The development and implementation are described of the time of flight validation system, a system for the automated diagnosis of a large-scale nuclear physics detector. The diagnostic system is multi-leveled, combining a single monitoring level based on statistical methods with two model-based diagnostic levels, one operating on structural information and the other using both structural and behavioral models. The later diagnostic level uses a qualitative data model of the detector to provide evidence that is mapped on a continuous basis from observation values to belief in component failure hypotheses. The general architecture is scalable
Published in:
Artificial Intelligence for Applications, 1992., Proceedings of the Eighth Conference on
Date of Conference: 2-6 Mar 1992