Rigorous modeling of viscosity of branched alkanes using ANFIS optimized with evolutionary algorithm

ABSTRACT

In the current study, prediction of the viscosity of branched alkanes was considered using the adaptive network-based fuzzy inference system optimized with an evolutionary algorithm named differential evolution (DE). The outcomes of the model were compared with the experimental data. A good agreement between experimental data and adaptive neuro-fuzzy inference system (ANFIS) outcomes was observed. Graphical and statistical analysis were performed. Then, the values of the statistical parameters R², RMSE, and AARD% reveal that the ANFIS model is accurate. Results showed that the developed model accurately predicts the experimental data with an overall R² and AARD% values of 0.985 and 0.657%, respectively. Results indicate that the DE-ANFIS is accurate and robust for the prediction of viscosity of alkanes.

KEYWORDS:

• Viscosity
• branched n-alkane
• ANFIS
• predictive modeling
• evolutionary algorithm

Additional information

Notes on contributors

Xijian Fan

Xijian Fan is now a professor in the College of Information Science Technology, Nanjing Forestry University.