Abstract
A novel first-principles-based expert system is proposed for on-line detection and identification of faulty component candidates during incipient off-normal process operations. The system performs function-oriented diagnostics and can be reused for diagnosing single-component failures in different processes and different plants through the provision of the appropriate process schematics information. The function-oriented and process-independent diagnostic features of the proposed expert system are achieved by constructing a knowledge base containing three distinct types of information, qualitative balance equation rules, functional classification of process components, and the process piping and instrumentation diagram. The various types of qualitative balance equation rules for processes utilizing single-phase liquids are derived and their usage is illustrated through simulation results of a realistic process in a nuclear power plant.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
W. R. Nelson, “REACTOR: An Expert System for Diagnosis and Treatment of Nuclear Reactor Accidents,” Proceedings of the National Conference on Artificial Intelligence, AAAI, pp. 296–301, Pittsburgh, Pennsylvania, August 18–20, 1982.
F. E. Finch and M. A. Kramer, “Narrowing Diagnostic Focus Using Functional Decomposition,” AIChE J., 34, 25, 1988.
J. E. Larsson, “Hyperfast Algorithms for Model-Based Diagnosis,” Proceedings of the IEEE/IFAC Joint Symposium on Computer-Aided Control System Design,” pp. 533–538, Tucson, Arizona, March 7–9, 1994.
J. Reifman, L. L. Briggs, and T. Y. C. Wei, “A First-Principles General Methodology for Representing the Knowledge Base of a Process Diagnosis Expert System,” Proceedings of the 4th International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems, pp. 255–265, Kauai, Hawaii, June 2–5, 1991.
J. Reifman, L. L. Briggs, and T. Y. C. Wei, “Nuclear Power Plant Diagnostics Using Qualitative Analysis and Component Functional Classification,” Proceedings of the Frontiers in Innovative Computing for Nuclear Industry, pp. 227–236, Jackson, Wyoming, September 15–18, 1991.
J. De Kleer and J. S. Brown, “A Qualitative Physics Based on Confluences,” AI, 24, 7, 1984.
J. Reifman and T. Y. C. Wei, “PRODIAG — Dynamic Qualitative Analysis for Process Fault Diagnosis,” Proceedings of the 9th Power Plant Dynamics, Control and Testing Symposium, pp. 40.01–40.15, Knoxville, Tennessee, May 24–26, 1995.
Quintus Corporation, Palo Alto, California, Release 3, 1991.
J. Reifman, T. Y. C. Wei, R. G. Abboud, and T. M. Chasensky, “Cooperative Research and Development for Artificial Intelligence Based Reactor Diagnostic System,” Proceedings of the American Power Conference, pp. 365–370, Chicago, Illinois, April 25–27, 1994.
J. Reifman, T. Y. C. Wei, R. G. Abboud, and T. M. Chasensky, “FunctionBased Approach to Plant Diagnosis,” paper submitted to the American Nuclear Society 1995 Winter Meeting, San Francisco, California, October 29–November 2, 1995.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Reifman, J., Wei, T.Y.C. (1995). Systematic construction of qualitative physics-based rules for process diagnostics. In: Pinto-Ferreira, C., Mamede, N.J. (eds) Progress in Artificial Intelligence. EPIA 1995. Lecture Notes in Computer Science, vol 990. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-60428-6_26
Download citation
DOI: https://doi.org/10.1007/3-540-60428-6_26
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-60428-0
Online ISBN: 978-3-540-45595-0
eBook Packages: Springer Book Archive