Simultaneous spectrophotometric determination of Fe and Ni with xylenol orange using principal component analysis and artificial neural networks in some industrial samples

Artificial neural networks (ANNs) are among the most popular techniques for nonlinear multivariate calibration in complicated mixtures using spectroph otometric data. In this study, Fe and Ni were simultaneously determined in aqueous medium with xylenol orange (XO) at pH 4.0. In this way, after reduc ing the number of spectral data using principal component analysis (PCA), a n artificial neural network consisting of three layers of nodes was trained by applying a back-propagation learning rule. Sigmoid transfer functions w ere used in the hidden and output layers to facilitate nonlinear calibratio n. Adjustable experimental and network parameters were optimized, 30 calibr ation and 20 prediction samples were prepared over the concentration ranges of 0-400 mu g l(-1) Fe and 0-300 mu g l(-1) Ni. The resulting R.S.E. of pr ediction (S.E.P.) of 3.8 and 4.7% for Fe and Ni were obtained, respectively . The method has been applied to the spectrophotometric determination of Fe and Ni in synthetic samples, some Ni alloys, and some industrial waste wat ers. (C) 1999 Elsevier Science B.V. All rights reserved.