Skip to main content
SpringerLink
Log in

Data mining-based methods for fault isolation with validated FMEA model ranking

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

FMEA (Failure Mode and Effects Analysis), which was developed to enhance the reliability of complex systems, is a standard method to characterize and document product and process problems and a systematic method for fault identification/isolation in maintenance. When a failure is predicted or detected, it is expected to identify which component is the root cause or to isolate the fault to a specific contributing component. To efficiently perform fault isolation, we proposed data mining-based methods for fault isolation by using the validated FMEA information to rank data-driven models. However, FMEA, as a standard document, is produced during the design of products or systems. Therefore, FMEA documentation is rarely validated or updated in practice after it was generated. In order to use reliable FMEA information to rank models for fault isolation, it is necessary to validate FMEA before using it. In this paper, we first present brief overview of FMEA validation. Then we introduce the proposed data mining based method for fault isolation. Finally we apply the proposed methods to Auxiliary Power Unit (APU) fault isolation for a given failure mode, “Inability to Start”, by conducting large-scale experiments. The experimental results obtained from a case study demonstrate the usefulness and feasibility of the proposed methods for fault isolation.

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

Similar content being viewed by others

References

  1. Chen HC Failure Modes and Effects Analysis Training Manual, Personal Communication, Hen Technology Inc, USA

  2. Zaluski M, Japkowicz N, Matwin S (2003) Case authoring from text and historical experiences. In: Proceedings of the sixteenth canadian conference on artificial intelligence (AI2003)

  3. Genovesi A, Harmand J, Steyer J-P (2000) Integrated fault detection and isolation: Application tyo a Winery’s wasterwater treat,emt plant. Appl Intell 13(1):59–76

    Article  Google Scholar 

  4. Bahrampour S, Moshiri B, Salahshoor K (2011) Weighted and constrained possibilistic C-means clustering for online fault detection and isolation. Appl Intell 35(2):269–284

    Article  Google Scholar 

  5. Cholette ME, Liu J, Djurdjanovic D, Marko KA (2012) Monitoring of complex systems of interacting dynamic systems. Appl Intell 37(1):60–79

    Article  Google Scholar 

  6. Mengshoel O, et al. (Sep. 2010) Probabilistic model-based diagnosis: An electrical power system case study. IEEE Trans Syst Man Cybern A Syst Humans 40(5):874–885

  7. Yang C, Létourneau S, Zaluski M, Scarlett E (2010) APU FMEA validation and its application to fault identification. In: Proceedings of the ASME 2010 international design engineering technical conference & computer and information in engineering conference, IDETC/CIE 2010, Montreal, Canada

  8. Yang C, Létourneau S, Scarlett E, Zaluski M (2009) APU FMEA validation using operation and maintenance data. In: Proceedings of the annual conference of the prognostics and health management society, San Diego, CA, USA

  9. Sellappan N, Sivasubramanian R (February 2008) Modified method for evaluation of risk priority number in design FMEA. Icfai J Oper Manag 7(1):43–52

  10. Létourneau S, Yang C, Drummond C, Scarlett E, Valdes J, Zaluski M (April 2005) A domain independent data mining methodology for prognostics. In: Proceedings of the 59th meeting of the society for machine failure prevention technology, MFPT ’05, Virginia Beach, Virginia, USA

  11. Yang C, Létourneau S (2005) Learning to predict train wheel failures. In: Proceedings of the 11th ACM SIGKDD international conference on knowledge discovery and data mining (KDD2005), Chicago, USA, pp 516–525

  12. Létourneau S, Famili A F, Matwin S (1999) Data mining for prediction of aircraft component replacement. IEEE Intell Syst Appl 14(6):59–66

    Article  Google Scholar 

  13. Hall M (A 2000) Correlation-based feature selection for discrete and numeric class machine learning. In: Proceedings of the 17th international conference on machine learning, pp 359–366

  14. Kira K, Rendell (1992) A practical approach to feature selection. In: Proceedings of the 9th international conference on machine learning, pp 249–256

  15. Yang C, Létourneau S (2009) Two-stage classifications for improving time-to-failure estimates: A case study in prognostic of train wheels. Int J Appl Intell 31(3):255–266

    Article  MATH  Google Scholar 

  16. Japkowicz N, Shah M (2011) Evaluation of learning algorithms, a classification perspective. Cambridge University Press

  17. Provost F, Fawcett T (1997) Analysis and visualization of classifier performance: Combination under imprecise class and cost distributions. In: Proceedings of international conference on knowledge discovery and data mining (KDD1997)

  18. Fawcett T (2003) ROC Graphs: Notes and practical considerations for data mining researchers, Technical report, Intelligent Enterprise Technologies Laboratory, HP

  19. Flach P The Many Faces of ROC Analysis in Machine Learning, ICML’04 tutorial. http://www.cs.bris.ac.uk/%7Eflach/ICML04tutorial/

  20. Flach P The Geometry of ROC space: Understanding machine learning metrics through ROC isometrics

  21. Bradley A (1997) The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recogn 30:1145–1159

    Article  Google Scholar 

  22. Huang J, Ling C (2005) Using AUC and accuracy in evaluating learning algorithms. IEEE Trans Knowl Data Eng 17(3):299–310

    Article  Google Scholar 

  23. Drummond C, Holte R (2004) What ROC curve can’t do (and cost curve can),. In: ECAI workshop on ROC analysis in artificial intelligence

  24. Zheng Z, Padmanabhan B, et al. (2004) A DEA approach for model combination

  25. Caruana R, Niculescu-Mizil A (2006) An empirical comparison of supervised learning algorithms. In: Proceedings of the 23rd international conference on machine learning (ICML2006)

  26. Caruana R, Niculescu-Mizil A (2004) Data mining in metric space: An empirical analysis of supervised learning performance criteria. In: Proceedings of the 10th ACM SIGKDD international conference on knowledge discovery and data mining (KDD2004), Seattle, Washington, USA, pp 69–78

  27. Yang C, Zou Y, Liu J, Mulligan KR (2014) Predictive model evaluation for PHM. Int J Prognostics Health Manag 5(2)

  28. Elkan C (2001) The foundations of cost-sensitive learning. Proceedings of the 7th international joint conference on artificial intelligence (IJCAI 2001), Seattle, USA

Download references

Acknowledgments

Many people at the National Research Council Canada have contributed to this work. Special thanks go to Xijia Wu for providing the FMEA documents and to Marvin, Zaluski, Elizabeth Scarlett, and Jeff Bird for their support and valuable insights. This work is supported by the Natural Science Foundation of China (Grant No.61463031) and External Science and Technology Cooperation Project of Jiangxi Province of China(No.20151BDH80010).

Author information

Authors and Affiliations

  1. National Research Council Canada, Ottawa, Ontario, Canada

    Chunsheng Yang

  2. Jiujiang University, Jiangxi, China

    Yanni Zou

  3. Nanchang University, Nanchang, China

    Pinhua Lai

  4. East Chine Jiao Tong University, Nanchang, China

    Nan Jiang

Authors
  1. Chunsheng Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yanni Zou
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Pinhua Lai
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Nan Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Chunsheng Yang.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yang, C., Zou, Y., Lai, P. et al. Data mining-based methods for fault isolation with validated FMEA model ranking. Appl Intell 43, 913–923 (2015). https://doi.org/10.1007/s10489-015-0674-x

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-015-0674-x

Keywords

Search

Navigation