Development and comparison of non-parameter regression methods for prediction of cell voltage and current efficiency in a lab scale chlor-alkali membrane cell

Abstract

This article presents the development & comparison of Non-parameter Regression Methods such as Artificial neural network (ANN), Genetic algorithm optimization (GA) and Support vectormachine (SVM) models for the prediction of cell voltage and caustic current efficiency (CCE) versus different operating parameters in a lab scale chlor-alkali membrane cell. In order to validate the model predictions, the effects of various operating parameters on the cell voltage and CCE of the membrane cell were experimentally investigated. Each of six process parameters including anolyte pH (2–5), operating temperature (25–90°C), electrolyte velocity (1.3–5.9 cm/s), brine concentration (200–300 g/L), current density (1–4 kA/m2), and run time (up to 150 min) were thoroughly studied. The new models yielded the accurate prediction of experimental data with the lowest standard deviation error (SD). It was found that the developed models are not only capable to predict the voltage and CCE but also to reflect the impacts of process parameters on the same functions. According to the obtained results, SVM model is suitable for the prediction of CCE with an average deviation of 1.53% while GA & ANN models are more accurate than SVM model for predicting the voltage with an AD of 1.21% & 1.27%, respectively.