Machine learning for two-phase gas-liquid flow regime evaluation based on raw 3D ECT measurement data

• Autorzy: Wajman Radosław , Nowakowski Jacek , Łukiański Michał , Banasiak Robert

Identyfikatory

DOI

10.24425/bpasts.2024.148842

• Języki publikacji: EN

Abstrakty

EN

This paper presents a study on applying machine learning algorithms for the classification of a two-phase flow regime and its internal structures. This research results may be used in adjusting optimal control of air pressure and liquid flow rate to pipeline and process vessels. To achieve this goal the model of an artificial neural network was built and trained using measurement data acquired from a 3D electrical capacitance tomography (ECT) measurement system. Because the set of measurement data collected to build the AI model was insufficient, a novel approach dedicated to data augmentation had to be developed. The main goal of the research was to examine the high adaptability of the artificial neural network (ANN) model in the case of emergency state and measurement system errors. Another goal was to test if it could resist unforeseen problems and correctly predict the flow type or detect these failures. It may help to avoid any pernicious damage and finally to compare its accuracy to the fuzzy classifier based on reconstructed tomography images – authors’ previous work.

Słowa kluczowe

EN

neural networks; machine learning; data augmentation; electrical capacitance tomography; industrial process monitoring

PL

sieci neuronowe; nauczanie maszynowe; powiększanie danych; elektryczna tomografia pojemnościowa; monitorowanie procesów przemysłowych

• Wydawca: Polska Akademia Nauk, Wydział IV Nauk Technicznych
• Czasopismo: Bulletin of the Polish Academy of Sciences. Technical Sciences
• Rocznik: 2024
• Tom: Vol. 72, nr 1
• Strony: art. no. e148842
• Opis fizyczny: Bibliogr. 30 poz., rys., tab.

Twórcy

autor

Wajman Radosław

• Institute of Applied Computer Science, Lodz University of Technology, Stefanowskiego 18, 90-537 Łódź, Poland

• https://orcid.org/0000-0002-6372-5960

autor

Nowakowski Jacek

• Institute of Applied Computer Science, Lodz University of Technology, Stefanowskiego 18, 90-537 Łódź, Poland

• https://orcid.org/0000-0002-2665-5289

autor

Łukiański Michał

• Institute of Applied Computer Science, Lodz University of Technology, Stefanowskiego 18, 90-537 Łódź, Poland

autor

Banasiak Robert

• Institute of Applied Computer Science, Lodz University of Technology, Stefanowskiego 18, 90-537 Łódź, Poland

