A hybrid hierarchical neural network-fuzzy expert system approach to chemical process fault diagnosis

被引：19

作者：

Ozyurt, B ^{[1
]}

Kandel, A ^{[1
]}

机构：

[1] UNIV S FLORIDA,TAMPA,FL 33620

来源：

FUZZY SETS AND SYSTEMS | 1996年 / 83卷 / 01期

关键词：

hybrid systems; fault diagnosis; neural networks; fuzzy expert systems; fuzzy logic; KNOWLEDGE; STATE;

D O I：

10.1016/0165-0114(95)00314-2

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

Increasing complexity of the chemical process industries (CPI) requires more reliable and efficient real time diagnostic tools. Here, a hybrid diagnostic methodology is introduced for fault diagnosis based on a hierarchical multilayer perceptron-elliptical neural network structure and a fuzzy expert system. The introduced hybrid system is noise tolerant, easy to train and maintain and also reliable under changing process conditions.

引用

页码：11 / 25

页数：15

共 35 条

[1]

ADLASSNIG KP, 1985, METHOD INFORM MED, V24, P13

[2]

[Anonymous], 1992, HYBRID ARCHITECTURES

[3]

[Anonymous], BYTE OCT

[4] AN INTEGRATED NEURAL-NETWORK EXPERT-SYSTEM APPROACH FOR FAULT-DIAGNOSIS [J].