Artificial Neural Networks for Gas‐Liquid Flow Regime Classification in Small Channels

Abstract: The reliable design of multiphase micro‐structured apparatus requires a precise knowledge of the internal flow regime. Previous research indicated that classifiers based on artificial neural networks (ANN) are relatively simple to develop and provide a reasonable accuracy when trained with data for specific inlet designs. This paper introduces advanced ANN classifiers capable of predicting all relevant flow regimes regardless of the inlet design with a recall of 94 % and above for Taylor, churn, dispersed, rivulet, and parallel flows, between 89 % and 94 % for annular and bubbly flows, and 83 % for Taylor‐annular flow. These classifiers were trained and validated by using more than 13,000 experimental data points extracted from 97 flow maps.

Standort
Deutsche Nationalbibliothek Frankfurt am Main
Umfang
Online-Ressource
Sprache
Englisch

Erschienen in
Artificial Neural Networks for Gas‐Liquid Flow Regime Classification in Small Channels ; day:25 ; month:04 ; year:2024 ; extent:10
Chemie - Ingenieur - Technik ; (25.04.2024) (gesamt 10)

Urheber
Haase, Stefan
May, Henry
Hiller, Andreas
Schubert, Markus

DOI
10.1002/cite.202300214
URN
urn:nbn:de:101:1-2404261406398.340286662595
Rechteinformation
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
Letzte Aktualisierung
14.08.2025, 10:55 MESZ

Datenpartner

Dieses Objekt wird bereitgestellt von:
Deutsche Nationalbibliothek. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.

Beteiligte

Ähnliche Objekte (12)