A hierarchical symptom classification for model based causal reasoning

Authors:
C. Lee;P. Liu;S. Clark;M. Y. Chiu
Affiliations:
Siemens Research and Technology Labs, Princeton, NJ;Siemens Research and Technology Labs, Princeton, NJ;Siemens Research and Technology Labs, Princeton, NJ;Siemens Research and Technology Labs, Princeton, NJ
Venue:
IEA/AIE '88 Proceedings of the 1st international conference on Industrial and engineering applications of artificial intelligence and expert systems - Volume 1
Year:
1988

Citing 9
Cited 0

How circuits work

Artificial Intelligence - Special volume on qualitative reasoning about physical systems
Diagnostic reasoning based on structure and behavior

Artificial Intelligence - Special volume on qualitative reasoning about physical systems
The use of design descriptions in automated diagnosis

Artificial Intelligence - Special volume on qualitative reasoning about physical systems
A blackboard architecture for control

Artificial Intelligence
A formal model of diagnostic inference. I. Problem formulation and decomposition

Information Sciences: an International Journal - Special issue on expert systems
A theory of diagnosis from first principles

Artificial Intelligence
Diagnosing multiple faults

Artificial Intelligence
Theories of causal ordering

Artificial Intelligence
Issues in Model Based Troubleshooting

Issues in Model Based Troubleshooting

Quantified Score

Hi-index	0.00

Visualization

Abstract

Model based causal reasoning has been widely used for physical systems diagnosis. The system fault is localized with the causal relation of system structure and behavior. In such applications, if the system fault is not localized with the observed behavior, then a subsequent observation is made. This research studies a hierarchical symptom classification for guiding a subsequent observation in model based causal reasoning. The diagnostic symptoms are mapped to the system functional hierarchy and the symptoms are classified by partitioning the functional hierarchy. The dependency relation of symptoms guides subsequent observation. This strategy enhances the control of subsequent observation by hierarchically structuring and classifying the symptoms.