NEURAL-NETWORK-BASED OBJECTIVE FLOW REGIME IDENTIFICATION IN AIR-WATER 2-PHASE FLOW

被引：81

作者：

CAI, SQ

TORAL, H

QIU, JH

ARCHER, JS

机构：

[1] Department of Mineral Resources Engineering, Imperial College of Science Technology and Medicine, London, SW7 2BP, Prince Consort Road

来源：

CANADIAN JOURNAL OF CHEMICAL ENGINEERING | 1994年 / 72卷 / 03期

关键词：

NEURAL NETWORK; SELF-ORGANIZING FEATURE MAP; PATTERN RECOGNITION; FLOW REGIME IDENTIFICATION;

D O I：

10.1002/cjce.5450720308

中图分类号：

TQ [化学工业];

学科分类号：

0817 ;

摘要：

The Kohonen self-organising neural network was applied to identify flow regimes in horizontal air-water flow. The neural network was trained with stochastic features derived from turbulent absolute pressure signals obtained across a range of flow regimes. The feature map succeeded in classifying samples into distinctive flow regime classes consistent with the visual flow regime observation.

引用

页码：440 / 445

页数：6

共 16 条

[1]

Annunziato M, 1987, 3 INT C MULT FLOW HA, P169

[2]

CAI S, 1993, OCT P INT JOINT C NE, P2013

[3]

DARWICH TD, 1991, SPE PRODUCTION ENG, V6, P265

[4]

EBERHART RC, 1990, NEURAL NETWORK PC TO

[5] APPLICATIONS OF COUNTERPROPAGATION NETWORKS [J].

HECHTNIELSEN, R .

NEURAL NETWORKS, 1988, 1 (02) :131-139

[6] THE SELF-ORGANIZING MAP [J].

KOHONEN, T .

PROCEEDINGS OF THE IEEE, 1990, 78 (09) :1464-1480

[7]

KOHONEN T, 1990, JUN P IEEE INT JOINT, P545

[8]

Kohonen T., 1989, SELF ORG ASSOCIATIVE, V3rd

[9]

Lippmann R. P., 1988, Computer Architecture News, V16, P7, DOI [10.1109/MASSP.1987.1165576, 10.1145/44571.44572]

[10]

LIPPMANN RP, 1989, IEEE COMMUNICATION M, V11, P47

← 1 2 →