Enhancing Accuracy in Gas-Water Two-Phase Flow Sensor Systems Through Deep-Learning-Based Computational Framework

被引：0

作者：

Bao, Minghan ^{[1
]}

Wu, Rining ^{[2
]}

Wang, Mi ^{[1
]}

Li, Kang ^{[3
]}

Jia, Xiaodong ^{[1
]}

机构：

[1] Univ Leeds, Sch Chem & Proc Engn, Leeds LS2 9JT, W Yorkshire, England

[2] Univ Leeds, Sch Comp Sci, Leeds LS2 9JT, W Yorkshire, England

[3] Univ Leeds, Sch Elect & Elect Engn, Leeds LS2 9JT, W Yorkshire, England

来源：

IEEE SENSORS JOURNAL | 2024年 / 24卷 / 23期

关键词：

Deep learning; fluid flow measurement; neural networks; sensor systems; tomography; ELECTRICAL-RESISTANCE TOMOGRAPHY; CROSS-VALIDATION; NETWORKS; RATES; OIL;

D O I：

10.1109/JSEN.2024.3475292

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Multiphase flow is a critical component in contemporary industrial operations, yet the accurate quantification of multiphase parameters presents a substantial obstacle. This research enhances gas-water two-phase flow measurement accuracy via a deep learning framework, leveraging a multisensor array in a laboratory-simulated dual-layer pipeline. Employing electrical resistance tomography (ERT), electromagnetic flow meters (EMFs), and temperature and pressure sensors, it captures real-time data for a deep learning model integrating a classical drift flux model (DFM) for a nonintrusive, comprehensive measurement system. Two models, 1-D convolutional bidirectional long short-term memory neural network (1D CNN-BiLSTM) and multiphase flow estimation neural network (MFENet)-featuring positional encoding, multiattention mechanisms, and a sliding window-were developed. Testing across 185 different flow conditions demonstrated superior precision of MFENet in flow predictions with the average relative errors of 2.45% for gas volumetric flow rate and 1.38% for water volumetric flow rate, outperforming 1D CNN-BiLSTM. This emphasizes the capability of deep learning to improve the accuracy of multiphase flow measurement techniques.

引用

页码：39934 / 39946

页数：13

共 58 条

[21] Wang M., Inverse solutions for electrical impedance tomography based on conjugate gradients methods, Meas. Sci. Technol, 13, 1, pp. 101-117, (2002)
[22] Abam F.I., Dilibe N.I., Nwankwojike B.N., Diemuodeke O., John I., Comparative evaluation of homogenous and drift-flux models for a three-phase downward flow in a pipe, Sci. Afr, 13, (2021)
[23] Soprano A.B., Ribeiro G.G., Da Silva A.F., Maliska C.R., Solution of a one-dimensional three-phase flow in horizontal wells using a drift-flux model, Mecanica Computacional, 29, 89, pp. 8767-8779, (2010)
[24] Dong C., Hibiki T., Drift-flux parameter modeling of vertical downward gas-liquid two-phase flows for interfacial drag force formulation, Nucl. Eng. Des, 378, (2021)
[25] Shi H., Et al., Drift-flux modeling of two-phase flow in wellbores, SPE J, 10, 1, pp. 24-33, (2005)
[26] Wang J., Yu L.-C., Lai K.R., Zhang X., Dimensional sentiment analysis using a regional CNN-LSTM model, Proc. 54th Annu. Meeting Assoc. Comput. Linguistics, pp. 225-230, (2016)
[27] Lu W., Li J., Li Y., Sun A., Wang J., A CNN-LSTM-based model to forecast stock prices, Complexity, 2020, pp. 1-10, (2020)
[28] Mehtab S., Sen J., Stock price prediction using CNN and LSTM-based deep learning models, Proc. Int. Conf. Decision Aid Sci. Appl. (DASA), pp. 447-453, (2020)
[29] Hou J., Wang Y., Zhou J., Tian Q., Prediction of hourly air temperature based on CNN-LSTM, Geomatics, Natural Hazards Risk, 13, 1, pp. 1962-1986, (2022)
[30] Fan M., Imran O., Singh A., Ajila S.A., Using CNN-LSTM model for weather forecasting, Proc. IEEE Int. Conf. Big Data (Big Data), pp. 4120-4125, (2022)

← 1 2 3 4 5 6 →