Application of artificial neural networks for response surface modelling in HPLC method development

This paper discusses the usefulness of artificial neural networks (ANNs) for response surface modelling in HPLC method development. In this study, the combined effect of pH and mobile phase composition on the reversed-phase liquid chromatographic behaviour of a mixture of salbutamol (SAL) and guaiphenesin (GUA), combination I, and a mixture of ascorbic acid (ASC), paracetamol (PAR) and guaiphenesin (GUA), combination II, was investigated. The results were compared with those produced using multiple regression (REG) analysis. To examine the respective predictive power of the regression model and the neural network model, experimental and predicted response factor values, mean of squares error (MSE), average error percentage (Er%), and coefficients of correlation (r) were compared. It was clear that the best networks were able to predict the experimental responses more accurately than the multiple regression analysis.