Prediction of thiophene removal from diesel using [BMIM][AlCl4] in EDS Process: GA-ANFIS and PSO-ANFIS modeling

摘要

In this study, the treatment capability of 1-butyl-3-methylimidazolium tetrachloroaluminate [BMIM] [AlCl4] ionic liquid was investigated in a diesel fuel containing thiophene. The effects of operating parameters including the volumetric ratio of ionic liquid to model fuel, extraction temperature and time have been studied. Then, a neuro-fuzzy inference system (ANFIS) tuned by particle swarm optimization (PSO) algorithm has been developed to predict the sulphur removal from diesel fuel using [BMIM][AlCl4] in EDS process. The outputs were in a good agreement with the experimental data, and the model tuned by PSO predicts the data better than ANFIS and ANFIS tuned by GA.