{"title":"Real-time expert system for gas plant operation support (GAPOS)","authors":"K. Koyama","doi":"10.1109/IECON.1990.149323","DOIUrl":null,"url":null,"abstract":"High reliability and a quick and appropriate response to abnormal conditions are required for operation of city gas production plants. To respond to these needs, the real-time expert system GAPOS (gas advanced plant operation support system) has been developed by the Tokyo Gas Company on the basis of minicomputers and an inference engine with numeric analysis, man-machine functions, etc. This system links the analysis functions of process time series data and a rule-type knowledge base and not only investigates the causes of abnormalities but also makes predictions about the potential for abnormalities. Basic performance has been proven with a prototype of approximately 2000 rules for a calorie control plant, and development has begun on the practical application of such a system.<<ETX>>","PeriodicalId":253424,"journal":{"name":"[Proceedings] IECON '90: 16th Annual Conference of IEEE Industrial Electronics Society","volume":"19 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1990-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"[Proceedings] IECON '90: 16th Annual Conference of IEEE Industrial Electronics Society","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IECON.1990.149323","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
High reliability and a quick and appropriate response to abnormal conditions are required for operation of city gas production plants. To respond to these needs, the real-time expert system GAPOS (gas advanced plant operation support system) has been developed by the Tokyo Gas Company on the basis of minicomputers and an inference engine with numeric analysis, man-machine functions, etc. This system links the analysis functions of process time series data and a rule-type knowledge base and not only investigates the causes of abnormalities but also makes predictions about the potential for abnormalities. Basic performance has been proven with a prototype of approximately 2000 rules for a calorie control plant, and development has begun on the practical application of such a system.<>