Abstract
A modelling and simulation problem is considered for longitudinal motion of a maneuverable aircraft that is viewed as a nonlinear controlled dynamical system under multiple and diverse uncertainties. This problem is solved by utilizing semi-empirical neural network based approach that combines theoretical domain-specific knowledge with training tools of artificial neural network field. Semi-empirical approach allows for a substantial accuracy improvement over traditional purely empirical models such as the Nonlinear AutoRegressive neural network with eXogenous inputs (NARX). It also provides solution to system identification problem for aerodynamic characteristics of an aircraft, such as the coefficients of aerodynamic axial and normal forces, as well as the pitch moment coefficient. Representative training data set is obtained using an automatic procedure which synthesizes control actions that provide a sufficiently dense coverage of the region of change in the values of variables describing the simulated system. Neural network model learning efficiency is further improved by the use of special weighting scheme for individual training samples. Obtained simulation results confirm the efficiency of proposed simulation approach.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Egorchev, M.V., Kozlov, D.S., Tiumentsev, Y.V., Chernyshev, A.V.: Neural network based semi-empirical models for controlled dynamical systems. J. Comput. Inf. Technol. 9, 3–10 (2013). (in Russian)
Egorchev, M.V., Kozlov, D.S., Tiumentsev, Y.V.: Neural network adaptive semi-empirical models for aircraft controlled motion. In: Proceedings of the 29th Congress of the International Council of the Aeronautical Sciences, vol. 4 (2014)
Egorchev, M.V., Tiumentsev, Y.V.: Learning of semi-empirical neural network model of aircraft three-axis rotational motion. Optical Memory Neural Netw. 24(3), 201–208 (2015)
Oussar, Y., Dreyfus, G.: How to be a gray box: dynamic semi-physical modeling. Neural Netw. 14(9), 1161–1172 (2001)
Dreyfus, G.: Neural Networks – Methodology and Applications. Springer (2005)
Bochkariov, A.F., Andreyevsky, V.V., Belokonov, V.M., Klimov, V.I., Turapin, V.M.: Aeromechanics of Airplane: Flight Dynamics, 2nd edn. Mashinostroyeniye, Moscow (1985). (in Russian)
Nguyen, L.T., Ogburn, M.E., Gilbert, W.P., Kibler, K.S., Brown, P.W., Deal, P.L.: Simulator study of stall/post-stall characteristics of a fighter airplane with relaxed longitudinal static stability. Technical report TP-1538, NASA, December 1979
Muja, M., Lowe, D.G.: Scalable nearest neighbor algorithms for high dimensional data. IEEE Trans. Pattern Anal. Mach. Intell. 36(11), 2227–2240 (2014)
Haykin, S.: Neural Networks: A Comprehensive Foundation, 2nd edn. Prentice Hall PTR, Upper Saddle River (1998)
Jesus, O.D., Hagan, M.T.: Backpropagation algorithms for a broad class of dynamic networks. IEEE Trans. Neural Netw. 18(1), 14–27 (2007)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Egorchev, M., Tiumentsev, Y. (2018). Neural Network Semi-empirical Modeling of the Longitudinal Motion for Maneuverable Aircraft and Identification of Its Aerodynamic Characteristics. In: Kryzhanovsky, B., Dunin-Barkowski, W., Redko, V. (eds) Advances in Neural Computation, Machine Learning, and Cognitive Research. NEUROINFORMATICS 2017. Studies in Computational Intelligence, vol 736. Springer, Cham. https://doi.org/10.1007/978-3-319-66604-4_10
Download citation
DOI: https://doi.org/10.1007/978-3-319-66604-4_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-66603-7
Online ISBN: 978-3-319-66604-4
eBook Packages: EngineeringEngineering (R0)