Take a look at the new version of this page: [ beta version ]. Tell us what you think.

ABSTRACT

This article presents an aid system for the setting of non-destructive testing instruments. Some problems inherent in this field are briefly discussed, before showing how they led us to introduce machine learning techniques into the system. The approach uses learning from examples. The goal of the learning module is to determine dependencies between parameters of different experiments in order to automatically generate a set of rules. A prototype, called MANDRIN, has been implemented and is being evaluated on a real application: an x-ray tomograph. The first results are presented in the last section.

REFERENCES

• Elli-88: Ellingson, WA and Vannier MW, "X-ray computed tomography for non-destructive evaluation of advanced structural ceramics", Report of Argonne National Laboratory, July 1988
• Gana-87: Ganascia, JG, "AGAPE et CHARADE: deux techniques d'apprentissage symbolique appliqu6es it la construction de bases de connaissances", Thdse d'dtat, Universit6 de Paris-sud, Orsay, 1987
• Glas-89: Glasser, F, Thomas, G, Gagelin, JJ and Cuzin, M, "Detection of high-energy pulsed xrays for industrial tomography", ASNT Conf. on Industrial Computerized Tomography, Seattle USA, July 1989, pp 54-58
• Jose-81: Joseph, PM, "Artifacts in Computed Tomography", Radiology of the skull and brain Technical aspects of Computed Tomography, vol.5, 1981, pp 3956-3992
• Mart-89: Martz, HE, Skeate, MF, Schneberk, DJ and Azevedo, SG, "Design, Performance and application of a CCD camera-based CT system", ASNT Conf. on Industrial Computerized Tomography, Seattle USA, july 1989, pp 34-38
• Melt-87: R. B. Melton, Knowledge based systems in nondestructive evaluation(a), Proceedings of a NATO Advanced Research Workshop held within the activities of the NATO Special Programme on Sensory Systems for Robotic Control on Signal processing and pattern recognition in nondestructive evaluation of materials, p.199-204, June 1988, Lac Beauport, Quebec, Canada
• Mich-83a: S Ryszard Michalski , G Jaime Carbonell , M Tom Mitchell, Machine learning an artificial intelligence approach volume II, Morgan Kaufmann Publishers Inc., San Francisco, CA, 1986
• Mich-83b: Michalski, RS, "A Theory and a Methodology of Inductive Learning", in Artificial Intelligence, 20, 1983, pp 111-161
• Mich-86: S Ryszard Michalski , G Jaime Carbonell , M Tom Mitchell, Machine learning an artificial intelligence approach volume II, Morgan Kaufmann Publishers Inc., San Francisco, CA, 1986
• Oost-88: Gerhard Deon Oosthuizen, The use of a lattice in knowledge processing, University of Strathclyde, Glasgow, Scotland, UK, 1992
• Quin-86: J. R. Quinlan, Induction of Decision Trees, Machine Learning, v.1 n.1, p.81-106 [doi>10.1023/A:1022643204877]
• Quin-87: Quinlan, JR, "Generating Production Rules from Decision Trees", in Proc. of the tenth Int. Joint Conf. on Artificial Intelligence, Milan, Aofit 1987, pp 304-307
• Rizo-89: Rizo, P and Grangeat, P, "Development of a 3D cone beam tomographic system for NDT of ceramics", ASNT Conf. on industrial Computerized Tomography, Seattle USA, July 1989, pp 24-28
• Roye-90: Royer, JC, "MANDRiN : un syst~me d'aide au r6glag~ d'un instrument complexe", Ph.D., INPG, Grenoble, 1990 (in preparation)
• Sain-89: de Sainte Marie, C, "D6pendance Per~ue- Une Introduction", 7~ Congrds Reconnaissance des Formes et Intelligence Artificielle, Paris, D6c. 1989

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.6 Learning
          Subjects: Knowledge acquisition

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.1 Applications and Expert Systems
          Subjects: Industrial automation
      I.2.4 Knowledge Representation Formalisms and Methods
          Subjects: Representations (procedural and rule-based)

General Terms:
Algorithms