Effect of Choice of Basis Functions in Neural Network for Capturing Unknown Function for Dynamic Inversion Control

  • Gandham Ramesh
  • P. N. Dwivedi
  • P. Naveen Kumar
  • R. Padhi
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 188)


The basic requirement for an autopilot is fast response and minimum steady state error for better guidance performance. The highly nonlinear nature of the missile dynamics due to the severe kinematic and inertial coupling of the missile airframe as well as the aerodynamics has been a challenge for an autopilot that is required to have satisfactory performance for all flight conditions in probable engagements. Dynamic inversion is very popular nonlinear controller for this kind of scenario. But the drawback of this controller is that it is sensitive to parameter perturbation. To overcome this problem, neural network has been used to capture the parameter uncertainty on line. The choice of basis function plays the major role in capturing the unknown dynamics. Here in this paper, many basis function has been studied for approximation of unknown dynamics. Cosine basis function has yield the best response compared to any other basis function for capturing the unknown dynamics. Neural network with Cosine basis function has improved the autopilot performance as well as robustness compared to Dynamic inversion without Neural network.


Function Approximation Steady State Error Dynamic Inversion Neural Network Approximation Nominal Controller 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



The authors gratefully acknowledge the Dr. S.K. Chaudhuri, Outstanding Scientist and Director, RCI for his guideline and constant encouragement. Author is thank full to Abhijit Bhattacharya, PD, AD(M), PGAD for his suggestion and support towards this work. Authors are also grateful to SP Rao, Technology Director PGCT, RCI, Hyderabad for his constant encouragement during the course of this work. Author is also grateful to Dr. P. Chandra shekhar, Head of ECE Dept, Osmania University for his support towards this work. The authors are grateful to Prasanth Bhale, Scientist ‘D’, DRDL for his timely help during the course of this work.


  1. 1.
    Menon PK, Badget ME, Walker RA, Duke EL (1987) Nonlinear flight test trajectory controllers for aircraft. J Guid Control Dyn 10(1):67–72MATHCrossRefGoogle Scholar
  2. 2.
    Menon PK, Iragavarapu VR, Ohlmeyer EJ (1997) Nonlinear missile autopilot using time scale separation. AIAA Paper 96-3765Google Scholar
  3. 3.
    Reiner J, Balas G, Garrard WL (1994) Design of a flight control systems for a highly maneuverable aircraft using robust dynamic inversion. AIAA Paper 94-3682-CPGoogle Scholar
  4. 4.
    Buffington J, AdAms R, Banda SS (1993) Robust, nonlinear, high AOA control design for a supermaneuvring vehicle. AIAA Paper 93-3774-CPGoogle Scholar
  5. 5.
    Palumbo NF, Reardon BE, Blauwkamp RA (2004) Integrated guidance and control for homing missiles. Johns Hopkins APL Tech Dig 25(2):121–139 (2004)Google Scholar
  6. 6.
    Schumacher C, Khargankar PP (1998) Missile autopilot design using H1 control with gain scheduling and dynamic inversion. J GCD 21(2):234–243Google Scholar
  7. 7.
    Hogui S, Balas G, Garrard WL (1995) Design of a robust dynamics inversion lateral flight controller. AIAA 95-32534-CPGoogle Scholar
  8. 8.
    Mafarland MB, D’Souza CN (1994) Missile flight control with DI and structured singular value synthesis. AIAA 94-3604-CPGoogle Scholar
  9. 9.
    Devaud E, Harcaut J-P, Siguerdidjane H (2001) Three-axes missile autopilot design: from linear to nonlinear control strategies. J. Guid Control Dyn 24(1):64–71. ISSN:0731-5090Google Scholar
  10. 10.
    Bhattacharyaa A, Dwivedi PN, Kumar P, Prashant, Bhale G, Bhattacharjee RN (2007) A practical approach for robust scheduling of nonlinear time-scale separated autopilot. In: ACCORDS 2007. IISC, BangloreGoogle Scholar
  11. 11.
    Padhi R, Chunodhkar A (2007) Precision attitude maneuver of spacecraft using model following neuro adaptive control. J Syst Sci Eng 16:1Google Scholar
  12. 12.
    Padhi R, Unnikrishnan N, Balakrishnan SN (2007) Model following neuro adaptive control design for non-square, non-affine systems. IET, Control Theory Appl 1(6):1650–1661Google Scholar
  13. 13.
    Padhi R, Kothari M (2007) An optimal dynamic inversion based neuro adaptive approach for treatment of chronic mylogenous leukemia. Comput Methods Prog Biomed 87:208–228Google Scholar
  14. 14.
    Dwivedi PN, Bhattacharyaa A, Padhi R (2009) Robust dynamic inversion missile autopilot using neural network. In: Proceedings of ICEAE 2009Google Scholar

Copyright information

© Springer India 2013

Authors and Affiliations

  • Gandham Ramesh
    • 1
  • P. N. Dwivedi
    • 1
  • P. Naveen Kumar
    • 2
  • R. Padhi
    • 3
  1. 1.RCI, DRDOHyderabadIndia
  2. 2.Department of ECEOsmania UniversityHyderabadIndia
  3. 3.Department of Aerospace EngineeringIndian Institute of ScienceBangaloreIndia

Personalised recommendations