Early expert systems for fault analysis tended to be based on shallow, heuristic knowledge. For success in engineering applications, it is argued that the complementary knowledge of the underlying principles (deep knowledge) should also be modelled. An object-oriented software library representing models of components of hydraulic circuits is being built using deep knowledge alone. The software modules within this library are reusable for the construction of model-based expert systems for the performance of failure mode and effects analysis and fault tree analysis on any arbitrary hydraulic circuit.
Get full access to this article
View all access options for this article.
References
1.
HoganP. A.BurrowsC. R.EdgeK. A.WoollonsD. J.AtkinsonR. M.MontakhabM. R.Automated fault analysis for hydraulic systems: Part 2. Applications. Proc. Instn Mech. Engrs, Part I, 1992, 206(I4), this issue.
2.
BridsonD. W.AtkinsonR. M.WoollonsD. J.The use of expert systems in advanced condition monitoring, Proceedings of IMechE Seminar on Mechanical condition monitoring, 1990.
MalinJ. T.LanceN.Processes in construction of failure management expert systems from device design information. IEEE Trans. Systems, Man Cybernetics, 1987, SMC-17(6), 956–967.
5.
PriceC. J.LeeM. H.Applications of deep knowledge. Artificial intelligence in Engineering, 1988, 3(1), 12–17.
6.
LeeM. H.HuntJ. E.PriceC. J.LongF. W.Repair: a model-based diagnosis system. UK-IT-90, 1990, pp. 266–270 (Institution of Electrical Engineers).
7.
HuntJ. E.PriceC. J.Towards a generic qualitative based diagnostic architecture. Proceedings of 9th International Workshop on Expert systems and their applications, 1989, pp. 253–268.
8.
HuntJ. E.PriceC. J.An augmented model based diagnostic system exploiting diagnostic and domain knowledge. Research and Development in Expert Systems 8, (Eds GrahamMilne), 1991 (Cambridge University Press).
9.
TelloE. R.Object-oriented programming for artificial intelligence, 1989, Addison-Wesley).
10.
TelloE. R.DIPOLE: An AI architecture suitable for space applications. Proceedings IEEE Conference on Expert systems in government, 1986.
11.
FinkP. K.LusthJ. C.A second generation expert system for diagnosis and repair of mechanical and electrical devices. SAE AI SP-664, International Congress and Exposition, 1986, pp. 27–35, Detroit, Michigan, USA.
12.
KulpersB.Qualitative reasoning with causal models in diagnosis of complex systems. In Artificial intelligence simulation and modelling, WidmanL. E.), 1989, pp. 257–273 (Wiley).
13.
DavisR.Diagnostic reasoning based on structure and behaviour. Artificial Intelligence, 1984, 24, 347–410.
14.
GeneserethM. R.The use of design descriptions in automated diagnosis. Artificial Intelligence, 1984, 24, 411–436.
15.
GranthamS. D.UngarL. H.Qualitative physics. In Formal techniques in artificial intelligence, BanerjiR. B.), 1990, pp. 77–121 (North Holland).
16.
PayneE. C.McArthurR. C.Developing expert systems: a knowledge engineer's handbook for rules and objects, 1990, Wiley).
17.
HamiltonT. P.SimmonsD. W.HELIX: an engine monitoring system. Proceedings of 41st Meeting of Mechanical Failures Prevention Group, Naval Air Test Center, Maryland, USA, 1986.
18.
SteelsL.Diagnosis with a function fault model: Causal AI models, HornW.), 1990, pp. 129–153 (Hemisphere).
19.
WoollonsD. J.AtkinsonR. M.PillayK. D. A.BurrowsC. R.HoganP. A.EdgeK. A.Fault diagnosis for condition monitoring applied to hydraulic circuits. IMechE Congress Aerotech 92, Seminar C428/12, 1992 (Mechanical Engineering Publications, London).
20.
HuntJ. E.A task specific integration architecture for multiple problem solver, model-based, diagnostic expert systems. PhD thesis, University College of Wales, 1991.
21.
PriceC. J.HuntJ. E.Automating FMEA through multiple models. Proceedings of BCS Expert Systems Conference, 1991, Cambridge University Press).
22.
WoodC. L.FADES: A tool for automated fault analysis of complex systems. Research and Development in Expert Systems 89, 1989, pp. 253–262 (Cambridge University Press).
23.
TzafestasS. G.System fault diagnosis using the knowledge based methodology. In Fault diagnosis in dynamic systems, PattonR.). 1989, pp. 509–572 (Prentice Hall).
