Export file:

Format

  • RIS(for EndNote,Reference Manager,ProCite)
  • BibTex
  • Text

Content

  • Citation Only
  • Citation and Abstract

Classification with automatic detection of unknown classes based on SVM and fuzzy MBF: Application to motor diagnosis

1 Safran Electronics & Defense, Avionics Division, Center of Product Excellence in Avionic Systems and Actuation (CEP-SAA) F-91300, Massy, France
2 University of Lyon, UCB Lyon 1, CNRS, AMPERE, F-69100, Villeurbanne, France
3 Groupe de Recherche en Electrotechnique et Electronique de Nancy (GREEN), University of Lorraine, F-54510 Nancy, France

Topical Section: Artificial Intelligence and Machine Learning

Classification algorithms based on data mining tools show good performances for the automatic diagnosis of systems. However, these performances degrade quickly when the database is not exhaustive. This happens, for example, when a new class appears. This class could correspond to a previous unknown fault or to an unknown combination of simultaneous faults. Described algorithm in this paper proposes a solution to this issue. It combines Support Vector Machine (SVM), fuzzy membership functions (mbf) and fuzzy information fusion. It results in the construction of a matrix of memberships to known classes U_class and a vector of membership to unknown classes U_others. Then, from these values, indicators of distance and ambiguity of the observations can be computed. These indicators allow setting a simple rejection rule with a threshold classifier. The algorithm is validated by using Cross-Validation (CV) on experimental data on an induction motor faults supplied by a voltage-source inverter. The results show the good performances of the proposed algorithms and its suitability for transportation systems like aircrafts.
  Figure/Table
  Supplementary
  Article Metrics

References

1. Polo G (2011) On maritime transport costs, evolution, and forecast. Ship Science and Technology, 5: 19–31.

2. Operations and Maintenance (O&M) Costs Technical Memorandum, 2015. PARSONS BRINCKERHOFF –AECOM. Available from:https://www.fra.dot.gov/necfuture/pdfs/feis/volume_2/appendix/app_b09.pdf.

3. Markou C, Cros G, Sng A (2015) Airline Maintenance Cost Executive Commentary. IATA. Available from:https://www.iata.org/whatwedo/workgroups/Documents/MCTF/AMC-Exec-Comment-FY14.pdf.

4. Thomson R, Edwards M, Britton E, et al. (2014) Predictive Maintenance : Is the timing right for predictive maintenance in the manufacturing sector ? Roland Berger Strategy Consultants.

5. Fumera G, Roli F (2002) Support vector machines with embedded reject option, In: Pattern Recognition with Support Vector Machines. Springer, 68–82.

6 Grandvalet Y, Rakotomamonjy A, Keshet J, et al. (2009) Support vector machines with a reject option, In: Advances in Neural Information Processing Systems. 537–544.

7. Wegkamp M, Yuan M (2011) Support vector machines with a reject option. Bernoulli 17: 1368–1385. Available from: https://projecteuclid.org/euclid.bj/1320417508.    

8. Abe S, Inoue T (2002) Fuzzy Support Vector Machines for Multiclass Problems. European Symposium on Artificial Neural Networks, Bruges (Belgium).

9. Lin CF, Wang SD (2002) Fuzzy support vector machines. IEEE Transaction on Neural Network 13: 464–471.    

10. Ma H, Xiong Y, Fang H, et al. (2015) Fault diagnosis of bearing based on fuzzy support vector machine, In: 2015 Prognostics and System Health Management Conference (PHM), 1–4.

11. Ebrahimi H, Gatabi JR, El-Kishky H (2015) An auxiliary power unit for advanced aircraft electric power systems. Electr Pow Syst Res 119: 393–406.    

12. Guan Y, Zhu ZQ, Afinowi IAA, et al. (2016) Difference in maximum torque-speed characteristics of induction machine between motor and generator operation modes for electric vehicle application. Electr Pow Syst Res 136: 406–414.    

13. Wu Y, Jiang B, Lu N, et al. (2016) Multiple incipient sensor faults diagnosis with application to high-speed railway traction devices. ISA T 67:183–192.

14. Baraldi P, Cannarile F, Maio FD, et al. (2016) Hierarchical k-nearest neighbours classification and binary differential evolution for fault diagnostics of automotive bearings operating under variable conditions. Eng Appl Artif Intel 56: 1–13.    

15. Bessam B, Menacer A, Boumehraz M, et al. (2016) Detection of broken rotor bar faults in induction motor at low load using neural network. ISA T 64: 241–246.    

