Performance optimisation of forward-osmosis membrane system using machine learning for the treatment of textile industry wastewater

Forward osmosis (FO) is an emerging low energy membrane-based technology and can be applied if the diluted draw solution (DS) directly utilized without additional recovery/treatment. In this study, FO process was for treatment of textile industry wastewater using fertilizer as DS. This paper focuses on modelling optimisation machine learning techniques like Response Surface Methodology (RSM), Artificial Neural Network (ANN) Adaptive Neuro-Fuzzy Inference System (ANFIS). To model process, central composite design to examine effect initial concentration, feed time, pH temperature water flux reverse salt flux. The optimum (8.527 L.m?2.h?1 (LMH)) (7.246 g.m?2.h?1 (GMH)) obtained concentration 1.625 M, 1090 mg/L, reaction time 90 min, 7.33 35 °C. Under these conditions, performance carried out experimentally validated with models. developed by ANN RSM considerably better than that other models in terms precision predicting flux, respectively. About six different chemical solutions were screened tested at conditions identify best suitable DS wastewater. results indicate Diammonium Phosphate (DAP) along Potassium Chloride (KCl) gave respect