Identification of flow regimes in boiling flows in a vertical annulus channel with machine learning techniques. (April 2022)

• Record Type: Journal Article
• Authors: Ooi, Zhiee Jhia; Zhu, Longxiang; Bottini, Joseph L.; Brooks, Caleb S.
• Is Part Of: International journal of heat and mass transfer. Volume 185(2022)
• Publication Date: 2022-04
• Subjects: Flow regime identification -- Conductivity probe -- Boiling flow -- Machine learning; Heat -- Transmission -- Periodicals; Mass transfer -- Periodicals; Chaleur -- Transmission -- Périodiques; Transfert de masse -- Périodiques; Electronic journals; 621.4022
• DOI: 10.1016/j.ijheatmasstransfer.2021.122439
• Languages: English
• ISSNs: 0017-9310

Abstract

Highlights: Flow regime identification with the unsupervised self-organizing map. Bubble durations measured by conductivity probes are used as the input data. Analysis on the combinations of local flow regimes that form global flow regimes. Flow regime classification with supervised machine learning algorithms. Data from probe signals are used for training the supervised learning algorithms. Abstract: Machine learning techniques are applied to identify the flow regimes of boiling flows in a vertical annulus channel using conductivity probe signals as the input data. The boiling dataset used in this work spans a system pressure of 198.7–907.2 kPa, a heat flux of 68–285 kW/m 2, an inlet subcooling of 3.8–11.4 ° C, a mass flux of 642.6–2465.1 kg/m 2 s, an area-averaged gas superficial velocity of 0.01–2.83 m/s, and an area-averaged liquid superficial velocity of 0.68–2.69 m/s. A two-step approach that uses the unsupervised self-organizing map (SOM) for identifying the local and global flow regimes is proposed. The cumulative distribution functions (CDFs) of bubble durations are used as the input of the SOM. The combinations of local flow regimes that form the global regimes are extensively analyzed. The radial profiles of the global flow regimes are studied where the effects of the heated inner wall and local subcooling are discussed. Furthermore, the supervised support vector machine (SVM) and the K -nearest neighbors (KNN) algorithms are trained with features extracted from the conductivity probe signals for flow regime classification, with the global flow regimes identified by the SOM as the reference. Two sets of features are generated where the first consists of four statistical features of bubble durations and the second consists of six flow features that describe the collective bubble behaviors in the flow. Using the global flow regimes identified by the SOM as the reference and the flow features dataset as the input data, the trained models are able to classify the flow regimes to an accuracy of more than 90%.