Prediction of surface tension of branched alkanes using ANN-MLP and ANN-RBF: application to bitumen recovery. (1st February 2020)

• Record Type: Journal Article
• Authors: Yang, Liping; Lu, Songfeng
• Is Part Of: Petroleum science and technology. Volume 38:Number 3(2020)
• Page Start: 279
• Page End: 287
• Publication Date: 2020-02-01
• Subjects: artificial neural network -- bitumen recovery -- branched alkanes -- multi-layer perception -- radial basis function -- surface tension; Liquid fuels -- Periodicals; Petroleum -- Periodicals; 665.505
• DOI: 10.1080/10916466.2019.1697290
• Languages: English
• ISSNs: 1091-6466

Abstract

Abstract: The viscosity of bitumen is extremely high at ambient temperature and in order to produce and transport the bitumen, it is necessary to reduce its viscosity. In this regard various n-alkane with different surface tension dilutes bitumen. This study features the application of artificial neural network for prediction of surface tension of branched alkanes. Modeling results showed that the both models are accurate and effective in prediction of surface tension of branched alkanes. However, the results were compared with experimental data and it was found that the estimated surface tension by ANN-MLP is more accurate than radial basis function network.