Abstract
Using the engineering algorithm, the aerodynamic characteristics data set for tactical missiles with over 3000 shapes has been established. The adoption of four machine learning algorithms, including gradient boosting decision tree (GBDT), XGBoost, multi-task learning neural network (MTLNN) and embedded Physics Informed Neural Network (PINN), is made. A proposed method for predicting the aerodynamic characteristics of tactical missiles is based on data. Test set shows that the deep learning algorithm is better than the classic machine learning algorithm. The synthetic deviation of normal force and pitching moment coefficients obtained by the latter three machine learning algorithms is less than 5%; Due to the introduction of physical mechanism between aerodynamic characteristics parameters in PINN model, not only the prediction accuracy is improved, but also the dependence of the model on the number of training samples is reduced. The PINN model has strong generalization ability and high prediction accuracy can still be obtained for data outside the training samples. Among the three machine learning algorithms, PINN model has the best prediction effect, and the comprehensive deviation of normal force and pitching moment coefficient is 0.72% and 1.05%, respectively. A new idea for the aerodynamic design of tactical missiles is provided by this prediction method.
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
He, K., Qian, W., Wang, Q., et al.: Application of data fusion technique in aerodynamics studies. Acta Aerodynamica Sinica 32(6), 777–782 (2014)
Zhang, T., Qian, W., Zhou, Y., et al.: Preliminary thoughts on the combination of artificial intelligence and aerodynamics. Adv. Aeronaut. Sci. Eng. 10(1), 1–11 (2019)
Dupuis, R., Jouhaud, J.: Aerodynamic data predictions for transonic flows via a machine-learning-based surrogate model. In: 2018 AIAA/ASCE/AHS/ASC Structures, Structural Dynamics, and Materials Conference (2018)
Zhang, W., Kou, J., Liu, Y.: Prospect of artificial intelligence empowered fluid mechanics. Acta Aerodynamica Sinica 42(4), 524689 (2021)
Sekar, V., Jiang, Q., Shu, C., et al.: Fast flow field prediction over airfoils using deep learning approach. Phys. Fluids 31(5), 057103 (2019)
Yang, H.: Research and application of aerodynamic data analysis method. Master’s thesis of Bei**g University of Posts and Telecommunications (2018)
Chen, H., Qian, W., He, L.: Aerodynamic coefficient prediction of airfoils based on deep learning. Acta Aerodynamica Sinica 36(2), 294–299 (2018)
He, L., Qian, W., Wang, Q., et al.: Applications of machine learning for aerodynamic characteristics modeling. Acta Aerodynamica Sinica 37(3), 470–479 (2019)
Chen, B., Liu, C., Bai, P., et al.: Aerodynamic prediction for waveriders using deep residual learning. Acta Aerodynamica Sinica 37(3), 505–509 (2019)
Sun, Y., Sun, G., Wang, S.: Neural net based wing shape prediction. Chin. Q. Mech. 25(3), 482–490 (2014)
Chen, H., Deng, K., Li, R.: Utilization of machine learning technology in aerodynamic optimization. Acta Aeronautica et Astronautica Sinica 40(1), 522480 (2019)
Chen, J.: Research on advanced aerodynamic wing design of civil aircraft based on neural network method. Master’s thesis, Fudan University (2011)
Wu, P., et al.: Missile aerodynamic shape optimization design using deep neural networks. Aerosp. Sci. Technol. 126, 107640 (2022)
Yan, X., Zhu, J., Kuang, M., Wang, X.: Missile aerodynamic design using reinforcement learning and transfer learning. Sci. China Inf. Sci. 61, 119204 (2018)
Zhao, T., Zhou, Y., Cheng, Y., et al.: Solving forward and inverse problems of the heat conduction equation using physics-informed neural networks. Acta Aerodynamica Sinica 39(5), 19–26 (2021)
Zhou, L., Zhao, X.: Aerodynamic calculation of air-breathing missile. Acta Aerodynamica Sinica 24(4), 491–494 (2006)
Lesieutre, D., Love, J., Dillenius, M.: Recent applications and improvements to the engineering-level aerodynamic prediction software MISL3. In: AIAA 2002, p. 0275 (2002)
Moore, F., Hymer, T.: 2005 version of the aeroprediction code. J. Spacecraft Rockets 42(2), AP05 (2005)
Zhang, Y., Liu, J., Zuo, X.: Multi-tasking learning. J. Comput. Sci. 43(7), 1340–1378 (2020)
Karniadakis, E., Kevrekidis, G., Lu, L., et al.: Physics-informed machine learning. Nat. Rev. Phys. 3(6), 422–440 (2021)
Lin, J., Zhou, L., Wu, P., et al.: Research on rapid prediction technology of missile aerodynamic characteristics based on PINN. J. Bei**g Univ. Aeronaut. Astronaut. 49(10), 1–10 (2023)
Mao, Z., Jagtap, D., Karniadakis, E.: Physics-informed neural networks for high-speed flows. Comput. Methods Appl. Mech. Eng. 360, 112789 (2020)
Buhendwa, B., Adami, S., Adams, A.: Inferring incompressible two-phase flow fields from the interface motion using physics-informed neural networks. Mach. Learn. Appl. 4, 100029 (2021)
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
Zhou, L. et al. (2024). Data-Driven Prediction Method of Tactical Missile Aerodynamic Characteristics. In: Fu, S. (eds) 2023 Asia-Pacific International Symposium on Aerospace Technology (APISAT 2023) Proceedings. APISAT 2023. Lecture Notes in Electrical Engineering, vol 1051. Springer, Singapore. https://doi.org/10.1007/978-981-97-4010-9_123
Download citation
DOI: https://doi.org/10.1007/978-981-97-4010-9_123
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-4009-3
Online ISBN: 978-981-97-4010-9
eBook Packages: EngineeringEngineering (R0)