Skip to main content
SpringerLink
Log in

Efficient anomaly classification for spacecraft reaction wheels

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Attitude Determination and Control Subsystem (ADCS) in spacecraft is one of the vital systems for low-earth-orbit spacecraft in which the pointing accuracy is a highly recommended factor to satisfy its mission requirements. When any malfunction takes place at attitude actuator, the spacecraft will not satisfy the required mission objectives. It is required to identify specific faults for attitude actuators in a manner that helps to optimally recover this type of anomaly. An efficient anomaly detection and identification technique is a suitable way to identify such anomaly. This research introduces an accurate and high-performance methodology for fault detection and identification for spacecraft reaction wheels (RW) as (ADCS) actuator. Proposed approach is to differentiate among signatures of possible anomalies that may be occurred at RW like under-voltage, over-voltage, current losses, temperature decrease, and temperature increase. “Prony method,” as a feature extraction technique, is used to discriminate between normal system behavior and anomalies based on the three-axis spacecraft RW operation. A feed-forward neural network with back-propagation algorithm is used for anomaly identification. Prony order assessment is also carried out to obtain the proper order of poles and zeros to minimize the processing time required for identification. The results verify that the proposed anomaly identification is successfully accomplished with high degree of confidence and with minimal execution time. Research approach leads to generic methodology for anomaly identification process among all spacecraft subsystem anomalies.

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

Similar content being viewed by others

References

  1. Ure N, Kaya Y, Inalhan G, (2011) The development of a software and hardware in the-loop test system for ITU-PSAT nano satellite ADCS. In: IEEE aerospace conference, vol 16. pp 1–15

  2. Boskovic JD, Li SM, Mehra RK (1999) Intelligent control of spacecraft in the presence of actuator failures, In: 38th IEEE conference on decision and control, vol 5. IEEE, 6:4472–4477

  3. Pirmoradi F, Sassani F, De Silva C (2009) Fault detection and diagnosis in a spacecraft ADCS. Acta Astronaut 65(5):710–729

    Article  Google Scholar 

  4. Venkatasubramanian V et al (2003) A review of process fault detection and diagnosis part I: Quantitative model-based methods. Comput Chem Eng 27(19):293–311

    Article  Google Scholar 

  5. Venkatasubramanian V et al (2003) A review of process fault detection and diagnosis part II: Qualitative models and search strategies. Comput Chem Eng 27(14):313–326

    Article  Google Scholar 

  6. Venkatasubramanian V et al (2003) A review of process fault detection and diagnosis part III: Process history based methods. Comput Chem Eng 27(20):327–346

    Article  Google Scholar 

  7. Al-Zyoud IAD, Khorasani K (2005) Detection of actuator faults using a dynamic neural network for the attitude control subsystem of a satellite. In: Conference on neural networks, Montreal, Canada, vol 5. pp 1747–1751

  8. Wu Q, Saif M (2005) Neural adaptive observer based fault detection and identification for satellite attitude control systems. In: 2005 American control conference, USA, vol 5. pp 1055–1059

  9. Li ZQ, Ma L, Khorasani K (2006) A dynamic neural network-based reaction wheel fault diagnosis for satellites. In: International joint conference on neural networks, vol 8. Vancouver, BC, Canada, pp 3714–3721

  10. Talebi HA, Patel RV (2006) An intelligent fault detection and recovery scheme for reaction wheel actuator of satellite attitude control systems. In: IEEE international conference on control applications Munich, Germany, vol 6. pp 3282–3287

  11. Selmic RR, Polycarpou Marios M, Parisin T (2009) Actuator fault detection in nonlinear uncertain systems using neural on-line approximation models. Eur J Control EUCA No. 1 16:29–44

    Article  MathSciNet  MATH  Google Scholar 

  12. Wu Q, Saif M (2009) Model-based robust fault diagnosis for satellite control systems using learning and sliding mode approaches. J Comput 4(10):1022–1032

    Article  Google Scholar 

  13. Baldi P, Castaldi P, et al (2010) Fault diagnosis and control reconfiguration for satellite reaction wheels. In: Conference on control and fault tolerant systems, France, vol 6. pp 143–148

  14. Long X et al (2011) Anomaly detection of spacecraft based on least squares support vector machine. In: Prognostics and system health management conference, Shenzhen, vol 6. pp 1–6

