Advertisement

Prognostic Model Development with Missing Labels

A Condition-Based Maintenance Approach Using Machine Learning
  • Patrick ZschechEmail author
  • Kai Heinrich
  • Raphael Bink
  • Janis S. Neufeld
Research Paper
  • 90 Downloads

Abstract

Condition-based maintenance (CBM) has emerged as a proactive strategy for determining the best time for maintenance activities. In this paper, a case of a milling process with imperfect maintenance at a German automotive manufacturer is considered. Its major challenge is that only data with missing labels are available, which does not provide a sufficient basis for classical prognostic maintenance models. To overcome this shortcoming, a data science study is carried out that combines several analytical methods, especially from the field of machine learning (ML). These include time-domain and time–frequency domain techniques for feature extraction, agglomerative hierarchical clustering and time series clustering for unsupervised pattern detection, as well as a recurrent neural network for prognostic model training. With the approach developed, it is possible to replace decisions that were made based on subjective criteria with data-driven decisions to increase the tool life of the milling machines. The solution can be employed beyond the presented case to similar maintenance scenarios as the basis for decision support and prognostic model development. Moreover, it helps to further close the gap between ML research and the practical implementation of CBM.

Keywords

Condition-based maintenance Predictive maintenance Prognostics Big data analytics Data science study Machine learning Unsupervised learning Missing labels 

