An incremental retrieval mechanism for case-based electronic fault diagnosis

One problem with using CBR for diagnosis is that a full case description ma y not be available at the beginning of the diagnosis. The standard CBR meth odology requires a detailed case description in order to perform case retri eval and this is often not practical in diagnosis. We describe two fault di agnosis tasks where many features may make up a case description but only a few features are required in an individual diagnosis. We evaluate an incre mental CBR mechanism that can initiate case retrieval with a skeletal case description and will elicit extra discriminating information during the dia gnostic process. (C) 1998 Elsevier Science B.V. All rights reserved.