SYDCOD - KNOWLEDGE-BASED STUDENT TRAINING TOOL TO FAULT-DIAGNOSIS IN A DISTILLATION COLUMN

作     者：NOORSAMAN, A PAPASTRATOS, S ISAMBERT, A DEPEYRE, D 

作者机构：Laboratoire de Gé nie et Informatique Chimiques Ecole Centrale Paris 92295 Chatenay Malabry FRANCE 

出 版 物：《COMPUTERS & CHEMICAL ENGINEERING》 (计算机与化工)

年 卷 期：1993年第17卷第Sup1期

页      面：S389-S394页

核心收录：

学科分类：0817[工学-化学工程与技术] 08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：KNOWLEDGE BASED SYSTEM COUPLED SYSTEM PATTERN-MATCHING SYMBOLIC AND NUMERIC COMPUTING HIERARCHICAL CLASSIFICATION TASK-SPECIFIC ARCHITECTURE 

摘      要：A Coupled-System approach (SyDCoD) for student training tool to fault diagnosis in a distillation column has been developed. The basic methodology based on the coupling between symbolic-numeric computing integration in which the symbolical computing is represented by a knowledge base of diagnosis and the numerical computing is represented by a *** Knowledge Base approach involves a structure hierarchical diagnosis and structure pattern-matching by categorisation of component malfunction. The hierarchy is a collection of small individual components coordinated to achieve at an overall diagnosis. This fault hierarchy is particularly effective, in handling multiple symptoms and multiple fault situations. This methodology give to the students or the student operators better initiation and better understanding on the failure diagnosis in the distillation column plant. The coupled system problem-solver strategy gives more posibilities to students how to choose the strategy to solve their problem.