16. Ferracuti F, Giantomassi A, Iarlori S, et al. (2015) Electric motor defects diagnosis based on kernel density estimation and Kullback–Leibler divergence in quality control scenario. Eng Appl Artif Intel 44: 25–32.    

17 Glowacz A, Glowacz Z (2017) Diagnosis of the three-phase induction motor using thermal imaging. Infrared Phys Techn 81: 7–16.    

18. Vapnik VN (1995) The Nature of Statistical Learning Theory. Springer-Verlag New York, Inc., New York, NY, USA.

19. Han G, Meng-Kun L (2018) Induction motor faults diagnosis using support vector machine to the motor current signature. IEEE Industrial Cyber-Physical Systems (ICPS), 417–421.

20. Camarena-Martinez D, Valtierra-Rodriguez M, Amezquita-Sanchez JP, et al. (2016) Shannon Entropy and K-Means Method for Automatic Diagnosis of Broken Rotor Bars in Induction Motors Using Vibration Signals. Shock Vib Article ID: 4860309.

21. Burges CJC (1998) A Tutorial on Support Vector Machines for Pattern Recognition. Data Min Knowl Disc 2: 121–167.    

22. Bottou L, Lin CJ (2007) Support vector machine solvers. Large scale kernel machines 3: 301–320.

23. Zadeh LA (1965) Fuzzy sets. Information and Control 8: 338–353.    

24. Gassert H (2004) Operators on Fuzzy Sets: Zadeh and Einstein. Seminar Paper, Department of Computer Science Information Systems Group, University of Fribourg.

25. Mizumoto M, Tanaka K (1981) Fuzzy sets and their operations. Information and Control 48: 30–48.    

26. Ondel O, Clerc G, Boutleux E, et al. (2009) Fault Detection and Diagnosis in a Set "Inverter–Induction Machine" Through Multidimensional Membership Function and Pattern Recognition. IEEE Transaction on Energy Conversion 24: 431–441.    

27. Ondel O (2006) Diagnosis by Pattern Recognition: application on a set inverter – induction machine. Ecole Centrale de Lyon.

28. Bolander N, Qiu H, Eklund N, et al. (2009) Physics-based Remaining Useful Life Prediction for Aircraft Engine Bearing Prognosis. Annual Conference of the Prognostics and Health Management Society.

29. Deleroi W (1982) Squirrel cage motor with broken bar in the rotor-Physical phenomena and their experimental assessment. Proc of Int Conf on Electrical Machines (ICEM), Budapest, Hungary, 767–771.

30. Venet P, Lahyani A, Grellet G, et al. (1999) Influence of aging on electrolytic capacitors function in static converters: Fault prediction method. Eur Phys J-Appl Phys 5: 71–83.    

31. Schoen RR, Habetler TG, Kamran F, et al (1994) Motor bearing damage detection using stator current monitoring, In: Proceedings of 1994 IEEE Industry Applications Society Annual Meeting 1: 110–116.

32. Schoen RR, Habetler TG (1993) Effects of time-varying loads on rotor fault detection in induction machines, In: Conference Record of the 1993 IEEE Industry Applications Conference Twenty-Eighth IAS Annual Meeting 1: 324–330.

33. Vas P (1992) Electrical machines and drives: a space-vector theory approach, Monographs in electrical and electronic engineering. Clarendon Press.

34. Casimir R, Boutleux E, Clerc G, et al. (2003) Broken bars detection in an induction motor by pattern recognition, In: IEEE Bologna Power Tech Conference Proceedings 2: 313–319.

35. Kudo M, Sklansky J (2000) Comparison of algorithms that select features for pattern classifiers. Pattern Recogn 33: 25–41.    

36. Larsen J, Goutte C (1999) On optimal data split for generalization estimation and model selection, In: Neural Networks for Signal Processing IX: Proceedings of the 1999 IEEE Signal Processing Society Workshop, 225–234.

37. Zalila Z, Cuquemelle J, Penet C, et al. (2006) Is your accurate model actually robust ? Regulation and validation methods by xtractis. Sensometrics 2006–Imagine the Senses, Norway.

38. Plutowski ME (1996) Survey : Cross-validation in theory and practise (Research Report). David Sarnoff Research Center - Princeton.

39. Shao J (1993) Linear model selection by cross-validation. J Am Stat Assoc 88: 486–494.    

© 2018 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution Licese (http://creativecommons.org/licenses/by/4.0)

Download full text in PDF

Export Citation

Article outline

Show full outline
Copyright © AIMS Press All Rights Reserved