Research on Aerodynamic Optimization of Aircraft Engine Nacelle Based on Multi-Precision Deep Learning (MFDNN)

Che Chen

doi:10.54097/q4hfj028

Authors

Che Chen

DOI:

https://doi.org/10.54097/q4hfj028

Keywords:

Multi-Fidelity Modeling; Aerodynamic Optimization; Aircraft Engine Nacelle; Deep Neural Network; CFD.

Abstract

The design of an aircraft engine nacelle directly affects aircraft drag, fuel consumption, and noise levels, and is a key step in aerodynamic shape optimization. Traditional optimization design methods based on computational fluid dynamics (CFD) rely heavily on high-precision simulation data. However, high-precision CFD calculations are expensive and time-consuming, severely limiting the exploration of the design space and the efficiency of optimization. With the development of artificial intelligence (AI), optimization methods based on surrogate models have become a research hotspot. However, existing methods often rely on data of a single precision and are unable to effectively utilize abundant and easily accessible low-precision data resources. This study aims to introduce a multi-fidelity deep learning (MFDNN) method for the aerodynamic optimization of aircraft engine nacelles. By fusing CFD data of different precisions, a high-precision and efficient aerodynamic performance prediction model is constructed. This method significantly reduces the number of expensive CFD calculations while maintaining optimization accuracy, providing a new technical approach for the rapid and efficient design of aircraft engines.

Downloads

Download data is not yet available.

References

[1] CICTT (General Aviation Accident and Incident Classification Team). Statistics of air accident.

[2] Oceanic operations an authoritative guide to oceanic operations. (1994). U.S. Dept. of Transportation, Federal Aviation Administration, FAA Flight Standards Service.

[3] Slotnick, J., Langley Research Center, issuing body, & United States. National Aeronautics and Space Administration, sponsoring body. (2014). CFD vision 2030 study: a path to revolutionary computational aerosciences. National Aeronautics and Space Administration, Langley Research Center.

[4] Li, J., Gao, Z., Huang, J., & Zhao, K. (2013). Aerodynamic design optimization of nacelle/pylon position on an aircraft. Chinese Journal of Aeronautics, 26(4), 850–857.

[5] NASA. Inlet Design.

[6] Haines, A. B. (2000). [Rev. of Intake Aerodynamics — Second edition. J. Seddon and E.L. Goldsmith. Blackwell Science, Osney Mead, Oxford OX2 0EL, UK. 1999. 1407pp. Illustrated. £59.50. ISBN 0-632-04963-4]. Aeronautical Journal, 104(1032), 96–96.

[7] NASA. Inlet Design.

[8] Slotnick, J., Khodadoust, A., Alonso, J., Darmofal, D., Gropp, W., Lurie, E., & Mavriplis, D. (2014). CFD Vision 2030 Study: A Path to Revolutionary Computational Aerosciences. In NASA Center for AeroSpace Information (CASI). Reports. NASA/Langley Research Center.

[9] Mani, M., Rider, B., & Lunk, M. (2013). Nacelle design and analysis for an N3-X hybrid wing body configuration. In 31st AIAA Applied Aerodynamics Conference. American Institute of Aeronautics and Astronautics.

[10] Zhang, Y., Chen, H., Fu, S., Zhang, M., & Zhang, M. (2015). Drag prediction method of powered-on civil aircraft based on thrust drag bookkeeping. Chinese Journal of Aeronautics, 28(4), 1023–1033.

[11] Ferziger, J. H. (2019). Computational Methods for Fluid Dynamics (R. L. Street & M. Perić, Eds.; Fourth edition.). Springer Nature.

[12] Tuo, R., & Wu, C. F. J. (2018). PREDICTION BASED ON THE KENNEDY-O’HAGAN CALIBRATION MODEL: ASYMPTOTIC CONSISTENCY AND OTHER PROPERTIES. Statistica Sinica, 28(2), 743–759.

[13] Baining CHEN, Fangfang XIE, & Xuhui MENG. (2024). Adaptive Multi-Fidelity Composite Deep Neural Networks. PHYSICS OF GASES, 9(4), 1–8.