Adaptive Markov Model Analysis for Improving the Design of Unmanned Aerial Vehicles Autopilot

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 384)


The need for Unmanned Aerial Vehicles (UAVs) is increasing as they are being used across the world for various civil, defense and aerospace applications such as surveillance, remote sensing, rescue, geographic studies, and security applications. The functionalities provided by the system is based on the system health. Monitoring the health of the system such as healthy, degraded (partially healthy or partially unhealthy) and unhealthy accurately without any impact on safety and security is of utmost importance. Hence in order to monitor the health of the system to provides the functionality for a longer period of time system fault detection and isolation techniques should be incorporated. This paper discusses Fault Detection and Isolation (FDI approach used in Unmanned Aerial Vehicle (UAV) autopilot to make its functionality more robust and available for a longer period of time. We proposes an integrated Adaptive Markov Model Analysis (AMMA) to detect and isolate faults in critical components of the system. The effectiveness of the novel approach is demonstrated by simulating the modified system design with FDI incorporation for the UAV autopilot. The proposed FDI approach helps in identifying the gyro sensor failure and provides a degraded mode to the system functionality which did not exist earlier in the design. The simulation demonstrates the system modes such as healthy, degraded (partially healthy or partially unhealthy) and unhealthy to understand the functionality better as the current design which works in only two modes i.e. healthy and unhealthy.


UAV AMMA FDI Functionality modes 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Pullum, L.L.: Software Fault Tolerance Techniques and Implementation, pp. 1–358 (2001).
  2. 2.
    Baoan, Li, Dawei, D.: Automatic test system for large unmanned aerial vehicle. IEEE, pp. 1–4 (2014)Google Scholar
  3. 3.
    Kumar, Nilesh, Jain, Sheilza: Identification Modeling and Control of Unmanned Aerial Vehicles. International Journal of Advanced Science and Technology 67, 1–10 (2014)CrossRefGoogle Scholar
  4. 4.
    Austin, R.: Design, UAVs Development and Deployment. Willey Publication, pp. 1–399 (2010)Google Scholar
  5. 5.
    Hoffer, N.V., Coopmans, C., Jensen, A.M., Chen, Y.Q.: International Conference on Unmanned Aircraft Systems (ICUAS), pp. 897–903 (2013)Google Scholar
  6. 6.
    Sadeghzadeh, I., Zhang, Y.: A Review on Fault-Tolerant Control for Unmanned Aerial Vehicles (UAVs). American Institute of Aeronautics and Astronautics, pp. 1–12 (2011)Google Scholar
  7. 7.
    Marzat, J, Piet-Lahanier, H., Damongeot, F., Walter, E.: Model-based fault diagnosis for aerospace systems: a survey, In: Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering, 1–31 (2011)Google Scholar
  8. 8.
    Supervision, I.: Fault- Detection and Fault – Diagnosis Methods- an Introduction. Elsevier science Ltd, pp. 639–652 (1997)Google Scholar
  9. 9.
    Ghahramani.Z.: An Introduction to Hidden Markov Models and Bayesian Networks. International Journal for Pattern Recognition and Artificial Intelligence, 1–25 (2001)Google Scholar
  10. 10.
    Lv, F., Li, X., Wang, X.-Q.: A survey of intelligent network fault diagnosis technology. In: 25th Chinese Control and Decision Conference (CCDC), pp. 4874–4879, (2013)Google Scholar
  11. 11.
    Grewal, M., Andrews, A.: How Good Is Your Gyro? IEEE Control Systems Magazine, 1–4, February 2010Google Scholar
  12. 12.
    G200 Dual Axis MEMS Gyro User Guide. Gladiator Technologies (2012- 2014), pp. 1–36Google Scholar
  13. 13.
    Lopez-Estrada, F.R., Ponsart, J-C, Theillio, D., Astorga-Zaragoza, C.M., Zhang, Y.M.: Robust sensor fault diagnosis and tracking controller for a UAV modelled as LPV system. In: International Conference on Unmanned Aircraft Systems (ICUAS), pp. 1311–1316, May 2014Google Scholar
  14. 14.
    Hu, B., Seiler, P.: Worst-case false alarm analysis of fault detection systems. In: American Control Conference (ACC), pp. 654–659, June 2014Google Scholar
  15. 15.
    Ahmed Nagy, Mercy Njima and Lusine Mkrtchyan.: A bayesian based method for agile software development release planning and project health monitoring. In: International Conference on Intelligent Networking and Collaborative Systems, pp. 192–199 (2010)Google Scholar
  16. 16.
    Berenji, H.R., Wang, Y.: Wavelet neural networks for fault diagnosis and prognosis. In: IEEE International Conference on Fuzzy Systems, pp. 1334–1339 (2006)Google Scholar
  17. 17.
    Kapadia, R., Stanley, G., Walker, M.: Real World Model-based Fault Management, pp. 1–8Google Scholar
  18. 18.
    Rabiner, L.R., Juang, B.H.: An Introduction to Hidden Markov Models. IEEE ASSP Magazine, 4–16 (1986)Google Scholar
  19. 19.
    Le, T.T., Chatelain, F., Berenguer, C.: Hidden Markov Models for Diagnostics and Prognostics of Systems under Multiple Deterioration Modes, pp. 1–9, July 2014Google Scholar
  20. 20.
    Stamp, M.: A Revealing Introduction to Hidden Markov Models, pp. 1–20, September 2012Google Scholar
  21. 21.
    Narasimhan, S., Choudhury, I.R., Balaban, E., Saxena, A.: combining model-based and feature-driven diagnosis approaches – a case study on electromechanical actuators. In: 21st International Workshop on Principles of Diagnosis, pp. 1–8 (2010)Google Scholar
  22. 22.
    Shang, Y.: The limit behavior of a stochastic logistic model with individual time dependent rates. Journal of Mathematics, 1–8 (2013).

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.Jawaharlal Collage of Engineering and TechnologyPalakkadIndia
  2. 2.CSIR- National Aerospace LaboratoriesBangaloreIndia

Personalised recommendations