Gas-liquid flow regimes identification using non-intrusive Doppler ultrasonic sensor and convolutional recurrent neural networks in an S-shaped riser

Simple item page
dc.contributor.authorKuang, Boyu
dc.contributor.authorNnabuife, Somtochukwu Godfrey
dc.contributor.authorSun, Shuang
dc.contributor.authorWhidborne, James F.
dc.contributor.authorRana, Zeeshan A.
dc.date.accessioned2022-01-31T12:54:59Z
dc.date.available2022-01-31T12:54:59Z
dc.date.issued2022-01-19
dc.description.abstractThe problem of gas-liquid (two-phase) flow regime identification in an S-shaped riser using an ultrasonic sensor and convolutional recurrent neural networks (CRNN) is addressed. This research systematically evaluates three different schemes with four CRNN-based classifiers over fourteen experiments. Four metrics are used as the evaluation criteria: categorical accuracy, categorical cross-entropy, mean square error (MSE), and computation graph complexity. Compared with existing results, a compatible performance is achieved while considerably reducing the model complexity. The testing and validation accuracies were 98.13% and 98.06%, while the complexity decreased by 98.4% (only 117,702 parameters). The proposed approach is i) accurate, low complexity, and non-intrusive and hence suitable for industry, and ii) could provide a benchmark for flow regime identification.en_UK
dc.identifier.citationKuang B, Nnabuife SG, Sun S, et al., (2022) Gas-liquid flow regimes identification using non-intrusive Doppler ultrasonic sensor and convolutional recurrent neural networks in an S-shaped riser, Digital Chemical Engineering, Volume 2, March 2022, Article number 100012en_UK
dc.identifier.issn2772-5081
dc.identifier.urihttps://doi.org/10.1016/j.dche.2022.100012
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/17523
dc.language.isoenen_UK
dc.publisherElsevieren_UK
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/*
dc.subjectTwo-phase flowen_UK
dc.subjectFlow regime identificationen_UK
dc.subjectUltrasonic signalen_UK
dc.subjectTime-domain propertyen_UK
dc.subjectDeep learningen_UK
dc.titleGas-liquid flow regimes identification using non-intrusive Doppler ultrasonic sensor and convolutional recurrent neural networks in an S-shaped riseren_UK
dc.typeArticleen_UK

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Gas-liquid_flow_regimes_identification-2022.pdf
Size:
9.47 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Staff publications (SATM)