Human-like fault diagnosis using a neural network implementation of plausibility and relevance |
| |
Authors: | Viorel?Ariton Email author" target="_blank">Vasile?PaladeEmail author |
| |
Affiliation: | (1) Danubius University, Lunca Siretului, no. 3, 800416 Galati, Romania;(2) Computing Laboratory, Oxford University, Parks Road, OX13QD Oxford, UK |
| |
Abstract: | In real systems, fault diagnosis is performed by a human diagnostician, and it encounters complex knowledge associations, both for normal and faulty behaviour of the target system. The human diagnostician relies on deep knowledge about the structure and the behaviour of the system, along with shallow knowledge on fault-to-manifestation patterns acquired from practice. This paper proposes a general approach to embed deep and shallow knowledge in neural network models for fault diagnosis by abduction, using neural sites for logical aggregation of manifestations and faults. All types of abduction problems were considered. The abduction proceeds by plausibility and relevance criteria multiply applied. The neural network implements plausibility by feed-forward links between manifestations and faults, and relevance by competition links between faults. Abduction by plausibility and relevance is also used for decision on the next best test along the diagnostic refinement. A case study on an installation in a rolling mill plant is presented. |
| |
Keywords: | Fault diagnosis Incremental diagnosis Abduction problem Neural networks Fuzzy logic |
本文献已被 SpringerLink 等数据库收录! |
|