| Zugriffsnummer | 48799 |
| Dokumenttyp | Zeitschriftenartikel |
| Peer Review | mit Peer Review |
| Sprache | Englisch |
| Titel | Deep learning based liquid level extraction from video observations of gas-liquid flows |
| Autor(in); Institution |
Olbrich, Marc; 8.4, Mathematische Modellierung und Datenanalyse, PTB-Berlin; Institute of Fluid Dynamics and Technical Acoustics, Technische Universität Berlin, Berlin, GERMANY
Riazy, Leili; Cardiovascular Magnetic Resonance, Experimental and Clinical Research Center, Charité Campus Buch, Berlin, GERMANY
Kretz, Tobias; 8.4, Mathematische Modellierung und Datenanalyse, PTB-Berlin; 6.2, Dosimetrie für Strahlentherapie und Röntgendiagnostik, PTB-Braunschweig
Leonard, Terri; TÜV SÜD National Engineering Laboratory (NEL), East Kilbride, Glasgow, UK
van Putten, Dennis S.; DNV, AN Groningen, THE NETHERLANDS
Bär, Markus; 8.4, Mathematische Modellierung und Datenanalyse, PTB-Berlin
Oberleithner, Kilian; TU Berlin, ISTA, Berlin, GERMANY
Schmelter, Sonja; 8.4, Mathematische Modellierung und Datenanalyse, PTB-Berlin
|
| Quelle/Jahr | International Journal of Multiphase Flow: 157 (2022), 12 |
| Artikelnummer | 104247 |
| ISSN | 0301-9322 (PRINT) ; 1879-3533 (ONLINE) |
| DOI | |
| Verlag | Amsterdam [u.a.]: Elsevier |
| Freie Schlagworte | Multiphase flow ; Gas-liquid interface ; Deep learning ; Image processing ; Convolutional neural network ; Videometry |
| Zusammenfassung | The slug flow pattern is one of the most common gas-liquid flow patterns in multiphase transportation pipelines, particularly in the oil and gas industry. This flow pattern can cause severe problems for industrial processes. Hence, a detailed description of the spatial distribution of the different phases in the pipe is needed for automated process control and calibration of predictive models. In this paper, a deep-learning based image processing technique is presented that extracts the gas-liquid interface from video observations of multiphase flows in horizontal pipes. The supervised deep learning model consists of a convolutional neural network, which was trained and tested with video data from slug flow experiments. The consistency of the hand-labelled data and the predictions of the trained model have been evaluated in an inter-observer reliability test. The model was further tested with other data sets, which also included recordings of a different flow pattern. It is shown that the presented method provides accurate and reliable predictions of the gas-liquid interface for slug flow as well as for other separate flow patterns. Moreover, it is demonstrated how flow characteristics can be obtained from the results of the deep-learning based image processing technique. |
| Kostenfreier Zugang | Open Access Hybrid |
| Rechteinformation | CC BY 4.0 ; Creative Commons Attribution 4.0 License |
| Themenbereich der Metrologie | Metrologie in der Medizin |
| Forschungsprojekt | 16ENG07: MultiFlowMet II: Multiphase flow reference metrology |
| Förderinformationen (1) |
Förderername: European Commission (EC)
Förderer ID: 0000 0001 2242 8989 Förderer ID Typ: ISNI Förderprogramm: EMPIR 2016 Energy Titel der Förderung: 16ENG07: MultiFlowMet II: Multiphase flow reference metrology Förderungsnummer: 16ENG07 URI der Förderung: https://www.euramet.org/research-innovation/search-research-projects/details/?tx_eurametctcp_project[project]=1466&tx_eurametctcp_project[controller]=Project&tx_eurametctcp_project[action]=show |
Zitierung
Olbrich, M., Riazy, L., Kretz, T., Leonard, T., van Putten, D. S., Bär, M., Oberleithner, K., & Schmelter, S. (2022). Deep learning based liquid level extraction from video observations of gas-liquid flows. International Journal of Multiphase Flow, 157(12). https://doi.org/10.1016/j.ijmultiphaseflow.2022.104247