Skip to main content
SpringerLink
Log in

Kernel-based support vector machines for automated health status assessment in monitoring sensor data

  • ORIGINAL ARTICLE
  • Published:
The International Journal of Advanced Manufacturing Technology Aims and scope Submit manuscript

Abstract

This paper presents a novel algorithm to assess the health status in monitoring sensor data using a kernel-based support vector machine (SVM) approach. Today, accurate fault prediction is a key issue raised by maintenance. In particular, automatically modelling the normal behaviour from condition monitoring data is probably one of the most challenging problems, specially when there is limited information of real faults. To overcome this difficulty, a data-driven learning framework based on nonparametric density estimation for outlier detection and ν-SVM for normality modelling, with optimal bandwidth selection, is proposed. A health score based on the log-normalisation of the distance to the separating hyperplane is also provided. Experimental results obtained when analysing the propagation of a critical fault over time in a marine diesel engine demonstrate the validity of the algorithm. The predictions of normality models learned were compared to those of the k-nearest neighbours (kNN) method. Low false positive rates on healthy data and improved prediction capacities are achieved.

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

Similar content being viewed by others

References

  1. Choudhary AK, Harding JA, Tiwari MK (2009) Data mining in manufacturing: a review based on the kind of knowledge. J Intell Manuf 20(5):501–521

    Article  Google Scholar 

  2. Vogl GW, Weiss BA, Helu M (2016) A review of diagnostic and prognostic capabilities and best practices for manufacturing. J Intell Manuf 27:1–17

    Article  Google Scholar 

  3. Kothamasu R, Huang SH, VerDuin WH (2006) System health monitoring and prognostics—a review of current paradigms and practices. Int J Adv Manuf Technol 28(9-10):1012–1024

    Article  Google Scholar 

  4. Das A, Maiti J, Banerjee R (2012) Process monitoring and fault detection strategies: a review. Int J Qual Reliab Manag 29(7): 720–752

    Article  Google Scholar 

  5. Lee S, Ng Y (2006) Hybrid case-based reasoning for on-line product fault diagnosis. Int J Adv Manuf Technol 27(7-8):833–840

    Article  Google Scholar 

  6. Krishnakumari A, Elayaperumal A, Saravanan M, Arvindan C (2017) Fault diagnostics of spur gear using decision tree and fuzzy classifier. Int J Adv Manuf Technol 89(9-12):3487–3494

    Article  Google Scholar 

  7. Banks J, Hines J, Lebold M, Campbell R, Begg C (2001) Failure modes and predictive diagnostics considerations for diesel engines. Technical report, The Pennsylvania State University Park, Applied Research Laboratory

  8. Michalski RS, Carbonell JG, Mitchell TM (2013) Machine learning: an artificial intelligence approach. Springer Science & Business Media, Berlin

    MATH  Google Scholar 

  9. Jones N, Li YH (2000) A review of condition monitoring and fault diagnosis for diesel engines. Tribotest 6(3):267–291

    Article  Google Scholar 

  10. Tidriri K, Chatti N, Verron S, Tiplica T (2016) Bridging data-driven and model-based approaches for process fault diagnosis and health monitoring: a review of researches and future challenges. Ann Rev Control 42:63–81

    Article  Google Scholar 

  11. Steinwart I, Hush DR, Scovel C (2005) A classification framework for anomaly detection. In: Journal of machine learning research, pp 211–232

  12. Greene WC (2005) Evaluation of non-intrusive monitoring for condition based maintenance applications on US Navy propulsion plants. PhD thesis, Massachusetts Institute of Technology, Department of Mechanical Engineering, USA

    Google Scholar 

  13. Barber DE (2011) Shipboard condition based maintenance and integrated power system initiatives. PhD thesis, Massachusetts Institute of Technology, USA

    Google Scholar 

  14. Krogerus TR, Hyvönen MP, Huhtala K (2016) A survey of analysis, modeling, and diagnostics of diesel fuel injection systems. Journal of Engineering for Gas Turbines and Power

