期刊
JOURNAL OF NATURAL GAS SCIENCE AND ENGINEERING
卷 26, 期 -, 页码 1306-1316出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.jngse.2015.08.036
关键词
Multiphase flow; Pressure drop; Neural network; Taguchi design; Artificial intelligence
The pressure drop in tubing constitutes a major part of the total pressure drop. However, its calculation is very complex due to the possibility of presence of multiple phases. A number of empirical and mechanistic methods have been proposed for multiphase flows. Each method had its own assumptions, which often reduce the calculation accuracy of the actual pressure drop. In this study, the best probable model was developed by employing the Artificial Neural Network (ANN) and training this network using Levenberg-Marquardt (LM), Genetic algorithm (GA), and Particle Swarm Optimization (PSO). A total number of 1740 data collected from the wells in Middle East region were used to train and test the ANN. Taguchi design was used to optimize GA and PSO parameters. The trend analysis test carried out to prove the model stability and its ability to simulate the physical process of the problem. The comparison between the best obtained results and the results of the available methods indicated the higher accuracy of the proposed method. (C) 2015 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据