Abstract
This paper describes the industrialisation of a software system to support fault diagnosis of the CFM 56 -3 aircraft engine. The system uses data-mining techniques known as induction and case based reasoning which exploit failure descriptions that are stored in a case base. A first prototype using the induction technique applied on an initial case base has been achieved. The paper presents the main characteristics of the CBR and induction techniques. The modelling of the engine failures and the process of feeding the case base are given next. The system is intended to be used by airline maintenance staff and CFMI specialists. A user friendly environment has been implemented to allow an optimum use of the system as a troubleshooting support.
Preview
Unable to display preview. Download preview PDF.
References
Althoff, K.-D., Auriol, E., Barletta, R. & Manago, M.A Review of Industrial Case-Based Reasoning Tools. A. Goodall (Ed.), AI Intelligence, Oxford, 1995.
Auriol, E., Wess, S., Althoff, K.-D., Manago, M. & Traphöner, R.. “Inreca: A seamlessly integrated system based on inductive inference and case-based reasoning”. ICCBR 95, First International Conference on Case-Based Reasoning, Veloso M. & Aamodt A. (eds), Springer Verlag, Heidelberg, 1995.
Vingerhoeds, R.A., Janssens, P., Netten, B.D. & Fernandez-Montesinos “Enhancing off-line and on-line condition monitoring and fault diagnosis”. Control Eng. Practice, Vol 3, No. 11, pp. 1515–1528, 1995. Elsevier Science Ltd.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Heider, R. (1996). Troubleshooting CFM 56-3 engines for the Boeing 737 using CBR and data-mining. In: Smith, I., Faltings, B. (eds) Advances in Case-Based Reasoning. EWCBR 1996. Lecture Notes in Computer Science, vol 1168. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0020634
Download citation
DOI: https://doi.org/10.1007/BFb0020634
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61955-0
Online ISBN: 978-3-540-49568-0
eBook Packages: Springer Book Archive