References

  1. Aghabozorgi S, Shirkhorshidi AS, Wah TY (2015) Time-series clustering – a decade review. Inform Syst 53:16–38Google Scholar
  2. Ahmad R, Kamaruddin S (2012) An overview of time-based and condition-based maintenance in industrial application. Comput Ind Eng 63(1):135–149Google Scholar
  3. Baruah P, Chinnam RB, Filev D (2006) An autonomous diagnostics and prognostics framework for condition-based maintenance. In: International joint conference on neural networks, pp 3428–3435Google Scholar
  4. Bousdekis A, Magoutas B, Apostolou D, Mentzas G (2015) Review, analysis and synthesis of prognostic-based decision support methods for condition based maintenance. J Intell Manuf 115:1225–1250Google Scholar
  5. Breiman L (2001) Statistical modeling: the two cultures (with comments and a rejoinder by the author). Stat Sci 16(3):199–231Google Scholar
  6. Brock G, Pihur V, Datta S, Datta S (2008) clValid: an R package for cluster validation. J Stat Softw 25(4):1–22Google Scholar
  7. Bumblauskas D, Gemmill D, Igou A, Anzengruber J (2017) Smart maintenance decision support systems (SMDSS) based on corporate big data analytics. Expert Syst Appl 90:303–317Google Scholar
  8. Cartella F, Lemeire J, Dimiccoli L, Sahli H (2015) Hidden semi-markov models for predictive maintenance. Math Probl Eng 2015:278120Google Scholar
  9. Cheng GQ, Zhou BH, Li L (2018) Integrated production, quality control and condition-based maintenance for imperfect production systems. Reliab Eng Syst Safe 175:251–264Google Scholar
  10. Choudhary AK, Harding JA, Tiwari MK (2009) Data mining in manufacturing: a review based on the kind of knowledge. J Intell Manuf 20(5):501–521Google Scholar
  11. Cline B, Niculescu RS, Huffman D, Deckel B (2017) Predictive maintenance applications for machine learning. In: Reliability and maintainability symposium (RAMS), 2017 Annual. IEEE, pp 1–7Google Scholar
  12. Dickey DA, Fuller WA (1979) Distribution of the estimators for autoregressive time series with a unit root. J Am Stat Assoc 74(366):427–431Google Scholar
  13. Dragomir OE, Gouriveau R, Dragomir F, Minca E, Zerhouni N (2009) Review of prognostic problem in condition-based maintenance. In: European control conference. IEEE control systems society. Budapest, pp 1587–1592Google Scholar
  14. Elattar HM, Elminir HK, Riad AM (2016) Prognostics: a literature review. Complex Intell Syst 2(2):125–154Google Scholar
  15. Everitt BS, Landau S, Leese M, Stahl D (2011) Cluster analysis. Wiley Series in Probability and Statistics, New YorkGoogle Scholar
  16. Galar D, Kumar U, Lee J, Zhao W (2012) Remaining useful life estimation using time trajectory tracking and support vector machines. J Phys: Conf Ser 364:1–10Google Scholar
  17. Gouriveau R, Ramasso E, Zerhouni N (2013) Strategies to face imbalanced and unlabelled data in PHM applications. Chem Eng Trans 33:115–120Google Scholar
  18. Goyal D, Pabla BS (2015) Condition based maintenance of machine tools – a review. CIRP J Manuf Sci Technol 10:24–35Google Scholar
  19. Gregor S, Hevner AR (2013) Positioning and presenting design science research for maximum impact. MIS Q 37(2):337–355Google Scholar
  20. Hansen BE (2000) Sample splitting and threshold estimation. Econometrica 68(3):575–603Google Scholar
  21. Heimes FO (2008) Recurrent neural networks for remaining useful life estimation. In: International conference on prognostics and health management, pp 1–6Google Scholar
  22. Huang R, Xi L, Li X, Liu CR, Qiu H, Lee J (2007) Residual life predictions for ball bearings based on self-organizing map and back propagation neural network methods. Mech Syst Signal Process 21(1):193–207Google Scholar
  23. Jämsä-Jounela SL, Vermasvuori M, Endén P, Haavisto S (2003) A process monitoring system based on the Kohonen self-organizing maps. Control Eng Pract 11(1):83–92Google Scholar
  24. Jardine AK, Lin D, Banjevic D (2006) A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mech Syst Signal Process 20(7):1483–1510Google Scholar
  25. Khawaja T, Vachtsevanos G, Wu B (2005) Reasoning about uncertainty in prognosis: a confidence prediction neural network approach. In: Annual meeting of the north american fuzzy information processing society, pp 7–12Google Scholar
  26. Kurgan LA, Musilek P (2006) A survey of knowledge discovery and data mining process models. Know Eng Rev 21(1):1–24Google Scholar
  27. Leturiondo U, Salgado O, Ciani L, Galar D, Catelani M (2017) Architecture for hybrid modelling and its application to diagnosis and prognosis with missing data. Measurement 108:152–162Google Scholar
  28. Manyika J, Chui M, Brown B, Bughin J, Dobbs R, Roxburgh C, Byers AH (2011) Big data: the next frontier for innovation, competition, and productivity. Technical Report McKinsey Global InstituteGoogle Scholar
  29. Meeker WQ, Hong Y (2014) Reliability meets big data: opportunities and challenges. Qual Eng 26(1):102–116Google Scholar
  30. Muchiri P, Pintelon L, Gelders L, Martin H (2011) Development of maintenance function performance measurement framework and indicators. Int J Prod Econ 131(1):295–302Google Scholar
  31. Pan Y, Er MJ, Li X, Yu H, Gouriveau R (2014) Machine health condition prediction via online dynamic fuzzy neural networks. Eng Appl Artif Intel 35:105–113Google Scholar
  32. Peng Y, Dong M, Zuo MJ (2010) Current status of machine prognostics in condition-based maintenance: a review. Int J Adv Manuf Tech 50(1):297–313Google Scholar
  33. Ramasso E, Saxena A (2014) Performance benchmarking and analysis of prognostic methods for CMAPSS datasets. Int J Progn Health Manag 5(2):1–15Google Scholar
  34. Rinaldo A, Wasserman L, G’Sell M, Lei J (2016) Bootstrapping and sample splitting for high-dimensional, assumption-free inference. ArXiv Preprint: arxiv:1611.05401
  35. Saxena A, Goebel K (2008) C-MAPSS data set. NASA Ames Prognostics Data RepositoryGoogle Scholar
  36. Shmueli G, Koppius OR (2011) Predictive analytics in information systems research. MIS Q35(3):553–572Google Scholar
  37. Si XS, Wang W, Hu CH, Zhou DH (2011) Remaining useful life estimation – a review on the statistical data driven approaches. Eur J Oper Res 213(1):1–14Google Scholar
  38. Sneath PHA, Sokal RR (1973) Numerical taxonomy. The Principles and Practice of Numerical Classification. Freeman, San FranciscoGoogle Scholar
  39. Susto GA, Schirru A, Pampuri S, McLoone S, Beghi A (2015) Machine learning for predictive maintenance: a multiple classifier approach. IEEE Trans Ind Inform 11(3):812–820Google Scholar
  40. Tian Z, Wong L, Safaei N (2010) A neural network approach for remaining useful life prediction utilizing both failure and suspension histories. Mech Syst Signal Process 24(5):1542–1555Google Scholar
  41. Ullah I, Yang F, Khan R, Liu L, Yang H, Gao B, Sun K (2017) Predictive maintenance of power substation equipment by infrared thermography using a machine-learning approach. Energy 10(12):1–13Google Scholar
  42. Van der Laan M, Pollard K, Bryan J (2003) A new partitioning around medoids algorithm. J Stat Comput Simul 73(8):575–584Google Scholar
  43. Vapnik VN (1999) An overview of statistical learning theory. IEEE Trans Neural Netw 10(5):988–999Google Scholar
  44. Veldman J, Wortmann H, Klingenberg W (2011) Typology of condition based maintenance. J Qual Maint Eng 17(2):183–202Google Scholar
  45. Vogl GW, Weiss BA, Helu M (2016) A review of diagnostic and prognostic capabilities and best practices for manufacturing. J Intell Manuf pp 1–17Google Scholar
  46. Wang W, Christer AH (2000) Towards a general condition based maintenance model for a stochastic dynamic system. J Oper Res Soc 51(2):145–155Google Scholar
  47. Williams RJ (1995) Adaptive state representation and estimation using recurrent connectionist networks. In: Miller WT, Sutton RS, Werbos PJ (eds) Neural networks for control. MIT Press, Cambridge, pp 97–114Google Scholar
  48. Yuan J, Liu X (2013) Semi-supervised learning and condition fusion for fault diagnosis. Mech Syst Signal Process 38(2):615–627Google Scholar
  49. Zhao X, Li M, Xu J, Song G (2011) An effective procedure exploiting unlabeled data to build monitoring system. Expert Syst Appl 38(8):10199–10204Google Scholar
  50. Zschech P (2018) A taxonomy of recurring data analysis problems in maintenance analytics. In: Proceedings of the 26th European conference on information systemsGoogle Scholar

Copyright information

© Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature 2019

Authors and Affiliations

  • Patrick Zschech
    • 1
    Email author
  • Kai Heinrich
    • 1
  • Raphael Bink
    • 2
  • Janis S. Neufeld
    • 3
  1. 1.Lehrstuhl für WirtschaftsinformatikBusiness Intelligence Research, TU DresdenDresdenGermany
  2. 2.Herzogenrath R&D CentreSaint-GobainHerzogenrathGermany
  3. 3.Lehrstuhl für BWL, Industrielles ManagementTU DresdenDresdenGermany

Personalised recommendations