An improved model for gas-liquid flow pattern prediction based on machine learning

Mask, Gene; Wu, Xingru; Ling, Kegang

doi:10.1016/j.petrol.2019.106370

Cited by 44 publications

(9 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The phenomenon occurring during displacement can also explain the phenomena of fluid mechanics, reservoir physics, and other disciplines, and helps understand the dynamics of underground fluids. At the same time, it also complements and validates traditional core displacement experiments and numerical simulation experiments (Guo et al, 2018;Mask et al, 2019;Zhang et al, 2019).…”

Section: Introductionmentioning

confidence: 62%

Evaluating the Effect of Oil-Displacing Agents Using Computer Graphics and Visualization Glass Plate Model Experiments

Sun

Ren

et al. 2021

Front. Energy Res.

View full text Add to dashboard Cite

The results of visualization experiments primarily provide descriptions of local features or a general conclusion because, to obtain accurate numerical results, it is necessary to count each small point in the visual image and calculate the remaining oil based on the color. There is currently no method that can automatically and accurately calculate the recovery factor based on a visualized image. Computer graphics can be used to solve this problem, and Matlab software with its powerful image calculation functions was used to analyze and calculate images of visualization experiment processes. This article first summarizes the development and respective characteristics of the visual experiment evaluation of oil displacement agents. Then, the corresponding relationship between the actual oil displacement recovery parameters and the image parameters is introduced in detail, and a calculation formula for the visual image recovery factor is summarized. Finally, using the quantitative visual experimental results from different oil displacement agent injection methods as an example, we compared the different oil displacement processes and their recovery. The different characteristics of the two injection methods were evaluated, and the feasibility of the calculation method was verified. This method provides data support for interpreting visual experimental processes and a description of the experimental results. This provides a clear and unified calculation method for the recovery factors of oil displacement processes, which often involve many difficult-to-compare processes.

show abstract

Section: Introductionmentioning

confidence: 62%

Evaluating the Effect of Oil-Displacing Agents Using Computer Graphics and Visualization Glass Plate Model Experiments

Sun

Ren

et al. 2021

Front. Energy Res.

View full text Add to dashboard Cite

show abstract

“…As early as 1995, Ternyik et al [9] established a prediction model of BHP based on ANN according to the three-phase flow law of oil, gas and water, and compared the field data to verify the feasibility of the neural network model of BHP. Subsequently, several scholars have used machine learning methods and built different types of ANN models to predict BHP, such as Mohammadpoor et al [10], Jahanandish et al [11], Chen et al [12], Spesivtsev et al [13], Mask et al [14], Sami and Ibrahim [1], and Okoro et al [15]. The prediction results from these studies all indicate the following similarities:…”

Section: Introductionmentioning

confidence: 95%

A Hybrid Neural Network Model for Predicting Bottomhole Pressure in Managed Pressure Drilling

et al. 2022

View full text Add to dashboard Cite

Managed pressure drilling (MPD) is an essential technology for safe and efficient drilling in deep high-temperature and high-pressure formations with narrow safety pressure windows. However, the complex conditions in deep wells make the mechanism of multiphase flow in drilling annulus complicated and increase the difficulty for accurate prediction of bottomhole pressure (BHP). Recently, an increasing volume of research shows that intelligent technology is an efficient means of accurately predicting BHP. However, few studies have focused on the temporal properties and variation mechanism of BHP. In this paper, hybrid neural network prediction models based on the multi-branch parallel are established by combining the different advantages of back propagation (BP), long short-term memory (LSTM), and a one-dimensional convolutional neural network (1DCNN) model. The results show that the relative error of the best model is about 70% lower than the optimal single intelligent model. Preliminary experimental results reveal that the hybrid models combine the advantages of different single models, which is more accurate and robust for extracting the temporal features of MWD. Finally, based on the trend analysis, the validity of the hybrid model is further verified. This study provides a reference for solving the problem of optimizing temporal characteristics and guidance for fine pressure control in complex formations.

show abstract

“…Multiple other studies are based on fluid property experimental data using support vector machines, neural networks, or deep learning as a machine learning tool. Some of the related work was conducted by Osman (2004) 2020) [30][31][32][33][34][35][36]. The studies prove machine learning is an effective tool for predicting flow patterns based on pipe characteristics, superficial velocities, and other fluid properties.…”

Section: Application Of Machine Learning In Multiphase Flow Modelingmentioning

confidence: 99%

Machine Learning Augmented Two-Fluid Model for Segregated Flow

Rastogi¹,

Fan

2021

Fluids

View full text Add to dashboard Cite

Segregated flow, including stratified and annular flows, is commonly encountered in several practical applications such as chemical, nuclear, refrigeration, and oil and gas industries. Accurate prediction of liquid holdup and the pressure gradient is of great importance in terms of system design and optimization. The current most widely accepted model for segregated flow is a physics-based two-fluid model that treats gas and liquid phases separately by incorporating mass and momentum conservation equations. It requires empirically derived closure relationships that have the limitation of being applicable only under a narrow range of input parameters under which they were developed. In this paper, we proposed a more generalized machine learning augmented two-fluid model, using a database that spans the range of various flowing conditions and fluid properties. Machine learning algorithms such as random forest, neural networks, and gradient boosting were tested for the best performing data-driven predictive model. The new model proposed in this work successfully captures the complex, dynamic, and non-linear relationships between the friction factor and flowing conditions. A comprehensive model evaluation against nineteen existing correlations shows the best results from the proposed model.

show abstract

An improved model for gas-liquid flow pattern prediction based on machine learning

Cited by 44 publications

References 15 publications

Evaluating the Effect of Oil-Displacing Agents Using Computer Graphics and Visualization Glass Plate Model Experiments

Evaluating the Effect of Oil-Displacing Agents Using Computer Graphics and Visualization Glass Plate Model Experiments

A Hybrid Neural Network Model for Predicting Bottomhole Pressure in Managed Pressure Drilling

Machine Learning Augmented Two-Fluid Model for Segregated Flow

Contact Info

Product

Resources

About