COMBINED DEEP AND SHALLOW KNOWLEDGE IN A UNIFIED MODEL FOR DIAGNOSIS BY ABDUCTION

Abstract

Fault Diagnosis in real systems usually involves human expert’s shallow knowledge (as pattern causeseffects)but also deep knowledge (as structural / functional modularization and models on behavior). The paperproposes a unified approach on diagnosis by abduction based on plausibility and relevance criteria multipleapplied, in a connectionist implementation. Then, it focuses elicitation of deep knowledge on target conductiveflow systems – most encountered in industry and not only, in the aim of fault diagnosis. Finally, the paper giveshints on design and building of diagnosis system by abduction, embedding deep and shallow knowledge(according to case) and performing hierarchical fault isolation, along with a case study on a hydraulicinstallation in a rolling mill plant.