Inscriere cercetatori

Daca aveti cont Ad Astra si de Facebook, intrati pe pagina de profil pentru a da dreptul sa va logati pe site doar cu acest buton.

Site nou !

Daca nu va puteti recupera parola (sau aveti alte probleme), scrieti-ne la pagina de contact. Situl vechi se gaseste la adresa


Human-like fault diagnosis using a neural network implementation of plausibility and relevance

Domenii publicaţii > Ştiinţe informatice + Tipuri publicaţii > Articol în revistã ştiinţificã

Autori: Viorel Ariton, Vasile Palade

Editorial: Springer-Verlag London Ltd., Neural Computing & Applications, Volume 14, Number 2, p.149 - 165, 2005.


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.

Cuvinte cheie: retele neuronale artificiale, aplicatii // neural networks, applications