Skip to main content
SpringerLink
Log in

Development of Fault Detection and Identification Algorithm Using Deep learning for Nanosatellite Attitude Control System

  • Original Paper
  • Published:
International Journal of Aeronautical and Space Sciences Aims and scope Submit manuscript

Abstract

Satellites should have high reliability because they are required to operate autonomously, while performing a given mission. To realize this, it is necessary to use heritage parts or include redundancy. However, for nanosatellites, where it is difficult to include redundancy due to volume and weight limitations, fault management becomes crucial. In this study, a new method based on deep learning is proposed for detecting and identifying the faults in the reaction wheel, which is one of the satellite actuators. A deep learning model is applied to learn the fault and fault type using the residual between the measured attitude data and the estimated attitude date. In this study, it is assumed that three reaction wheels are installed, and fault detection is designed accordingly. The proposed model enables the satellite to detect faults autonomously, even when it is not communicating with the ground station, and is expected to be highly beneficial for the autonomous operation of the mega-constellation mission using nanosatellite that is to be activated in future.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

References

  1. Lim JK, Park CG, Lee JH (2009) Robust satellite FDI method for sudden strange signal. In: Proceeding of the 2009 KSAS Spring Conference Korea, pp 332–335

  2. Tudoroiu N, Sobhani-Tehrani E, Khorasani K (2006) Interactive bank of unscented Kalman filters for fault detection and isolation in reaction wheel actuators of satellite attitude control system. IEEE Industrial Electronics, IECON 2006—32nd Annual Conference on. IEEE, pp 264–269. https://doi.org/10.1109/IECON.2006.347890

  3. Kim DH, Choi DG, Kim JH, Oh HS (2009) PDF based failure diagnosis of reaction wheel. In: Proceeding of the 2009 KSME Fall Conference Korea, pp 964–968

  4. Choi KR, Park CG (2009) Design of fault isolator of satellite reaction wheel system using dual filter and multi-hypothesis extended Kalman Filter. JKSAS 37(12):1225–1231

    Article  Google Scholar 

  5. Jin JH, Yong KR (2011) fault detection of a spacecraft’s reaction wheels by extended unknown input observer. JICROS 17(11):1138–1144. https://doi.org/10.5302/J.ICROS.2011.17.11.1138

    Article  Google Scholar 

  6. Yoon HJ, Jin JH (2013) Design of nonlinear unknown input observer by SDRE method and fault detection of reaction wheels. JKSAS 41(4):284–290. https://doi.org/10.5139/JKSAS.2013.41.4.284

    Article  Google Scholar 

  7. Kim HD, Choi WS, Cho DH, Kim MK, Kim JH, Sim ES, Lim SM, Kim EJ (2016) Current status of the development of 6U cubesat for high resolution image and video (HiREV CubeSat). In: Proceeding of the Korean Society for Aeronautical and Fall Sciences Spring Conference (in Korean), pp 444–445

  8. Bang HC, Tahk MJ, Choi HD (2003) Large angle attitude control of spacecraft with actuator saturation. Control Eng Pract 11(9):989–997

    Article  Google Scholar 

  9. Karatas S (2006) Leo satellites: dynamic modelling, simulations and some nonlinear attitude control techniques. M.sc., Department of Electrical and Electronics Engineering, Middle East Technical University

  10. Yan S (2015) Understanding LSTM networks. http://web.stanford.edu/class/cs379c/class_messages_listing/content/Artificial_Neural_Network_Technology_Tutorials/OlahLSTM-NEURAL-NETWORK-TUTORIAL-15.pdf. Accessed 15 Oct 2018

Download references

Acknowledgements

This research was supported by the “Development of Rendezvous/Docking Technology demonstration Nanosatellite based on AI” funded by the Korea Aerospace Research Institute (KARI). We would like to thank KARI for their support.

Author information

Authors and Affiliations

  1. Korea University of Science and Technology, Daejeon, South Korea

    Kwang-Hyun Lee & SeongMin Lim

  2. Korea Aerospace Research Institute, Korea University of Science and Technology, Daejeon, South Korea

    Dong-Hyun Cho & Hae-Dong Kim

Authors
  1. Kwang-Hyun Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. SeongMin Lim
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Dong-Hyun Cho
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Hae-Dong Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hae-Dong Kim.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Lee, KH., Lim, S., Cho, DH. et al. Development of Fault Detection and Identification Algorithm Using Deep learning for Nanosatellite Attitude Control System. Int. J. Aeronaut. Space Sci. 21, 576–585 (2020). https://doi.org/10.1007/s42405-019-00235-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s42405-019-00235-9

Keywords

Search

Navigation