  15. Kontogeorgis GM, Folas GK (2009) Thermodynamic models for industrial applications: from classical and advanced mixing rules to association theories. Wiley, USA

    Google Scholar 

  16. Han J, Pei J, Kamber M (2011) Data mining: concepts and techniques. Elsevier, Netherlands

    MATH  Google Scholar 

  17. Luger GF (2008) Artificial intelligence: structures and strategies for complex problem solving, 6th edn. Addison-Wesley Publishing Company, USA

    Google Scholar 

  18. Meerschaert MM (2013) Mathematical modeling. Academic press, Cambridge

    MATH  Google Scholar 

  19. Riera-Guasp M, Antonino-Daviu JA, Capolino GA (2015) Advances in electrical machine, power electronic, and drive condition monitoring and fault detection: state of the art. IEEE Trans Ind Electron 62(3):1746–1759

    Article  Google Scholar 

  20. Basurko OC, Uriondo Z (2015) Condition-based maintenance for medium speed diesel engines used in vessels in operation. Appl Therm Eng 80:404–412

    Article  Google Scholar 

  21. Porteiro J, Collazo J, Patiño D, Míguez JL (2011) Diesel engine condition monitoring using a multi-net neural network system with nonintrusive sensors. Appl Therm Eng 31(17):4097–4105

    Article  Google Scholar 

  22. Yan GT, Ma GF (2004) Fault diagnosis of diesel engine combustion system based on neural networks. In: Proceedings of 2004 international conference on machine learning and cybernetics, vol 5. IEEE, USA, pp 3111–3114

  23. Parlak A, Islamoglu Y, Yasar H, Egrisogut A (2006) Application of artificial neural network to predict specific fuel consumption and exhaust temperature for a diesel engine. Appl Therm Eng 26(8):824–828

    Article  Google Scholar 

  24. Li Q, Zhu L, Xu Z (2007) Fuzzy Petri-nets based fault diagnosis for mechanical-electric equipment. In: ICCA 2007. IEEE international conference on control and automation. IEEE, USA, pp 2539–2543

  25. Liu Y, Zhang J, Ma L (2016) A fault diagnosis approach for diesel engines based on self-adaptive WVD, improved FCBF and PECOC-RVM. Neurocomputing 177:600–611

    Article  Google Scholar 

  26. Shigang Z, Zheng H (2010) Diagnostic Bayesian networks auto-construction and diagnostic strategy design based on multi-signal model. In: Prognostics and health management conference, 2010. PHM’10. IEEE, USA, pp 1–5

  27. Hernández-González J, Inza I, Lozano JA (2016) Weak supervision and other non-standard classification problems: a taxonomy. Pattern Recogn Lett 69:49–55

    Article  Google Scholar 

  28. Barnett V, Lewis T et al (1994) Outliers in statistical data, vol 3. Wiley, New York

    MATH  Google Scholar 

  29. Kriegel HP, Kröger P, Zimek A (2010) Outlier detection techniques. Tutorial at KDD 10

  30. Latecki LJ, Lazarevic A, Pokrajac D (2007) Outlier detection with kernel density functions. In: Machine learning and data mining in pattern recognition. Springer, Berlin, pp 61–75

  31. Hautamaki V, Karkkainen I, Franti P (2004) Outlier detection using k-nearest neighbour graph. In: ICPR 2004. Proceedings of the 17th international conference on pattern recognition, vol 3. IEEE, USA, pp 430–433

  32. Premrudeepreechacharn S, Utthiyoung T, Kruepengkul K, Puongkaew P (2002) Induction motor fault detection and diagnosis using supervised and unsupervised neural networks. In: IEEE ICIT’02. 2002 IEEE international conference on industrial technology, vol 1. IEEE, USA, pp 93–96

  33. Tallam RM, Habetler TG, Harley RG, Gritter DJ, Burton BH (2000) Neural network based on-line stator winding turn fault detection for induction motors. In: Industry applications conference, 2000. Conference record of the 2000, vol 1. IEEE, USA, pp 375–380

