Research on Lateral Aerodynamic Modeling Based on Relevance Vector Machine

Abstract:

To describe the dynamic characteristics of flight vehicle accurately, a Relevance Vector Machine (RVM) aerodynamic modeling method is proposed. RVM is a learning method which is based on Bayesian learning theory. Compared with Support Vector Machine (SVM), it has the benefits such as probabilistic predictions, sparser model, facilities to select arbitrary basis function and so on. Experimental results show that the proposed method can obtain the aerodynamic model with higher accuracy by less relevance vector. It is also effective and feasible for aerodynamic modeling.

• Periodical: Applied Mechanics and Materials (Volume 327)
• Pages: 306-309
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.327.306
• Online since: June 2013
• Authors: Xu Sheng Gan, Jing Shun Duanmu, Jian Guo Gao
• Keywords: Aerodynamic Model, Bayesian Theory, Flight Vehicle, Kernel Function, Relevance Vector Machine

References

[1] D. J. Linse, R. F. Strengel. Identification of aerodynamic coefficients using computational neural networks. Journal of Guidance, Control and Dynamics, 16(6), (1993), 1018-1025

DOI: 10.2514/3.21122

[2] Y. B. Meng, J. H. Zou, X. S. Gan, et al., Research on WNN aerodynamic modeling from flight data based on improved PSO algorithm. Neurocomputing 83, (2012), 212-221

DOI: 10.1016/j.neucom.2011.12.015

[3] N. K. Peyada, A. K. Ghosh. Longitudinal aerodynamic parameter estimation using neural network and Gauss Newton method. Journal of Aerospace Sciences and Technology, 61, (2009), 295-304

[4] R. V. Jategaonkar. Flight vehicle system identification: a time domain methodology. Progress in Astronautics and Aeronautics Series, 1st Edition, AIAA, (2006)

[5] R. Kumar, R. Ganguli, S. N. Omkar and M. V. Kumar. Rotorcraft parameter estimation from real time flight data using radial basis function networks. Journal of Aircraft, 45 (1), (2008), 333-341

DOI: 10.2514/1.32024

[6] S. Singh, A. K. Ghosh. Parameter estimation from flight data of a missile using maximum likelihood and neural network method. Proceedings of AIAA Flight Mechanics Conference and Exhibit, (2006), 21-24

DOI: 10.2514/6.2006-6284

[7] R. Malmathanraj, S. S. Thamarai and E. Mahendran. Prediction of aerodynamic Characteristics Using Neural Network. Asian Journal of Information Technology, 7(1), (2008), 19-26

[8] M. E. Tipping. Sparse Bayesian learning and the relevance vector machine. Journal of Machine Learning Research, 1(3), (2001), 211-214

[9] C. M. Bishop, M. E. Tipping. Variational relevance vector machine. Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence, (2000), 46-53