This paper argues that knowledge-based systems are an appropriate tool for the diagnosis of faults in complex devices and that both deep and shallow knowledge have their part to play in this process. The successful implementation and evaluation of the two diagnostic knowledge-based systems, named DIPLOMA and MIDAS, have shown that such systems are an appropriate tool for the diagnosis of faults in complex hydromechanical devices and that they make a beneficial contribution to the business performance of the host organization. Furthermore, it has been demonstrated that the most effective and comprehensive knowledge-based approach to fault diagnosis is one that incorporates both deep and shallow knowledge, so that the distinctive advantages of each can be realized in a single application.
HoldenP.Expert systems in manufacturing. Part 1: A user's perspective on expert-systems innovation. Knowledge-Based Systems, 1992, 5(2), 149–157.
3.
OldhamK.MainR. P.CooperJ. M.DohertyN. F.DIPLOMA—the seal of approval. In Applications of A.I. in Engineering (Eds RzevskiG.AdeyR.A.), Vol. 6, 1991 (Elsevier, Barking).
4.
DohertyN. F.Knowledge-based approaches to fault diagnosis. PhD thesis, University of Bradford, 1992.
5.
PauL. F.Survey of expert systems for fault detection, test generation and maintenance. Expert Systems, 1986, 3(2), 100–111.
6.
GuidaG.Reasoning about physical systems: Shallow versus deep models. In Expert systems and optimization in process control (Eds MamandiniA.EfstathiouJ.), 1985 (Technical Press, Aldershot).
7.
BonissoneP. P.JohnsonH. E.Expert system for diesel electric locomotive repair. Human and Systems Managmt, 1984, 4, 255–262.
8.
RandhawaS. U.BartonW. J.FarukuiS.Wave Solder Assistant—an expert system to aid in the troubleshooting of the wave soldering process. Computers and Ind. Engng, 1986, 10(4), 325–334.
9.
StuartJ. D.VinsonJ. W.TURBOMAC: an expert system to aid in the diagnosis of causes of vibration-producing problems in large turbomachinery. Proceedings of the Conference on Computers in mechanical engineering, Boston, 1985, pp. 319–325 (ASME).
10.
TorassoP.ConsoleL.Diagnostic problem solving, 1989 (North Oxford Academic Publishers, London).
11.
DavisR.Diagnostic reasoning based upon structure and behaviour. Artif. Intell., 1984, 24(3), 347–410.
12.
GeneserethM. R.The use of design descriptions in automated diagnosis. Artif. Intell., 1984, 24(3), 411–436.
13.
HannaA. AbuGoldY. I.Adaptive, multi-level diagnosis and modelling of dynamic systems. Int. J. of Expert Systems, 1990, 3(1), 1–30.
14.
PriceC. J.Developing a qualitative representation of mechanical devices for use in diagnosis. Engng Applics of AI, June 1988, 1, 87–96.
15.
KellyJ. J.FordK. M.Diagnosis using model-based reasoning by constraint propagation: A preliminary report on monitoring NASA space shuttle liquid hydrogen loading. Int. J. of Expert Systems, 1990, 3(2), 87–104.
16.
PriceC. J.LeeM.Applications of deep knowledge. Artif. Intell. in Engng, 1988, 3(1), 12–17.
17.
DohertyN. F.KochharA. K.Industrial applications of model-based approaches to fault diagnosis. Proceedings of the Thirtieth International MATADOR Conference, UMIST, Manchester, 1993, pp. 323–330.
18.
PopleH. E.Heuristic methods for imposing structure on ill-structured problems: The structuring of medical diagnosis. In AI in Medicine (Ed. SzolovitsP.), 1982 (Westview Press, Boulder, Colorado).
19.
DohertyN. F.KochharA. K.MIDAS: an application of model-based reasoning for the diagnosis of hydraulic systems. Loughborough University Business School working paper 1993: 8, 1993.
20.
LearyJ. J.GawthropP. J.Process fault detection using constraint suspension. IEE Proc., Part D, 1987, 134(4), 264–271.
21.
FinkP. K.LusthJ. C.Expert systems and diagnostic expertise in the mechanical and electrical domains. IEEE Trans. on Systems, Man and Cybernetics, 1987, 17(3), 340–349.