  15. Regaieg M et al (2013) Fault detection and isolation of spacecraft thrusters by using principal component analysis. In: 4th European conference for aerospace sciences, Algiers, vol 6. pp 1–6

  16. Odendaal HM, Jones Th (2014) “Actuator fault detection and isolation: an optimised parity space approach. ELSEVIER Control Eng Pract 26:222–232

    Article  Google Scholar 

  17. Gueddi I, Nasri O, Benothman K, Dague P (2015) VPCA-based fault diagnosis of spacecraft reaction wheels. In: XXV conference on information, communication, and automation technology, Sarajevo, vol 6. pp 1–6

  18. Gao Y et al (2012) Fault detection and diagnosis for spacecraft using principal component analysis and support vector machines. In: 7th IEEE conference on industrial electronics and applications (ICIEA), Singapore, vol 5. pp 1984–1988

  19. Baldi P et al (2016) Combined geometric and neural network approach to generic fault diagnosis in satellite actuators and sensors. In: 20th IFAC symposium on automatic control in aerospace sherbrooke, Quebec, Canada, vol 49(No. 17), 6, pp 432–437

  20. Mousavi S, Khorasani K (2014) Fault detection of reaction wheels in attitude control subsystem of formation flying satellites. Int J Intell Unmanned Syst 2(1):2–26

    Article  Google Scholar 

  21. Froelich R, Papapoff H (1959) Reaction wheel attitude control for space vehicles. Autom Control IRE Trans 4:139–149

    Article  Google Scholar 

  22. Bialke B (1998) High fidelity mathematical modeling of reaction wheel performance. In: 21th annual American astronautical society guidance and control conference, vol 14. pp 483–496

  23. Tawfik MM, Morcos MM (2005) On the use of Prony method to locate faults in loop systems by utilizing modal parameters of fault current. IEEE Power Deliv Trans 20(1):532–534

    Article  Google Scholar 

  24. Moustafa A, et al (2009) Electrocardiogram signals identification for cardiac arrhythmias using Prony’s method and neural network. In: 31st international conference of the IEEE, Minnesota, USA, vol 4. pp 893–1896

  25. Farshad M, Sadeh J (2014) Transmission line fault location using hybrid wavelet-Prony method and relief algorithm. Electr Power Energy Syst 61(10):127–136

    Article  Google Scholar 

  26. Elsayed OA, Eldeib A, Elhefnawi F (2014) Parametric modeling of ICTAL Epilepsy EEG signal using Prony method. Int J Comput Sci Softw Eng (IJCSSE) 3(1):86–89

    Google Scholar 

  27. Faiz J, Lotfi-fard S (2007) Prony-Based Optimal Bayes Fault Classification of Overcurrent Protection. IEEE Trans Power Deliv 22(3):1326–1334

    Article  Google Scholar 

  28. Reid HM (2013) Introduction to statistics: fundamental concepts and procedures of data analysis. 1st edn. ISBN: 978-1452271965

  29. Fausett LV (1993) Fundamentals of neural networks: architectures, algorithms and applications. 1st edn. ISBN: 9780133341867

  30. Zurada JM (1992) Introduction to artificial neural systems. West Publishing Comp, St. Paul. ISBN 0-314-93391-3

    Google Scholar 

  31. Kolcio Ksenia (2016) Model-based fault detection and identification system for increased autonomy. Am Inst Aeronaut Astronaut AIAA 12:1–12

    Google Scholar 

  32. Omran EA, Murtada WA (2017) Fault detection and identification of spacecraft reaction wheels using autoregressive moving average model and neural networks. In: IEEE 12th international computer engineering conference (ICENCO), vol 5. pp 77–82

Download references

Author information

Authors and Affiliations

  1. Egyptian Space Technology Center (STC/FUE), El-khalifa Maamoon, Kobri El-koba, Cairo, Egypt

    Ehab A. Omran

  2. National Authority for Remote Sensing and Space Sciences (NARSS), 23 Jozeph Tito St., Cairo, Egypt

    Wael A. Murtada

Authors
  1. Ehab A. Omran
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Wael A. Murtada
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ehab A. Omran.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Omran, E.A., Murtada, W.A. Efficient anomaly classification for spacecraft reaction wheels. Neural Comput & Applic 31, 2741–2747 (2019). https://doi.org/10.1007/s00521-017-3226-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-017-3226-y

Keywords

Search

Navigation