DIAGNOSIS OF MULTIPLE SIMULTANEOUS FAULT VIA HIERARCHICAL ARTIFICIAL NEURAL NETWORKS

被引：59

作者：

WATANABE, K ^{[1
]}

HIROTA, S ^{[1
]}

HOU, L ^{[1
]}

HIMMELBLAU, DM ^{[1
]}

机构：

[1] UNIV TEXAS,DEPT CHEM ENGN,AUSTIN,TX 78712

来源：

AICHE JOURNAL | 1994年 / 40卷 / 05期

关键词：

D O I：

10.1002/aic.690400510

中图分类号：

TQ [化学工业];

学科分类号：

0817 ;

摘要：

We discuss a new type of macroarchitecture of neural networks called a HANN and how to train it for fault diagnosis given appropriate data patterns. The HANN divides a large number of patterns into many smaller subsets so the classification can be carried out more efficiently via an artificial neural network. One of its advantages is that multiple faults can be detected in new data even if the network is trained with data representing single faults. The use of a HANN is illustrated in fault diagnosis of a chemical reactor.

引用

页码：839 / 848

页数：10

共 23 条

[1]

Decker D. K., 1989, Proceedings of the 24th Intersociety Energy Conversion Engineering Conference IECEC-89 (Cat. No.89CH2781-3), P219, DOI 10.1109/IECEC.1989.74466

[2]

DIETZ WE, 1989, J NEURAL NETWORK SUM, P5

[3] FAULT-DIAGNOSIS IN COMPLEX CHEMICAL-PLANTS USING ARTIFICIAL NEURAL NETWORKS [J].

HOSKINS, JC ;

KALIYUR, KM ;

HIMMELBLAU, DM .

AICHE JOURNAL, 1991, 37 (01) :137-141

[4]

KOSHIJIMA I, 1992, P IFAC DELAWARE, P174

[5] DIAGNOSIS USING BACKPROPAGATION NEURAL NETWORKS - ANALYSIS AND CRITICISM [J].

KRAMER, MA ;

LEONARD, JA .

COMPUTERS & CHEMICAL ENGINEERING, 1990, 14 (12) :1323-1338

[6]

Leonard J. A., 1990, Proceedings of the 1990 American Control Conference (IEEE Cat. No.90CH2896-9), P2478

[7]

Leonard J. A., 1991, IEEE Control Systems Magazine, V11, P31, DOI 10.1109/37.75576

[8]

MARKS K, 1991, C NEURAL NETWORK APP

[9]

MCDUFF RJ, 1990, J NEURAL NETWORK COM, V2, P19

[10]

MONTGOMERY RJ, 1989, DO NEURAL NETWORK ME

← 1 2 3 →