ANFIS-GA modeling of dynamic viscosity of N-Alkane in different operational conditions. (18th July 2018)

• Record Type: Journal Article
• Authors: Fallah, Ali; Zarei, Fariba; Zarrabi, Houman; Lariche, Milad Janghorban; Baghban, Alireza
• Is Part Of: Petroleum science and technology. Volume 36:Number 14(2018)
• Page Start: 1015
• Page End: 1021
• Publication Date: 2018-07-18
• Subjects: ANFIS-GA -- dynamic viscosity -- n-alkane -- reservoir condition -- predicting model; Liquid fuels -- Periodicals; Petroleum -- Periodicals; 665.505
• DOI: 10.1080/10916466.2018.1458117
• Languages: English
• ISSNs: 1091-6466

Abstract

ABSTRACT: Viscosity is known as one of major properties of fluids which have straight effects on different parts of chemical and petroleum industries. Due to this importance, in the present work, adaptive neuro-fuzzy interference system (ANFIS) was coupled with genetic algorithm (GA) to predict dynamic viscosity of normal alkane in terms of molecular weight of n-alkane, temperature and pressure. In order to prepare and validate the predicting model 228 experimental data points were extracted from the literature. The outputs of this predictive tool were compared with the experimental data and comparisons showed that predicted dynamic viscosities have good agreement with experimental data. According to the statistical and graphical analyses this simple tool can be used as a rigorous and accurate method for prediction of dynamic viscosity of n-alkane, especially at reservoir conditions.