EVALUATION OF NATURAL COMPUTATION TECHNIQUES IN THE MODELING AND OPTIMIZATION OF A SEQUENTIAL INJECTION FLOW SYSTEM FOR COLORIMETRIC IRON(III) DETERMINATION

The present study shows and gives evidence of the applicability of nat ural computation techniques in the modelling and optimization of a seq uential injection flow system of analysis for colorimetric iron(III) d etermination in water samples. The reaction with thiocyanate is used a s reagent colour. A neural network consisting of two hidden layers, ea ch one formed by eight neurons, was used to model the system, Optimiza tion of the system in terms of sensitivity, linearity and sampling rat e was carried out by using jointly the neural network and genetic algo rithms. The latter were used with a set of 50 crossed and mutated chro mosomes over 100 generations. In the system thus developed, 140 mu l o f sample and 70 mu l of reagent were sequentially introduced into the holding coil and propelled toward the detector at a flow of 5 ml/min. The system gave a sampling rate of 110 samples per hour, A comparison of the results obtained in the analysis of six samples with those obta ined using the reference method (atomic absorption spectrophotometry) showed the high quality of results provided.