Neural network and experimental design to investigate the effect of five factors in ion-interaction high-performance liquid chromatography

The effect of five experimental parameters on the ion-interaction chromatographic retention of pesticides characterized by different polarity was investigated by means of experimental design and artificial neural network treatments. The factors considered were: (1) the mobile phase pH; (2) N, the alkyl-chain length of the IIR (ion-interaction reagent); (3) CM, the organic modifier concentration in the mobile phase (4) CR, the concentration of IIR and (5) F, the flow-rate. The use of fractional design and Hoke design allowed useful information to be drawn about the retention mechanism involved and to build, through artificial neural network treatment (ANN), a model characterised by both descriptive and predictive ability. Four neurons and a bias unit were employed. The ANN proved to be a useful instrument in the optimisation of the chromatographic separation, as regards resolution and total analysis time: the experimental retention obtained in the optimal conditions always differed within 14% from the predicted ones.