zhou, Beckett Y. and Hanson, Liam and Pullin, Shaun F. and Zang, Bin and Hauth, Jeremiah and Huan, Xun},
  title = {Data-Driven Propeller Noise Prediction Approach with Transfer and Active Learning},
  journal = {AIAA Journal},
  year = {2025},
  volume = {63},
  number = {12},
  pages = {5393--5404},
  doi = {10.2514/1.j065406}
}
Kostenlos starten →