- Titel
- Image-Based Flow Regime Recognition in Aerated Stirred Tanks Using Deep Transfer Learning
- Zitierfähige Url:
- https://nbn-resolving.org/urn:nbn:de:bsz:14-qucosa2-954860
- Quellenangabe
- Chemie - Ingenieur - Technik
Erscheinungsjahr: 2023
Jahrgang: 95
Heft: 7
Seiten: 1172-1179
E-ISSN: 1522-2640 - Erstveröffentlichung
- 2023
- Abstract (EN)
- Monitoring of flow regimes in aerated stirred tanks is important to ensure energy efficiency and product quality. The use of deep learning models for the recognition of flow regimes shows promising results. However, such models require a large amount of data for training. The aim of this paper is to apply the deep transfer learning approach to address this challenge. We compare various pre-trained models with the differential learning rate and 2-step transfer learning approaches to analyse the resultant model performance. We also investigate the effect of the dataset size on the classification accuracy.
- Andere Ausgabe
- Link zum Artikel, der zuerst in der Zeitschrift „Chemie - Ingenieur - Technik” im Verlag Wiley-VCH erschienen ist.
DOI: 10.1002/cite.202200246 - Freie Schlagwörter (EN)
- Deep learning, Deep transfer learning, Flow regime recognition, Machine learning
- Klassifikation (DDC)
- 540
- 660
- Verlag
- Wiley-VCH, Weinheim
- Förder- / Projektangaben
- Federal Ministry of Economic Affairs and Energy of Germany ID: 01MK20014T
- Version / Begutachtungsstatus
- publizierte Version / Verlagsversion
- URN Qucosa
- urn:nbn:de:bsz:14-qucosa2-954860
- Veröffentlichungsdatum Qucosa
- 30.10.2025
- Dokumenttyp
- Artikel
- Sprache des Dokumentes
- Englisch
- Lizenz / Rechtehinweis
CC BY 4.0