• https://orcid.org/0000-0002-1234-4949

Bibliografia

• [1] M.R. Rzasa, “The measuring method for tests of horizontal two-phase gas–liquid flows, using optical and capacitance tomography,” Nucl. Eng. Des., vol. 239, no. 4, pp. 699–707, Apr. 2009, doi: 10.1016/J.NUCENGDES.2008.12.020.
• [2] T. Rymarczyk, G. Kłosowski, A. Hoła, J. Sikora, P. Tchórzewski, and Ł. Skowron, “Optimising the use of Machine learning algorithms in electrical tomography of building Walls: Pixel oriented ensemble approach,” Measurement, vol. 188, p. 110581, Jan. 2022, doi: 10.1016/J.MEASUREMENT.2021.110581.
• [3] Z.M. Łabęda-Grudziak and M. Lipiński, “The identification method of the coal mill motor power model with the use of machine learning techniques,” Bull. Pol. Acad. Sci. Tech. Sci., vol. 69, no. 1, p. e135842, Feb. 2021, doi: 10.24425/bpasts.2021.135842.
• [4] T. Pajchrowski, P. Siwek, and A. Wójcik, “Adaptive controller design for electric drive with variable parameters by Reinforcement Learning method,” Bull. Pol. Acad. Sci. Tech. Sci., vol. 68, no. 4, pp. 1019–1030, Oct. 2020, doi: 10.24425/bpasts.2020.134667.
• [5] Q. Zhu, X. Ji, J. Wang, and C. Cai, “A machine learning-based mobile robot visual homing approach,” Bull. Polish Acad. Sci. Tech. Sci., vol. 66, no. 5, pp. 621–634, 2020, doi: 10.24425/bpasts. 2018.124278.
• [6] P. Mane, S. Sonone, N. Gaikwad, and J. Ramteke, “Smart personal assistant using machine learning,” 2017 Int. Conf. Energy, Commun. Data Anal. Soft Comput. ICECDS 2017, Jun. 2018, pp. 368–371, doi: 10.1109/ICECDS.2017.8390128.
• [7] R. Szmurło and S. Osowski, “Ensemble of classifiers based on CNN for increasing generalization ability in face image recognition,” Bull. Pol. Acad. Sci. Tech. Sci., vol. 70, no. 3, p. e141004, 2022, doi: 10.24425/bpasts.2022.141004.
• [8] J. Kryszyn and W. Smolik, “2D modelling of a sensor for electrical capacitance tomography in ECTSIM toolbox,” Informatics Control Meas. Econ. Environ. Prot., vol. 7, no. 1, pp. 146–149, Mar. 2017, doi: 10.5604/01.3001.0010.4604.
• [9] T. Rymarczyk, K. Król, E. Kozowski, T. Wołowiec, M. Cholewa-Wiktor, and P. Bednarczuk, “Application of Electrical Tomography Imaging Using Machine Learning Methods for the Monitoring of Flood Embankments Leaks,” Energies, vol. 14, no. 23, p. 8081, Dec. 2021, doi: 10.3390/EN14238081.
• [10] J.F. Conway, “The Science Behind Trash Data,” 20visioneers15. [Online]. Available: https://www.20visioneers15.com/post/trash-data
• [11] P. Teng, J. Yang, and M. Pfister, “Studies of Two-Phase Flow at a Chute Aerator with Experiments and CFD Modelling,” Model. Simul. Eng., vol. 2016, pp. 1–11, Aug. 2016, doi: 10.1155/2016/4729128.
• [12] S.L. Kiambi, H.K. Kiriamiti, and A. Kumar, “Characterization of two phase flows in chemical engineering reactors,” Flow Meas. Instrum., vol. 22, no. 4, pp. 265–271, Aug. 2011, doi: 10.1016/j.flowmeasinst.2011.03.006.
• [13] B. Vadlakonda and N. Mangadoddy, “Hydrodynamic study of two phase flow of column flotation using electrical resistance tomography and pressure probe techniques,” Sep. Purif. Technol., vol. 184, pp. 168–187, 2017, doi: 10.1016/j.seppur.2017.04.029.
• [14] M.R. Rząsa, Z. Kabza, and R. Gasz, “Wastewater flow measurement with adjustable slurge flow meter,” Przegląd Elektrotechniczny, vol. 98, no. 12, pp. 60–63, 2022, doi: 10.15199/48.2022.12.15.
• [15] H. Abdulmouti, “Bubbly Two-Phase Flow: Part II- Characteristics and Parameters,” Am. J. Fluid Dyn., vol. 4, no. 4, pp. 115–180, 2015, doi: 10.5923/j.ajfd.20140404.01.
