Predicting emulsion breakdown in the emulsion liquid membrane process: Optimization through response surface methodology and a particle swarm artificial neural network

• Published in: Chemical engineering and processing 2022-06, Vol.176, p.108956, Article 108956
• Main Authors: Fetimi, Abdelhalim, Dâas, Attef, Merouani, Slimane, Alswieleh, Abdullah M., Hamachi, Mourad, Hamdaoui, Oualid, Kebiche-Senhadji, Ounissa, Yadav, Krishna Kumar, Jeon, Byong-Hun, Benguerba, Yacine
• Format: Article
• Language: English
• Subjects: ANN-PSO algorithm; Artificial neural network (ANN); Emulsion breakage; Emulsion liquid membrane (ELM); Particle swarm optimization (PSO); Water pollution
• ISSN: 0255-2701; 1873-3204
• DOI: 10.1016/j.cep.2022.108956

•A novel method is proposed for predicting the emulsion breakage by the ELM process.•Artificial neural network (ANN) and particle swarm optimization (PSO) are coupled.•PSO algorithm is employed to model, optimize and found out the best parameters (weights and thresholds) of ANN.•A comprehensive relative importance analysis method is proposed.•The proposed combined model (ANN-PSO) demonstrates its effectiveness and robustness compared with RSM model. To anticipate emulsion breakdown in the ELM process, the Box–Behnken design was used with an artificial neural network (ANN) and a metaheuristic approach, namely particle swarm optimization (PSO) and response surface methodology (RSM). Membrane stability testing began with an experimental component to collect data. The following parameters were used to estimate membrane breakdown: emulsification time (3–7 min), surfactant loadings (2–6% v/v), internal phase concentration ([Na2CO3]: 0.01–1 mg L−1), external phase to w/o emulsion volume ratio (1–11), and internal aqueous phase to membrane volume ratio (0.5 to 1.5). The PSO algorithm was used to determine the optimal ANN parameter values. The hybrid ANN-PSO model outperformed the RSM in identifying optimal ANN parameters (weights and thresholds) and accurately forecasting emulsion breaking percentages throughout the ELM process. The hybrid ANN-PSO method may be a valuable optimization tool for predicting critical data for ELM stability under various operating conditions. [Display omitted]