CIESC Journal

• Original Article • 上一篇    下一篇

AN OBJECT-ORIENTED EXPERT SYSTEM FOR TROUBLESHOOTING REFINERY DISTILLATION COLUMNS

王学重; 徐亦方; 史忠植; 沈复   

  1. University of Petroleum, China, Beijing, 100083
  • 收稿日期:1991-10-03 修回日期:1991-11-25 出版日期:1992-12-28 发布日期:1992-12-28
  • 通讯作者: 王学重

AN OBJECT-ORIENTED EXPERT SYSTEM FOR TROUBLESHOOTING REFINERY DISTILLATION COLUMNS

WANG Xuezhong; XU Yifang; SHI Zhongzhi; SHEN Fu+   

  1. University of Petroleum, China, Beijing, 100083
  • Received:1991-10-03 Revised:1991-11-25 Online:1992-12-28 Published:1992-12-28
  • Contact: WANG Xuezhong

摘要: An object-oriented prototype expert system ORDEES for off-line trouble-shooting of refinery distillation columns is developed. It is found that highly modular knowledge base can be designed, and different types of data (e.g., graphs, numberical data, and algorithms) may be manipulated, by using object-oriented knowledge representation. In addition, a method termed Object-Oriented Multifunction Switcher is proposed for building multifunction expert systems. The results of the study are expected to be useful for designing multifunction expert systems for complex petroleum refining and petro-chemical processes with many kinds of equipment.

关键词: Expert system;Distillation column;Object-oriented knowledge representation;Fault diagnosis

Abstract: An object-oriented prototype expert system ORDEES for off-line trouble-shooting of refinery distillation columns is developed. It is found that highly modular knowledge base can be designed, and different types of data (e.g., graphs, numberical data, and algorithms) may be manipulated, by using object-oriented knowledge representation. In addition, a method termed Object-Oriented Multifunction Switcher is proposed for building multifunction expert systems. The results of the study are expected to be useful for designing multifunction expert systems for complex petroleum refining and petro-chemical processes with many kinds of equipment.

Key words: Expert system, Distillation column, Object-oriented knowledge representation, Fault diagnosis