Case-Based Reasoning in
an Ultrasonic Rail-Inspection System

Jacek Jarmulak1,2, Eugene J.H. Kerckhoffs, Peter Paul vant Veen2

1 Deift University of Technology, Faculty of Technical Mathematics & Informatics,
P.O. Box 356, 2600 AJ Delft, The Netherlands,
2TNO Institute of Applied Physics,

P.O. Box 155, 2600 AD Delft, The Netherlands,
jarmulak@tpd.tno.nl


Abstract: Non-destructive testing (NDT) is often used for petiodical inspection of infrastructure 
(e.g. railroads, pipelines). The inspection results in huge amounts of data
which usually has to be analysed by an operator (or a team of operators) for occurrence 
of defect indications. This paper presents an example of use of case-based reasoning 
in interpretation of data from non-destructive testing, namely, a prototype for
classification of images from an ultrasonic rail-inspection system. The reasons for the
choice of case-based reasoning instead of statistical classification or a rule-based expert-system 
approach are explained. The overall design of the prototype is described
and observations and conclusions relating to the prototype and generally to the use of
CBR for NDT are presented.


References
Giarratano,J. and Riley G. (1989): Expert Sy stems: Principles and Programming, PWS-KENT, Boston
Hopgood, F.F., Woodcock, N., Hallam, N.J. and Picton, P.D. (1993): Interpreting ultrasonic images 
using rules, algorithms and neural networks, European Jonrnal of NDT, Vol. 2, No. 4, pp.
135-149.
Jarmulak, J. (1996): B-scan Image clustering and Interpretation in Ultrasonic Rail-Inspection System, 
in ASCI96 Proceedings of the second annual conference of the Advanced Schoolfor Computing and Imaging, 
Lommel, Belgium, June 5-7, 1996, Kerckhoffs, E.J.H., Sloot, P.M.A, Tonino, J.F.M. and
Vossepoel, A.M. (eds.), ASCI, Delft, pp. 190-1 95.
Mark, W., Simoudis, E. and Hinkle, D. (1996): Case-Based Reasoning: Expectations and Results, in
Case-Based Reasoning: Experiences, Lessons & Future Directions, Leake D.B. (ed.), MIT Press, Cambridge, 
MA, pp. 269-294.
Pemer, P. (1993): Case-Based Reasoning for Image Interpretation in Non-Destructive Testing, in
Proceedings of the First European Workshop on Case-Based Reasoning EWCBR-93, University of Kaiserslautern, 
Germany, pp. 403-409.
Roos,J. (1990): Het ultrasoon railinspectie systeem, NAG Journal, Nr. 105, Nov., pp. 21-34
Sarle, W.S. (1994): Neural Networks and Statistical Models, in Proceedings of the Nineteenth Annual
SAS Users Group International Conference, April 1994.
Surma, J. and Vanhoof, K. (1995): Integrating Rules and Cases for the Classification Task, in Proceedings 
of the First International Conference on Case-Based Reasoning ICCBR-95, Portugal, pp. 325-334
Udpa, L. and Udpa. S.S. (1991): Neural networks for the classification of nondestructive evaluation
signals, lEE Proceedings-F, Vol. 138, No. 1, February, pp. 41-45.