• [16] S.S. Lafmejani, A.C. Olesen, and S.K. Kćr, “VOF modelling of gas–liquid flow in PEM water electrolysis cell micro-channels,” Int. J. Hydrogen Energy, vol. 42, pp. 16333–163442017, doi: 10.1016/j.ijhydene.2017.05.079.
• [17] J. Niderla, T. Rymarczyk, and J. Sikora, “Manufacturing planning and control system using tomographic sensors,” Inform. Control Meas. Econ. Environ. Prot., vol. 8, no. 3, pp. 29–34, Sep. 2018, doi: 10.5604/01.3001.0012.5280.
• [18] C.E. Brennen, Fundamentals of Multiphase Flows, Cambridge. Cambridge University Press, 2005.
• [19] S. Osowski, B. Sawicki, and A. Cichocki, “Computational intelligence in engineering practice,” Bull. Pol. Acad. Sci. Tech. Sci., vol. 69, no. 3, p. e137052, 2021, doi: 10.24425/bpasts.2021.137052.
• [20] Y. Zhang and X. Ai, “The identification of two-phase flow regimes using HMM model based on ERT system and PCA feature extraction,” Proc. – 2014 5th Int. Conf. Intell. Syst. Des. Eng. Appl. ISDEA 2014, Dec. 2014, pp. 1053–1055, doi: 10.1109/ISDEA.2014.232.
• [21] P. Fiderek, J. Kucharski, and R. Wajman, “Fuzzy inference for two-phase gas-liquid flow type evaluation based on raw 3D ECT measurement data,” Flow Meas. Instrum., vol. 54, pp. 88–96, 2017, doi: 10.1016/j.flowmeasinst.2016.12.010.
• [22] P. Wiedemann, A. Döß, E. Schleicher, and U. Hampel, “Fuzzy flow pattern identification in horizontal air-water two-phase flow based on wire-mesh sensor data,” Int. J. Multiph. Flow, vol. 117, pp. 153–162, Aug. 2019, doi: 10.1016/J.IJMULTIPHASEFLOW.2019.05.004.
• [23] H.B. Arteaga-Arteaga et al., “Machine learning applications to predict two-phase flow patterns,” PeerJ. Comput. Sci., vol. 7, p. e798, 2021, doi: 10.7717/PEERJ-CS.798.
• [24] F. Nie, H. Wang, Q. Song, Y. Zhao, J. Shen, and M. Gong, “Image identification for two-phase flow patterns based on CNN algorithms,” Int. J. Multiph. Flow, vol. 152, p. 104067, Jul. 2022, doi: 10.1016/J.IJMULTIPHASEFLOW.2022.104067.
• [25] M. Ezzatabadipour, P. Singh, M. D. Robinson, P. Guillen-Rondon, and C. Torres, “Deep Learning as a Tool to Predict Flow Patterns in Two-Phase Flow,” arXiv:1705.07117, May 2017, Accessed: Sep. 11, 2018. [Online]. Available: http://arxiv.org/abs/1705.07117.
• [26] J. Xiao, X. Luo, Z. Feng, and J. Zhang, “Using artificial intelligence to improve identification of nanofluid gas–liquid two-phase flow pattern in mini-channel,” AIP Adv., vol. 8, no. 1, p. 015123, Jan. 2018, doi: 10.1063/1.5008907.
• [27] Y. Zhang, A.N. Azman, K. W. Xu, C. Kang, and H.B. Kim, “Two-phase flow regime identification based on the liquid-phase velocity information and machine learning,” Exp. Fluids, vol. 61, no. 10, pp. 1–16, Oct. 2020, doi: 10.1007/S00348-020-03046-X/TABLES/7.
• [28] Y. Mi, M. Ishii, and L.H.Tsoukalas, “Flow regime identification methodology with neural networks and two-phase flow models,” Nucl. Eng. Des., vol. 204, no. 1–3, pp. 87–100, Feb. 2001, doi: 10.1016/S0029-5493(00)00325-3.
• [29] C. Shorten and T.M. Khoshgoftaar, “A survey on Image Data Augmentation for Deep Learning,” J. Big Data, vol. 6, no. 1, pp. 1–48, Dec. 2019, doi: 10.1186/S40537-019-0197-0/FIGURES/33.
• [30] J. Kryszyn, W.T. Smolik, B. Radzik, T. Olszewski, and R. Szabatin, “Switchless charge-discharge circuit for electrical capacitance tomography,” Meas. Sci. Technol., vol. 25, no. 11, p. 115009, Nov. 2014, doi: 10.1088/0957-0233/25/11/115009.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).