Abstract
In this study, a method for predicting unsteady aerodynamic forces under different initial conditions using a limited number of samples based on transfer learning is proposed, aiming to avoid the need for large-scale high-fidelity aerodynamic simulations. First, a large number of training samples are acquired through high-fidelity simulation under the initial condition for the baseline, followed by the establishment of a pre-trained network as the source model using a long short-term memory (LSTM) network. When unsteady aerodynamic forces are predicted under the new initial conditions, a limited number of training samples are collected by high-fidelity simulations. Then, the parameters of the source model are transferred to the new prediction model, which is further fine-tuned and trained with limited samples. The new prediction model can be used to predict the unsteady aerodynamic forces of the entire process under the new initial conditions. The proposed method is validated by predicting the aerodynamic forces of free flight of a high-spinning projectile with a large extension of initial angular velocity and pitch angle. The results indicate that the proposed method can predict unsteady aerodynamic forces under different initial conditions using 1/3 of the sample size of the source model. Compared with direct modeling using the LSTM networks, the proposed method shows improved accuracy and efficiency.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Kou, J., Zhang, W.: Data-driven modeling for unsteady aerodynamics and aeroelasticity. Prog. Aerosp. Sci. 125, 100725 (2021). https://doi.org/10.1016/j.paerosci.2021.100725
Hu, L., Zhang, J., **ang, Y., et al.: Neural networks-based aerodynamic data modeling: a comprehensive review. IEEE Access 8, 90805–90823 (2020). https://doi.org/10.1109/ACCESS.2020.2993562
Li, K., Kou, J., Zhang, W.: Unsteady aerodynamic reduced-order modeling based on machine learning across multiple airfoils. Aerosp. Sci. Technol. 119, 107173 (2021). https://doi.org/10.1016/j.ast.2021.107173
Wu, Y., Dai, Y., Yang, C., et al.: Unsteady and nonlinear aerodynamic prediction of airfoil undergoing large-amplitude pitching oscillation based on gated recurrent unit network. PI Mech. Eng. G-J Aer. 237(2), 270–284 (2023). https://doi.org/10.1177/09544100221097521
Alkhedher, M.: Comparative study of machine learning modeling for unsteady aerodynamics. CMC-Comput. Mater. Continua 72(1), 1901–1920 (2022). https://doi.org/10.32604/cmc.2022.025334
Mohamed, A., Wood, D.: Deep learning predictions of unsteady aerodynamic loads on an airfoil model pitched over the entire operating range. Phys. Fluids 35(5), 053113 (2023). https://doi.org/10.1063/5.0139907
Li, K., Kou, J., Zhang, W.: Deep neural network for unsteady aerodynamic and aeroelastic modeling across multiple Mach numbers. Nonlin. Dyn. 96, 2157–2177 (2019). https://doi.org/10.1007/s11071-019-04915-9
Wang, Z., Liu, X., Yu, J., et al.: A general deep transfer learning framework for predicting the flow field of airfoils with small data. Comput. Fluids 251, 105738 (2023). https://doi.org/10.1016/j.compfluid.2022.105738
Wang, X., Kou, J., Zhang, W.: A new dynamic stall prediction framework based on symbiosis of experimental and simulation data. Phys. Fluids 33(12), 127119 (2021). https://doi.org/10.1063/5.0075083
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997). https://doi.org/10.1162/neco.1997.9.8.1735
Jia, X., Li, C., Ji, W., et al.: A hybrid reduced-order model combing deep learning for unsteady flow. Phys Fluids 34(9), 097112 (2022). https://doi.org/10.1063/5.0104848
Wang, J.D., Chen, Y.Q.: Introduction to Transfer Learning, 1st edn. Springer Nature, Singapore (2023). https://doi.org/10.1007/978-981-19-7584-4
Silton, S.I., Sahu, J., Fresconi, F.: Comparison of uncoupled and coupled CFD-based simulation techniques for the prediction of the aerodynamic behavior of a complex projectile. In: 34th AIAA Applied aerodynamics conference, pp. 3574. AIAA, Washington, D.C (2016). https://doi.org/10.2514/6.2016-3574
Wang, G., Zeng, Z., Suo, Q.: Trajectory simulation of a spinning projectile based on variable step size CFD/RBD method. In: AIAA Atmospheric Flight Mechanics Conference, p. 0522. AIAA, Florida (2015). https://doi.org/10.2514/6.2015-0522
Acknowledgments
This work was supported by the National Natural Science Foundation of China (No. U2141254).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Ji, W., Sun, X., Li, C., Jia, X., Wang, G., Gong, C. (2024). Unsteady Aerodynamic Prediction Using Limited Samples Based on Transfer Learning. In: Fu, S. (eds) 2023 Asia-Pacific International Symposium on Aerospace Technology (APISAT 2023) Proceedings. APISAT 2023. Lecture Notes in Electrical Engineering, vol 1050. Springer, Singapore. https://doi.org/10.1007/978-981-97-3998-1_81
Download citation
DOI: https://doi.org/10.1007/978-981-97-3998-1_81
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-3997-4
Online ISBN: 978-981-97-3998-1
eBook Packages: EngineeringEngineering (R0)