  34. Vencl A, Rac A (2014) Diesel engine crankshaft journal bearings failures: case study. Eng Fail Anal 44:217–228

    Article  Google Scholar 

  35. Schölkopf B, Platt JC, Shawe-Taylor J, Smola AJ, Williamson RC (2001) Estimating the support of a high-dimensional distribution. Neural Comput 13(7):1443–1471

    Article  MATH  Google Scholar 

  36. Irigoien I, Sierra B, Arenas C (2014) Towards application of one-class classification methods to medical data. The Scientific World Journal 2014

  37. Ramaswamy S, Rastogi R, Shim K (2000) Efficient algorithms for mining outliers from large data sets. In: ACM SIGMOD record, vol 29. ACM, New York, pp 427–438

  38. Silverman BW (1986) Density estimation for statistics and data analysis, vol 26. CRC press, USA

    Book  MATH  Google Scholar 

  39. Terrell GR, Scott DW (1992) Variable kernel density estimation. Ann Stat 20(3):1236–1265

    Article  MathSciNet  MATH  Google Scholar 

  40. Scott DW (2015) Multivariate density estimation: theory, practice, and visualization. Wiley, New York

    Book  MATH  Google Scholar 

  41. Unnthorsson R, Runarsson TP, Jonsson MT (2003) Model selection in one-class ν-SVMS using RBF kernels. In: Proceedings of 16th international congress and exhibition on condition monitoring and diagnostic engineering management

  42. Munoz A, Moguerza JM (2004) One-class support vector machines and density estimation: the precise relation. In: Progress in pattern recognition, image analysis and applications. Springer, Berlin, pp 216–223

  43. Boser BE, Guyon IM, Vapnik VN (1992) A training algorithm for optimal margin classifiers. In: Proceedings of the fifth annual workshop on computational learning theory. ACM, New York, pp 144–152

  44. Hosmer Jr DW, Lemeshow S, Sturdivant RX (2013) Applied logistic regression, vol 398. Wiley, New York

    Book  MATH  Google Scholar 

  45. Altman NS (1992) An introduction to kernel and nearest-neighbour nonparametric regression. Amer Stat 46(3):175–185

    Google Scholar 

  46. Bhattacharya P, Mack Y (1987) Weak convergence of k-NN density and regression estimators with varying k and applications. Ann Stat 15(3):976–999

    Article  MathSciNet  MATH  Google Scholar 

  47. Jones E, Oliphant T, Peterson P et al (2001) SciPy: open source scientific tools for Python. http://www.scipy.org/

Download references

Acknowledgements

The author would like to thank the National ICT Australia for the great support to this work and during his internship, as part of the work on his diploma thesis.

Author information

Authors and Affiliations

  1. Tecnalia Research & Innovation, Donostia - San Sebastián, Guipúzkoa, Spain

    Alberto Diez-Olivan

  2. Navantia, Diagnose Engineering and Product Development, Diesel Engine Factory, Cartagena, Spain

    Jose A. Pagan

  3. Data61, CSIRO, 13 Garden Street, Eveleigh, NSW, 2015, Australia

    Nguyen Lu Dang Khoa

  4. Autonomous Systems Laboratory, UPM-CSIC Centre for Automation and Robotics, Universidad Politécnica de Madrid, Madrid, Spain

    Ricardo Sanz

  5. Department of Computer Sciences and Artificial Intelligence, UPV/EHU, Donostia - San Sebastián, Guipúzkoa, Spain

    Basilio Sierra

Authors
  1. Alberto Diez-Olivan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jose A. Pagan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Nguyen Lu Dang Khoa
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ricardo Sanz
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Basilio Sierra
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Alberto Diez-Olivan.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Diez-Olivan, A., Pagan, J.A., Khoa, N.L.D. et al. Kernel-based support vector machines for automated health status assessment in monitoring sensor data. Int J Adv Manuf Technol 95, 327–340 (2018). https://doi.org/10.1007/s00170-017-1204-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00170-017-1204-2

Keywords

Search

Navigation