A Methodology to Conceive A Case Based System Of Industrial Diagnosis

Abstract

The objective of this paper is to address the diagnosis knowledge-oriented system in terms of artificial intelligence, particular by the Case-Based Reasoning (CBR) approach. Indeed, the use of CBR, which is an approach to problem solving and learning, in diagnosis goes back to a long time with the appearance of diagnostic support systems based on CBR. A diagnostic system by CBR implements an expertise-base composed of past experiences through which the origins of failure and the maintenance strategy are given according to a description of a specific situation of diagnostic. A study is made on the different diagnostic systems based on CBR. This study showed that there was no common methodology for building a CBR system. This design depends primarily on the case representation and knowledge models of the domain application. Consequently, this paper proposes a general design approach of a diagnostic system based on the CBR approach.