Two-phase flow pattern identification in horizontal gas–liquid swirling pipe flow by machine learning method. (April 2023)

• Record Type: Journal Article
• Authors: Liu, Wen; Lv, Xiaofei; Jiang, Sheng; Li, Huazheng; Zhou, Hao; Dou, Xiangji
• Is Part Of: Annals of nuclear energy. Volume 183(2023)
• Publication Date: 2023-04
• Subjects: Gas–liquid -- Swirling flow -- Flow pattern identification -- Void fraction -- Horizontal pipe; Nuclear energy -- Periodicals; Nuclear engineering -- Periodicals; 621.4805
• DOI: 10.1016/j.anucene.2022.109644
• Languages: English
• ISSNs: 0306-4549

Abstract

Highlights: Swirling flow patterns in a horizontal pipe with a vane-type swirler were systematically investigated by a visualization experiment. Fluctuation of void fraction signals for typical swirling flow pattern were studied by statistical analysis. Four parameters were proposed to describe the characteristics of PDF signals as the indicator of machine learning method. RUSBoost tree algorithm performed best on identification of swirling flow patterns with an accuracy of 97.4%. Abstract: Gas–liquid two-phase swirling flow has been widely used in nuclear industry. Its flow pattern is fundamental to investigate the two-phase flow. Although flow patterns of non-swirling flow in a horizontal pipe have been investigated for a long history, flow patterns of swirling flow in the pipe are rarely reported. In this paper, gas–liquid two-phase flow patterns of swirling flow generated by a vane-type swirler inside a horizontal pipe were investigated by a visualization experiment. Five swirling flow patterns were observed and recorded by the backlight imaging method. Then image processing method was used to obtain void fraction, and the statistical analysis (CDF and PDF) of void fraction for each swirling flow patterns was performed. Owing to the distinguished and stable feature of PDF signals, four parameters describing the characteristics of PDF signals have been proposed as the indicator of machine learning method. Finally, five algorithms of machine learning method have been used to identify the swirling flow patterns, and RUSBoost tree algorithm performs best with an accuracy of 97.4%.