Modelling of Aircraft’s Dynamics Using Least Square Support Vector Machine Regression

  • Hari Om VermaEmail author
  • Naba Kumar Peyada
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 655)


The system identification is a broad area of research in various fields of engineering. Among them, our concern is to identify the aircraft dynamics by means of the measured motion and control variables using a new approach which is based on the support vector machine (SVM) regression. Due to the computational complexity of SVM, it is suggested to adopt the advanced version of SVM i.e. least square support vector machine (LSSVM) to be used for system identification. LSSVM regression is a network-based approach which requires a user defined kernel function and a set of input-output data for its training before the prediction phase like a neural-network (NN) based procedure. In this paper, LSSVM regression has been used to identify the non-linear dynamics of aircraft using real flight data.


System identification LSSVM regression Kernel function 


  1. 1.
    Zadeh, L.A.: From circuit theory to system theory. Proc. IRE 50, 856–865 (1962)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Hamel, P.G., Jategaonkar, R.V.: The evolution of flight vehicle system identification. AGARD, DLR Germany, 8–10 May 1995Google Scholar
  3. 3.
    Jategaonkar, R.V.: Flight Vehicle System Identification: A Time Domain Methodology. AIAA Progress in Aeronautics and Astronautics, vol. 216. AIAA, Weinheim (2006)CrossRefGoogle Scholar
  4. 4.
    Klein, V., Morelli, E.: Aircraft System Identification: Theory and Practice. AIAA Education Series Inc., Reston (2006)CrossRefGoogle Scholar
  5. 5.
    Goman, M., Khrabrov, A.: State-space representation of aerodynamic characteristics of an aircraft at high angles of attack. J. Aircr. 31(5), 1109–1115 (1994)CrossRefGoogle Scholar
  6. 6.
    Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Netw. 2, 359–366 (1989)CrossRefGoogle Scholar
  7. 7.
    Hassoun, M.H.: Fundamental of Artificial Neural Networks. The MIT Press, Cambridge (1995)zbMATHGoogle Scholar
  8. 8.
    Haykins, S.: Neural Networks: A Comprehensive Foundation. McMaster University, Macmillan College Publishing Company, New York (1994)Google Scholar
  9. 9.
    Raisinghani, S.C., Ghosh, A.K., Kalra, P.K.: Two new techniques for parameter estimation using neural networks. Aeronaut. J. 102(1011), 25–29 (1998). UKGoogle Scholar
  10. 10.
    Singh, S., Ghosh, A.K.: Estimation of lateral-directional parameters using neural networks based modified delta method. Aeronaut. J. 111(1124), 659–667 (2007). UKCrossRefGoogle Scholar
  11. 11.
    Peyada, N.K., Ghosh, A.K.: Aircraft parameter estimation using new filtering technique based on neural network and Gauss-Newton method. Aeronaut. J. 113(1142), 243–252 (2009)CrossRefGoogle Scholar
  12. 12.
    Kumar, R., Ghosh, A.K.: Nonlinear longitudinal aerodynamic modeling using neural Gauss-Newton method. J. Aircr. 48(5), 1809–1812 (2011). AIAA, USACrossRefGoogle Scholar
  13. 13.
    Vapnik, V.: The Nature of Statistical Learning Theory. Springer, Berlin (1995)CrossRefzbMATHGoogle Scholar
  14. 14.
    Suykens, J.A.K., Gestel, T.V., Brabanter, J.D., Moor, B.D., Vandewalle, J.: Least Squares Support Vector Machines. World Scientific Publishing Co., Singapore (2002)CrossRefzbMATHGoogle Scholar
  15. 15.
    Wang, Q., Qian, W., He, K.: Unsteady aerodynamic modelling at high angles of attack using support vector machines. Chin. J. Aeronaut. 28(3), 659–668 (2015)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2017

Authors and Affiliations

  1. 1.Aerospace DepartmentIIT KharagpurKharagpurIndia

Personalised recommendations