Abstract
A fault diagnosis system was developed to improve the availability and maintainability of control systems in nuclear power plants. To facilitate man-machine communications in the system a natural language interface was introduced. Features of the interface include two-step analysis of the meaning of input sentences, identification of the kind of input content using sentence patterns, and retrieval of the information required. For the information retrieval, when information is lacking supplementation is done by referring to the dialog history and knowledge of the control system composition. Dialog tests, including the required information inputs for diagnosis and questions about the validity of the diagnosis results, were performed by the control system simulator for an assumed component failure, such as a printed circuit board failure. Dialog inputs were made by voice and outputs were by voice or a CRT display. The tests confirmed that inputs required in the diagnosis process can be entered by voice witho...
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
