Premium
Biodiesel conversion modeling under several conditions using computational intelligence methods
Author(s) -
Mohadesi Majid,
Rezaei Abbas
Publication year - 2018
Publication title -
environmental progress and sustainable energy
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.495
H-Index - 66
eISSN - 1944-7450
pISSN - 1944-7442
DOI - 10.1002/ep.12698
Subject(s) - mean squared error , adaptive neuro fuzzy inference system , artificial neural network , biodiesel , correlation coefficient , coefficient of determination , mean absolute percentage error , matlab , approximation error , transesterification , engineering , computer science , mathematics , methanol , machine learning , algorithm , fuzzy logic , chemistry , statistics , artificial intelligence , fuzzy control system , catalysis , organic chemistry , operating system
The computational intelligence (CI) methods such as artificial neural network (ANN) and adaptive neuro‐fuzzy inference system (ANFIS) have many applications in chemistry, oil and gas, electronics, financial, telecommunications, and many others. In this article, ANN and ANFIS are used to model and predict the biodiesel conversion under several conditions. The inputs of the proposed CI models are oil type, catalyst type, calcination temperature, catalyst concentration, methanol‐to‐oil ratio, n ‐hexane‐to‐oil volume ratio, reaction time, and reaction temperature and the output is biodiesel conversion. Experimental data of available literature are used to train and test the CI models in MATLAB 7.0.4 software. Comparison between the proposed ANN and ANFIS models and the experimental data show that the proposed CI models are very efficient and fast tools, and there is a good agreement between them and the experimental data with a minimum error. Also, it can be found that the introduced ANN model is more accurate than the ANFIS model. The proposed ANN model has overall MRE% (mean relative error percentage) <1.5%, RMSE (root mean square error) <1.34, R (correlation coefficient) >0.9995, and MAE (mean absolute error) <0.9. © 2017 American Institute of Chemical Engineers Environ Prog, 37: 562–568, 2018