Optimization and prediction of safranin-O cationic dye removal from aqueous solution by emulsion liquid membrane (ELM) using artificial neural network-particle swarm optimization (ANN-PSO) hybrid model and response surface methodology (RSM)

Abstract

The cationic dye safranin-O was removed from an aqueous solution using the Emulsion Liquid membrane (ELM) method. The ELM system consists of a diluent (hexane) and a surfactant (Span 80). Sulfuric acid (H2SO4) solution was used as an internal aqueous phase. The key parameters regulating the safranin-O dye removal were investigated. Twenty-nine (29) experiments were conducted, with various parameters impacting the removal of the cationic dye safranin-O from aqueous solution using the ELM approach, including surfactant content and internal phase concentration in H2SO4 dye concentration and stirring speed. The RSM with Box–Behnken Design (BBD) was used to optimize and predict the ELM safranin-O cationic dye removal experiments. The model produces 99.68% separated safranin-O in under 2 min of contact time with optimal operation conditions. Furthermore, for forecasting the removal of the cationic dye safranin-O from an aqueous solution by ELM technique, a novel optimization approach based on merging an artificial neural network (ANN) algorithm with a metaheuristic technique, namely PSO, has been proposed. The PSO technique was used to determine the optimal ANN parameter values.