深度學習結合分子結構準確預測界面張力

doi:10.1016/j.molliq.2020.114571

淡江大學機構典藏 > 工學院 > 化學工程與材料工程學系暨研究所 > 期刊論文 > Item 987654321/120172

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/120172

题名:	深度學習結合分子結構準確預測界面張力
其它题名:	Molecular structure incorporated deep learning approach for the accurate interfacial tension predictions
作者:	Yang, Yan-Ling;Tsao, Heng-Kwong;Sheng, Yu-Jane
关键词:	Deep learning approach;Deep neural network;Molecular structure, interfacial tension;Water-organic fluid interfaces
日期:	2021-02
上传时间:	2021-03-12 12:11:05 (UTC+8)
摘要:	Characterization of the interface of a two-phase system by interfacial tension (IFT) imposes a great impact on the chemical and environmental engineering. In this work, a deep neural network (DNN) approach was developed to estimate IFT of water-hydrocarbon and water-alcohol interfaces. The predictive power of this approach for IFT was found to be much more improved than those of the previously proposed empirical correlations, both qualitatively and quantitatively. The input vector of two-phase systems generally contains five parameters, including critical temperature, critical pressure, and density difference, in addition to temperature and pressure. In this approach, a line notation describing the molecular structure of chemical species was also taken as an input. The most accurate results with the root-mean-square error (RMSE) of 1.28 mN/m are acquired as all six parameters are included. However, our analyses show that density difference and molecular structure are much more important than the critical properties. As a result, the DNN approach with the input vector involving molecular structure, temperature, and pressure only is able to yield sufficiently accurate results (RMSE 1.71 mN/m), and can successfully depict the descending, ascending, and concave dependences of IFT on temperature.
關聯:	Journal of Molecular Liquids 323, 114571
DOI:	10.1016/j.molliq.2020.114571
显示于类别:	[化學工程與材料工程學系暨研究所] 期刊論文

文件中的档案:

档案	描述	大小	格式	浏览次数
index.html		0Kb	HTML	71	检视/开启

在機構典藏中所有的数据项都受到原著作权保护.

TAIR相关文章

数据加载中.....