Journal of Failure Analysis and Prevention

, Volume 8, Issue 2, pp 199–206 | Cite as

An Instance-Based Method for Remaining Useful Life Estimation for Aircraft Engines

  • Feng Xue
  • Piero Bonissone
  • Anil Varma
  • Weizhong Yan
  • Neil Eklund
  • Kai Goebel
Technical Article---Peer-Reviewed


Under customer service agreements (CSA), engine operational data are collected and stored for monitoring and analysis. Other data sources provide damage assessments that are either provided post-maintenance or analytically assessed. This paper takes advantage of these data and investigates local fuzzy models to determine the remaining useful life (RUL) of an engine or engine component. Local fuzzy models are related to both kernel regressions and locally weighted learning. The particular local models described in this paper are not based on individual models that consider the track history of a specific engine nor are they based on a global average model that would consider the collective track history of all the engines. Instead, for a given engine or component, this local fuzzy model defines a cluster of peers in which each of these peers is a similar instance to this given engine with comparable operational characteristics; the RUL prediction for this given engine is obtained by a fuzzy aggregation of its peers’ RUL. We combine the fuzzy instance-based approach with an evolutionary framework for model tuning and maintenance. This evolutionary tuning process is repeated periodically to automatically update and improve the fuzzy models such that they can be updated to date with the latest collection of data. This fuzzy instance-based approach is applied to predicting the RUL of a commercial engine validated with post-maintenance assessment.


Evolutionary algorithm Fuzzy Instance-based Life-cycle Prognosis Remaining useful life (RUL) 


  1. 1.
    Bonissone, P., Goebel, K.: When will it break? A hybrid soft computing model to predict time-to break margins in paper machines. Proceedings of SPIE 47th Annual Meeting, International Symposium on Optical Science and Technology, vol. #4787, pp. 53–64 (2002)Google Scholar
  2. 2.
    Goebel, K.F., Bonissone, P.P.: Prognostic information fusion for constant load systems. Proceedings of the 7th Annual Conference on Information Fusion (2005)Google Scholar
  3. 3.
    Goebel, K.F., Bonanni, P., Eklund, N.E.: Towards an integrated reasoner for bearings prognostics. Proceedings of 2005 IEEE Aerospace Conference, pp. 1–11 (2005)Google Scholar
  4. 4.
    Goebel, K.F., Eklund, N.E., Bonanni, P.: Fusing competing prediction algorithms for prognostics. Proceedings of 2006 IEEE Aerospace Conference, 11.1004 (2006)Google Scholar
  5. 5.
    Bonissone, P.P., Varma, A.: Predicting the best units within a fleet: prognostic capabilities enabled by peer learning, fuzzy similarity, and evolutionary design process. Proceedings of the FUZZ-IEEE 2005, Reno NV, USA, May 22–25 (2005)Google Scholar
  6. 6.
    Bonissone, P., Varma, A., Aggour, K., Xue, F.: Design of local fuzzy models using evolutionary algorithms. Comput. Stat. Data Anal. 51, 398–416 (2006)CrossRefGoogle Scholar
  7. 7.
    Bonissone, P.: The life cycle of a fuzzy knowledge-based classifier. Proceedings of 2003 North American Fuzzy Information Processing Society. Chicago, IL (2003)Google Scholar
  8. 8.
    Atkeson, C.G.: Memory-based approaches to approximating continuous functions, In: Casdagli, M., Eubank, S. (eds.), Nonlinear Modeling and Forecasting. Addison Wesley, Harlow, UK, pp. 503–521 (1992)Google Scholar
  9. 9.
    Atkeson, C.G., Moore, A., Schaal, S.: Locally weighted learning. Artif. Intell. Rev. 11(1–5), 11–73 (1997)CrossRefGoogle Scholar
  10. 10.
    Bersini, B., Bontempi, G., Birattari, M.: Is readability compatible with accuracy? From neuro-fuzzy to lazy learning. In: Freksa, C. (ed.) Proceedings in Artificial Intelligence 7, Infix/Aka, Berlin, Germany, pp. 10–25 (1998)Google Scholar
  11. 11.
    Stom, R., Price, K.: Differential Evolution: A Simple and Efficient Adaptive Scheme for Global Optimization Over Continuous Spaces. Technical Report TR-95–012, International Computer Science Institute, Berkeley (1995)Google Scholar
  12. 12.
    Xue, F., Sanderson, A.C., Graves, R.J.: Pareto-based multi-objective differential evolution. Proceedings of IEEE Congress on Evolutionary Computation, pp. 862–869 (2003)Google Scholar

Copyright information

© Society for Machinery Failure Prevention Technology 2007

Authors and Affiliations

  • Feng Xue
    • 1
  • Piero Bonissone
    • 1
  • Anil Varma
    • 1
  • Weizhong Yan
    • 1
  • Neil Eklund
    • 1
  • Kai Goebel
    • 2
  1. 1.GE Global Research One Research Circle NiskayunaUSA
  2. 2.RIACS, NASA Ames Research CenterMoffett FieldUSA

Personalised recommendations