An application of failure-driven learning to the construction of the knowledge base of a diagnostic expert system is discussed. Diagnosis heuristics (i.e. efficient rules which encode empirical associations between atypical device behavior and device failure) are learned from information implicit in device models. This approach is desirable since less effort is required to obtain information about device functionality and connectivity to define device models than to encode and debug diagnosis heuristics from a domain expert. Results are given of applying this technique in an expert system for the diagnosis of failures in the attitude control system of the DSCS-III satellite. The system is fully implemented in a combination of LISP and PROLOG on a Symbolics 3600 computer. The results indicate that realistic applications can be built using this approach. The performance of the diagnostic expert system after learning is equivalent to and, in some cases, better than the performance of the expert system with rules supplied by a domain expert.
Failure-driven learning of fault diagnosis heuristics
Ausfallgetriebenes Lernen von Fehlerdiagnose-Heuristiken
IEEE Transactions on Systems, Man and Cybernetics ; SMC-17 , 3 ; 380-394
1987
15 Seiten, 30 Quellen
Article (Journal)
English
FAULT DIAGNOSIS DEVICE, FAULT DIAGNOSIS SYSTEM, FAULT DIAGNOSIS METHOD, AND FAULT DIAGNOSIS PROGRAM
European Patent Office | 2021
|