Proper maintenance and troubleshooting of complex mechanical equipment is a difficult task. A large amount of information, such as sensor data and previous repair actions, is available but infrequently used for interpretation by technical staff which is continually losing expertise due to turnover. Well structured knowledge-based systems can provide effective techniques for assisting in this task.
The paper describes a generalized knowledge-based tool for diagnosis which is currently being applied to jet engine maintenance. A domain dependent diagnostic tree is created for a particular jet engine by filling in an empty hypothesis frame for each diagnostic node in the tree. The knowledge in the tree is reasoned about using a generalized and explicit reasoning strategy. This strategy can be guided by rules specific to the activation of a particular diagnostic hypothesis in the tree.The user interacts with the system through a window interface which features definitions, glossary information, schematics and explanations of session reasoning, which are all linked to the knowledge contained in the system. A demonstration prototype which runs under the ART (LISP-based) environment on Symbolics 3620 and Sun 3/60 workstations was completed in December 1988. The preliminary prototype diagnoses a subset of the acceleration faults on the General Electric J85-CAN-15 jet engine and is being field tested and evaluated by potential users.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.