Abstract
This paper presents four major approaches for diagnosing machine faults. Given the description of a system to be diagnosed and the observations on the system when it works, the need for diagnosis arises when the observations are different from those expected. The objective of diagnosis is to identify the malfunctioning components in a systematic and efficient way. The four approaches discussed are based on fault-tree, rule, model, and qualitative model. Early diagnosis systems used fault-tree and rule-based approaches. These are efficient in situations where an expert is able to provide the knowledge in the form of associations between symptoms and faults. Model-based and qualitative model-based approaches overcome many of the deficiencies of the earlier approaches. Model-based approaches can take care of situations (faults) not envisageda priori. Also, one can cater to minor variations in design using the same set of components and their interconnections. This paper discusses in each case, how the knowledge is represented and what diagnosis technique is to be adopted, and their relative advantages and disadvantages. Implementation of each method is also discussed.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Addanki S, Cremonini R, Penberthy J S 1989 Reasoning about assumptions in graph of models.Proc. Int. Joint Conf. Artif. Intell. (Detroit,MI) 2: 1432–1438
Arun Kumar A T, Mahabala H N 1992 Multi-level qualitative reasoning applied to hydraulic circuits. Technical Report, Dept. of Comput. Sci. & Eng., Indian Inst. Technol., Madras
Collins J, Forbus K D 1987 Reasoning about fluids via molecular collections.Proc. Am. Assoc. Artif. Intell. 87 (Seattle,WA) 1: 590–594
de Kleer J 1986a An assumption-basedTMS.Artif. Intell. 28(2): 127–162
de Kleer J 1986b Problem solving withATMS.Artif. Intell. 28(2): 197–224
de Kleer J, Brown J S 1984 A qualitative physics based on confluences.Artif. Intell. 24(1–3): 7–83
de Kleer J, Williams B C 1987 Diagnosing multiple faults.Artif. Intell. 32(1): 97–130
Dressler O, Farquhar A 1990 Putting the problem solver back in the driver’s seat: Contextual control of theATMS.Lecture notes in artificial intelligence (eds) J P Martin, M Reinfrank (Springer-Verlag) 515: 1–16
Falkenhainer B, Forbus K D 1988 Setting up large scale qualitative models.Proc. Am. Assoc. Artif. Intell. 88 (St. Paul,MN) 1: 301–306
Forbus K D 1984 Qualitative process theory.Artif. Intell. 24(1–3): 85–168
Fukul C, Kawakami J 1986 An expert system for fault section estimation using information from protective relays and circuit breakers.IEEE Trans. Power Delivery. PRWD-1(4): 83–89
Hibler D L, Biswas G 1989TEPS: The thought experiment approach to qualitative physics,Proc. Int. Joint Conf. Artif. Intell. 89 (Detroit,MI) 2: 1279–1284
Kuipers B 1986 Qualitative simulation.Artif. Intell. 29(3): 289–338
Kurup R R, Mahabala H N 1992 Implementation of a constraint system.Proc. Int. Assoc. Sci. Technol. Dev., Int. Symp. Modeling, Identification and Control, Innsbruck Austria
Kurup R R, Mahabala H N 1993 Model-based diagnosis of power system network faults. Technical Report, Knowledge-Based Computer Systems Laboratory, Indian Inst. Technol., Madras
Liu Z Y, Farley A M 1990 Shifting ontological perspectives in reasoning about physical systems.Proc. Am. Assoc. Artif. Intell. 90 (Boston,MA) 1:395–400
Mahabala H N, Kurup R R 1991a Implementation of an extendedATMS. Technical Report, Knowledge-Based Computer Systems Laboratory, Indian Inst. Technol., Madras
Mahabala H N, Kurup R R 1991b An implementation of a general diagnostic engine.Proc. Int. AMSE Conference on Signals, Data & Systems (Delhi:AMSE Press) 2: 137–150
Mahabala H N, Ravikanth G 1990IITMRULE user’s manual,KBCS Laboratory, Indian Inst. Technol., Madras
Mahabala H N, Ravi Prakash G, Managoli V V 1992IITMDESS: A fault-tree based diagnosis shell, Technical Report,KBCS Laboratory, Indian Inst. Technol., Madras
Raiman O 1986 Order of magnitude reasoning.Proc. Am. Assoc. Artif. Intell. 86 (Philadelphia,PA) 1: 100–104
Struss P 1988 A framework for model-based diagnosis. Siemens Reporttr inf2 arm-10-88, Munich
Talukdar S N, Cardozo E, Perry T 1986 The operator’s assistant — an intelligent expandable program for power system trouble analysis.IEEE Trans. Power Syst. PRWS-1(3): 182–187
Vesonder G T, Salvatore J S, Zieliski J E, Miller F D, Copp D H 1983ACE: An expert system for telephone cable maintenance.Proc. Int. Joint Conf. Artif. Intell. 83 Karlsruhe, Germany 2: 116–121
Williams T L, Orgren P J, Smith C L 1983 Diagnosis of multiple faults in a nation-wide communications network.Proc. Int. Joint Conf. Artif. Intell. 83, Karlsruhe, Germany 2: 179–181
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Mahabala, H.N., Arun Kumar, A.T., Kurup, R.R. et al. Fault diagnosis of machines. Sadhana 19, 23–50 (1994). https://doi.org/10.1007/BF02760389
Issue Date:
DOI: https://doi.org/10.1007/BF02760389