Premium
An expert system for identifying separation processes
Author(s) -
Garg Mahesh K.,
Linders James G.,
Douglas Peter L.
Publication year - 1991
Publication title -
the canadian journal of chemical engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.404
H-Index - 67
eISSN - 1939-019X
pISSN - 0008-4034
DOI - 10.1002/cjce.5450690108
Subject(s) - heuristics , computer science , separation process , expert system , separation (statistics) , heuristic , identification (biology) , process (computing) , fuzzy logic , algorithm , artificial intelligence , machine learning , chromatography , chemistry , botany , biology , operating system
This paper presents the development of an expert system, called SIS (Separator Identification System), to generate near‐optimal separation sequences for any multicomponent mixture. SIS was designed based on a combination of heuristic and algorithmic approaches. Heuristics were used to select the location of the split. Algorithms were used to calculate physical properties of the multicomponent mixture. A fuzzy approach was used for the propagation of the truth function and uncertainty management. SIS was tested using four sample problems involving gas, liquid, and solid components. The separation sequences suggested by SIS were the same or similar to those found in process synthesis literature.