Abstract
The theory of a feature extraction method, called correspondence analysis, is given. It is applied to learning datas made of all available informations about a given type of equipment, as stored in a reliability and maintenance data bank.
Correspondence analysis is a variant of principal component analysis, based upon a CHI-square distributional metric wherein patterns and observations play symmetrical roles. A simultaneous graphical representation of both patterns and observations helps in analyzing the operational behaviour of the equipment for design review and maintenance control; two examples hereof are given for an airborne equipment, and for resistor components.
Real time diagnosis and fault localization have been achieved, thanks to a real time data compression into the reduced feature space generated by correspondence analysis, and by a sequential recognition procedure. This procedure is the generalized nearest neighbour rule, applied sequentially to learning sets of increasing size; the stopping rule uses a compromise between recognition time and the misclassification probability. An example of automated real time testing is given, showing a 92% true recognition rate for acceptable items produced by machine-tools, and a mean correct diagnosis rate of 81% for non-accepted items. 16 references.
This paper is part of a course in Technical Diagnosis at the Ecole Nationale Supérieure de l’Aéronautique et de l’Espace, France.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Becker, P.W. Recognition of patterns, Copenhagen, Denmark, Polyteknisk Forlag, 1968.
Benzecri, J.P. Statistical analysis as a tool to make patterns emerge from data. Proc., 1968 Honolulu Conf. on pattern recognition, Academic Press, 1969.
Cortina, E., Engel, H.L., and Scott, W.K. Pattern recognition techniques applied to diagnostics. SAE rep. 7000407, Midyear meeting, Detroit, Michigan, 18–22/5/1970.
Goarin, R. Application de l’analyse des correspondances à l’étude de la fiabilité des composants électroniques, Congrès national de fiabilité, Perros-Guirec, September 1972.
Hankley, W.J., and Merrill, H.M. A pattern recognition technique for system error analysis, IEEE Trans. on reliability, Vol. R-20, No. 3, August 1971.
Kulikowsky, C.A. Pattern recognition approach to medical diagnosis, IEEE Trans. Systems Science & Cybernetics, Vol. SSC-6, No. 3, July 1970.
Loftsgaarden, D.O., and Quesenbury, C.P. A non-parametric estimate of a multi-variate density function, Ann. Math. Statist., 36, 1965, 1049–1151.
Page, J. Recognition of patterns in jet engine vibration signals, IEEE Publ., No. 16 c 51, 102–105.
Pau, L.F. Diagnostic statistique; synthèse des informations relatives à la fiabilité et à la maintenance d’un matériel aéronautique, L’Aéronautique et l’Astronautique, No. 34, 1972–2.
Pau, L.F. Méthodes statistiques de réduction et de reconnaissance des formes, dr. thesis, Paris University, 1972.
Pau, L.F. Sequential pattern recognition methods applied to technical diagnosis and maintenance, IMSOR, Technical University of Denmark, 1972.
Pau, L.F. Statistical reduction and recognition of speech patterns, in: Machine perception of patterns and pictures, book, published by the Institute of Physics, London, as Conference series No. 13, 1972.
Pokrowsky, F.N. On reliability prediction by pattern classification, Proc. 1972 Annual reliability and maintenability symposium, San Francisco, Annals of Assurance sciences, IEEE Catalog 72CH0577–7R, 367–375.
Tukey, J.W. Non-parametric estimation, II: statistical equivalent blocks and tolerance regions, Ann. Math. Statist., 18, 1947, 529–539.
Watanabe, S., and Lampert, P.F. Evaluation and selection of variables in pattern recognition, in: Computers and information sciences, Vol. 2, N.Y., Academic Press, 1967, 91–122.
Young, H.W. Specifying the interface between design and test organizations, Inst. of electronic and radio engs., Conf. on automatic test systems, Proc. April 1970.
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1973 Springer-Verlag Berlin · Heidelberg
About this paper
Cite this paper
Pau, L.F. (1973). Applications of Pattern Recognition to the Diagnosis of Equipment Failures. In: Einsele, T., Giloi, W., Nagel, HH. (eds) NTG/GI Gesellschaft für Informatik Nachrichtentechnische Gesellschaft Fachtagung „Cognitive Verfahren und Systeme“. Lecture Notes in Economics and Mathematical Systems, vol 83. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-80749-7_17
Download citation
DOI: https://doi.org/10.1007/978-3-642-80749-7_17
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-06268-4
Online ISBN: 978-3-642-80749-7
eBook Packages: Springer Book Archive