Abstract
In this paper, we propose a deep-learning-based method using a convolutional neural network (CNN) to predict the volume flow rates of individual phases in the oil–gas–water three-phase intermittent flow simultaneously by analyzing the measurement data from multiple sensors, including a temperature sensor, a pressure sensor, a Venturi tube and a microwave sensor. To build datasets, a series of experiments for the oil–gas–water three-phase intermittent flow in a horizontal pipe, in which gas volume fraction and water-in-liquid ratio ranges are 23.77–94.45% and 14.95–86.97%, respectively, and gas flow superficial velocity and liquid flow superficial velocity ranges are 0.66–5.23 and 0.27–2.14 m/s, respectively, have been carried out on a test loop pipeline. The preliminary results indicate that the model can provide relative prediction errors on the testing-1 dataset for the volume flow rates of oil-phase, gas-phase and water-phase within ±10% with 94.49%, 92.56% and 95.71% confidence levels, respectively. Additionally, the prediction results on the testing-2 dataset also demonstrate the generalization ability of the model. The consuming time of a prediction with one sample is 0.43 s on an Intel Xeon CPU E5-2678 v3, and 0.01 s on an NVIDIA GeForce GTX 1080 Ti GPU. Hence, the proposed CNN-based prediction model, which can fulfill the real-time application requirements in the petroleum industry, reveals the potential of using deep learning to obtain accurate results in the multiphase flow measurement field.
Highlights
Multiphase flow is mixture flow of different components or phases, which widely exist in many industry fields, such as oil field exploitation, chemical engineering, and the metallurgical industry
We carried out various experiments on a test loop pipeline in the 50 mm diameter, in which Gas volume fraction (GVF) and Water-in-liquid ratio (WLR) ranges are 23.77–94.45% and 14.95–86.97%, respectively, and the gas flow superficial velocity range is 0.66–5.23 m/s and the liquid flow superficial velocity range is 0.27–2.14 m/s
We find that the proposed convolutional neural network (CNN)-7 can simultaneously predict the volume flow rates of three different flow phases of the oil–gas–water threephase intermittent flow
Summary
Multiphase flow is mixture flow of different components or phases, which widely exist in many industry fields, such as oil field exploitation, chemical engineering, and the metallurgical industry. Yan presented a method based on a multilayer feedforward neural network and conductance probes to obtain the gas and liquid flow rates of an air–water two-phase slug flow [12]. From the perspective of combining deep learning with the petroleum industry, this paper is trying to explore the data-driven black-box soft-sensing methods for complex systems such as Sensors 2021, 21, 1245 an oil–gas–water three-phase intermittent flow by using recently booming deep learning techniques to analyze the measured data from cost-effective sensors, which may bring new data analytics into the multiphase flow measurement and extend the application of deep learning. In this paper, based on the convolutional neural network (CNN), the volume flow rate prediction model for the oil–gas–water three-phase intermittent flow is proposed to organically integrate the measurement data from the multiple sensors which are mounted in the horizontal pipe of our experimental setup.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
