Failure Detection Processes by Pattern Recognition and Expert Systems,
BATTELLE MEMORIAL INST GENEVA (SWITZERLAND)
Pagination or Media Count:
This paper analyses the failure diagnostic processes involved in automatic testing, automatic imaging inspection and more general technical diagnostic systems. It is shown how properly selected pattern recognition methods, artificial intelligence procedures, and relational data base search schemes, must be assembled to achieve operational requirements which these diagnostic systems must meet. This paper will indicate some basic design and selection criteria, and outline how it can be simplified in a number of practical cases. It will also describe the corresponding failure diagnostic system architecture.