Network switching expert system for AC railway electrification

C. S. Chang, T. T. Chan, Kang Kuen Lee, K. Y. Wan

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

Abstract

The authors report the development of a Prolog expert system utilizing computer graphics for online monitoring and control of the 50-Hz, single-phase, overhead current-collection catenary system currently in operation in Hong Kong. Running as an online consultant on a personal computer, this expert system allows operating personnel to perform pseudo-network-switching on each of six full graphics pictures representing the whole of the catenary line system and thus visualize the effects of switching on the system. Equipped with a user-friendly interface, the expert system employs its topology recognition algorithm to decouple the knowledge base from implementation. In other words, it is independent of the configuration of an AC catenary railway system. A tentative inference strategy enables operators to avoid switching operations against that cause violation of interlocking rules, isolation of some catenary sections from the supply, or phase-to-phase short-circuit of the utility system. Due to the expert systems's modular structure, new rules can be added with ease.
Original languageEnglish
Title of host publicationProc 1988 Int Conf Syst Man Cybern
PublisherPubl by IEEE
Pages815-819
Number of pages5
ISBN (Print)7800030393
Publication statusPublished - 1 Dec 1988
EventProceedings of the 1988 International Conference on Systems, Man, and Cybernetics - Beijing/Shenyang, China
Duration: 8 Aug 198812 Aug 1988

Conference

ConferenceProceedings of the 1988 International Conference on Systems, Man, and Cybernetics
Country/TerritoryChina
CityBeijing/Shenyang
Period8/08/8812/08/88

ASJC Scopus subject areas

  • General Engineering

Fingerprint

Dive into the research topics of 'Network switching expert system for AC railway electrification'. Together they form a unique fingerprint.

Cite this