Linear Parameter-Varying Two Rotor Aero-Dynamical System Modelling with State-Space Neural Network

  • Marcel LuzarEmail author
  • Józef Korbicz
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10842)


In every model-based approaches, i.e., fault diagnosis, fuzzy control, robust fault-tolerant control, the exact model is crucial. This paper presents a methodology which allows to obtain an exact model of high-order, non-linear cross-coupled system, namely Two Rotor Aero-dynamical System (TRAS), using a state-space neural network. Moreover, the resulting model is presented in a linear parameter-varying (LPV) form making it easier to analyze (i.e., its stability and controllability) and control. Such a form is obtained by direct transformation of the neural network structure into quasi-LPV model. For the neural network modelling, a SSNN Toolbox is utilized.


Non-linear modelling Neural networks Linear parameter-varying system 



The work was supported by the National Science Centre of Poland under grant: UMO-2014/15/N/ST7/00749.


  1. 1.
    Abbas, H., Werner, H.: Polytopic quasi-LPV models based on neural state-space models and application to air charge control of a SI engine. In: 17th IFAC World Congress, pp. 6466–6471 (2008)CrossRefGoogle Scholar
  2. 2.
    Bendtsen, J., Trangbæk, K.: Robust quasi-LPV control based on neural state-space models. IEEE Trans. Neural Netw. 13(2), 355–368 (2002)CrossRefGoogle Scholar
  3. 3.
    Hassanabadi, A., Shafiee, M., Puig, V.: Robust fault detection of singular LPV systems with multiple time-varying delays. Int. J. Appl. Math. Comput. Sci. 26(1), 45–61 (2016)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Lachhab, N., Abbas, H., Werner, H.: A neural-network based technique for modelling and LPV control of an arm-driven inverted pendulum. In: Proceedings of the 47th IEEE Conference on Decision and Control, Cancun, Mexico, pp. 3860–3865 (2008)Google Scholar
  5. 5.
    Luzar, M., Czajkowski, A.: LPV system modeling with SSNN toolbox. In: American Control Conference, pp. 3952–3957 (2016)Google Scholar
  6. 6.
    Luzar, M., Witczak, M., Witczak, P., Auburn, C.: Neural-network based robust predictive fault-tolerant control for multi-tank system. In: 13th European Control Conference (ECC), pp. 276–281 (2014)Google Scholar
  7. 7.
    Martin, D.P., Johnson, K.E., Zalkind, D.S., Pao, L.Y.: LPV-based torque control for an extreme-scale morphing wind turbine rotor. In: American Control Conference, pp. 1383–1388 (2017)Google Scholar
  8. 8.
    Nørgaard, M., Ravn, O., Poulsen, N.K., Hansen, L.K.: Neural Networks for Modelling and Control of Dynamic Systems. Springer, Heidelberg (2014)zbMATHGoogle Scholar
  9. 9.
    Patan, K.: Artificial neural networks for the modelling and fault diagnosis of technical processes. Springer, Heidelberg (2008). Scholar
  10. 10.
    Shen, Y., Yu, J., Luo, G., Mei, Y.: Missile autopilot design based on robust LPV control. J. Syst. Eng. Electron. 28(3), 536–545 (2017)Google Scholar
  11. 11.
    Two Rotor Aero-Dynamical System–User’s Manual (2013).
  12. 12.
    Xu, F., Puig, V., Ocampo-Martinez, C., Olaru, S., Niculescu, S.: Robust MPC for actuator-fault tolerance using set-based passive fault detection and active fault isolation. Int. J. Appl. Math. Comput. Sci. 27(1), 43–61 (2017)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Yang, D., Zhao, J.: \(\cal{H}_{\infty }\) output tracking control for a class of switched LPV systems and its application to an aero-engine model. Int. J. Robust Nonlinear Control 27(12), 2102–2120 (2017)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Institute of Control and Computation EngineeringUniversity of Zielona GóraZielona GóraPoland

Personalised recommendations