A HYBRID HIERARCHICAL NEURAL NETWORK-FUZZY EXPERT-SYSTEM APPROACH TO CHEMICAL PROCESS FAULT-DIAGNOSIS

Authors
OZYURT B KANDEL A
Citation
B. Ozyurt et A. Kandel, A HYBRID HIERARCHICAL NEURAL NETWORK-FUZZY EXPERT-SYSTEM APPROACH TO CHEMICAL PROCESS FAULT-DIAGNOSIS, Fuzzy sets and systems, 83(1), 1996, pp. 11-25
Citations number
35
Categorie Soggetti
Computer Sciences, Special Topics","System Science",Mathematics,"Statistic & Probability",Mathematics,"Computer Science Theory & Methods
Journal title
Fuzzy sets and systems → ACNP
ISSN journal
01650114
Volume
83
Issue
1
Year of publication
1996
Pages
11 - 25
Database
ISI
SICI code
0165-0114(1996)83:1<11:AHHNNE>2.0.ZU;2-1
Abstract
Increasing complexity of the chemical process industries (CPI) require s more reliable and efficient real time diagnostic tools. Here, a hybr id diagnostic methodology is introduced for fault diagnosis based on a hierarchical multilayer perceptron-elliptical neural network structur e and a fuzzy expert system. The introduced hybrid system is noise tol erant, easy to train and maintain and also reliable under changing pro cess conditions.