Abstract
The paper summarizes results of a study about how the ‘general diagnostic engine’ (GDE) may be used to diagnose complex, dynamically modelled systems. To deal with complexity we extended GDE to hierarchical models and integrated filters for conflicts and candidates. Diagnosis at different levels in the hierarchy rendered our application tractable. Conflict and candidate filtering assumptions, retractable when necessary, were a good means for efficiently pruning the candidate space in typical situations, without loosing GDE's principal ability to diagnose unexpected faults. Concerning the dynamics in our application, a special extension of episode propagation was developed, and evaluation of probes had to be adapted. All of these extensions to GDE proved easily integratable without touching the basic mechanisms of prediction-based diagnosis. In particular, GDE's clear separation between diagnosis and behavior prediction allowed the straightforward integration of the new predictive engine. However, our work also showed that the application of GDE to complex and dynamic models requires further elaboration of some of its basic features. In particular, GDE's information theoretic probe selection procedure and the predictive engine should be supported by stronger heuristic knowledge.
Preview
Unable to display preview. Download preview PDF.
References
Rainer Decker: ”Modeling the temporal behavior of technical systems”, Proc. German Workshop on Artificial Intelligence GWAI, 1988, pp. 41–50.
Randy Davis: ”Diagnostic Reasoning based on Structure and Behavior”, Artificial Intelligence (24), 1984, pp. 347–410.
Johan de Kleer: ”An Assumption Based Truth Maintenance System”, Artificial Intelligence (28), 1986, pp. 127–162.
Johan de Kleer and Brian Williams: ”Diagnosing Multiple Faults”, Artificial Intelligence (32), 1987, pp. 97–130.
Johan de Kleer and Brian Williams: ”Diagnosis with Behavioral Modes”, Proc. IJCAI-89, 1989, pp. 1324–1330.
Michael Genesereth: ”The Use of Design Descriptions in Automated Diagnosis”, Artificial Intelligence (24), 1984, pp. 411–436.
Thomas Guckenbiehl: The Extended Episode Propagator, FhG-IITB, internal report, august 1990.
Walter Hamscher: Model-Based Troubleshooting of Digital Systems, technical report 1074, MIT AI-lab, 1988.
Walter Hamscher and Randy Davis: ”Diagnosing Circuits with state: an inherently underconstrained problem”, Proc. AAAI-84, pp. 142–147.
Walter Hamscher and Randy Davis: Issues in Model Based Troubleshooting, MIT-AI-Memo 893, March 1987.
H.Motoda, N. Yamada, K. Yoshida: ”A knowledge based system for plant diagnosis”, Proc. International Conference on Fifth Generation Computer Systems, 1984, pp. 582–588.
Yoav Shoham: Reasoning about Change: Time and Causation from the Standpoint of AI, Ph. D. thesis, Yale University, 1987.
Peter Struss and Oskar Dressler: ”Physical Negation: The integration of Fault Models into the General Diagnostic Engine”, Proc. IJCAI-89, pp. 1318–1323.
Brian Wiliams: ”Doing Time: Putting Qualitative Reasoning on firmer ground”, Proc. AAAI-86, pp. 105–112.
Bernard Zeigler: Theory of Modelling and Simulation, John Wiley & sons, 1976.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1990 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Guckenbiehl, T., Schäfer-Richter, G. (1990). Sidia: Extending prediction based diagnosis to dynamic models. In: Gottlob, G., Nejdl, W. (eds) Expert Systems in Engineering Principles and Applications. ESE 1990. Lecture Notes in Computer Science, vol 462. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-53104-1_31
Download citation
DOI: https://doi.org/10.1007/3-540-53104-1_31
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-53104-3
Online ISBN: 978-3-540-46711-3
eBook Packages: Springer Book Archive