skip to main content
10.1145/51909.51919acmconferencesArticle/Chapter ViewAbstractPublication Pagesiea-aeiConference Proceedingsconference-collections
Article
Free Access

Using hypertext to overcome the knowledge base development bottleneck: a case study

Published:03 June 1988Publication History

ABSTRACT

The installation of a new complex rolling mill used to manufacture the sheet metal to make beverage cans raised concerns about maintaining and troubleshooting the mill's systems. This led to an evaluation of computer-based technologies which could provide the needed diagnostic decision support, including expert and hypertext systems. Expert systems have been demonstrated for a variety of applications including equipment diagostics. Their principal drawback is that they are very costly to develop and maintain for large problems. In hypertext systems, objects in a documentation data base are represented by graphical objects on a computer screen. By manipulating the screen objects, users can display and organize the on-line documentation.

The course embarked upon was to construct a hypertext system with the means to build troubleshooting and maintenance aids as well. The Electronics Guidance and Documentation System (EGADS), now operational in the mill, combines a commercially available hypertext system with a custom interface which graphically depicts decision networks. The decision networks convey high level qualitative problem solving knowledge to users, and highly detailed information typical of technical documentation is available through the hypertext system. EGADS was used to develop a diagnostic and maintenance aid for one the mill's major components, the flatness subsystem. Its decision network gives step by step instructions for troubleshooting a wide variety of problems, and provides direct access to appropriate equipment functional descriptions and maintenance documentation. By using the detailed technical documentation available from equipment vendors, the authors conclude that the application they developed required considerably less resources than would be needed to create an expert system with comparable functionality.

References

  1. Document Examiner is a registered trademark of Symbolics Corporation.Google ScholarGoogle Scholar
  2. Williamson, M., "On Frames, Semantic Nets, and Hypertext," Computers in Science (Jan/Feb, 1988), pp. 49-51.Google ScholarGoogle Scholar
  3. Conklin, J., "A Survey of Hypertext," MCC Technical Report STP-356-86, Rev. 2 (Dec. 3, 1987).Google ScholarGoogle Scholar
  4. Bonissone, P.P., Johnson, H.E.,"Expert System for Diesel Electric Locomotive Repair," Proc. IJCAI (1983).Google ScholarGoogle Scholar
  5. Davis, R., Shrobe, H.,"Representing Structure and Behavior of Digital Hardware," MIT Report 4-57-84 (1984).Google ScholarGoogle Scholar
  6. Osborne, R.L.,"Online, Artificial Intelligence-Based Turbine Generator Diagnostics," AI Magazine (Fall 1986), pp. 97-103. Google ScholarGoogle ScholarDigital LibraryDigital Library

Index Terms

  1. Using hypertext to overcome the knowledge base development bottleneck: a case study

                  Recommendations

                  Comments

                  Login options

                  Check if you have access through your login credentials or your institution to get full access on this article.

                  Sign in
                  • Published in

                    cover image ACM Conferences
                    IEA/AIE '88: Proceedings of the 1st international conference on Industrial and engineering applications of artificial intelligence and expert systems - Volume 1
                    June 1988
                    636 pages
                    ISBN:0897912713
                    DOI:10.1145/51909
                    • Editor:
                    • Moonis Ali

                    Copyright © 1988 ACM

                    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

                    Publisher

                    Association for Computing Machinery

                    New York, NY, United States

                    Publication History

                    • Published: 3 June 1988

                    Permissions

                    Request permissions about this article.

                    Request Permissions

                    Check for updates

                    Qualifiers

                    • Article
                  • Article Metrics

                    • Downloads (Last 12 months)17
                    • Downloads (Last 6 weeks)1

                    Other Metrics

                  PDF Format

                  View or Download as a PDF file.

                  PDF

                  eReader

                  View online with eReader.

                  eReader