A Sophisticated Expert System for the Diagnosis of a CNC Machining Center

Klaus-Dieter Althoff, Klaus Nökel, Robert Rehbold, Michael M. Richter

In: Zeitschrift für Operations Research (ZOR) 32 Seiten 251-269 Physica Heidelberg 1988.


As the domains of diaqnostic expert systems become larger and more complex, purely associative approaches are no longer adequate solutions. A good example for such a situation is the diagnosis of a CNC machining center where the diagnostic process has a rich inner structure that has to be reflected in the system. In this article we describe three ways of extending the conventional expert system architecture. Firstly, our system uses a structural model of the machining center in addition to production rules. Secondly, we pay special attention to knowledge acquisition which is intimately related to the learning process. Finally, several temporal aspects of the diagnostic situation are addressed explicitly.

diagnosis_gesamt.pdf (pdf, 597 KB )

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence