Quantitative analysis of diclofenac sodium powder via near-infrared spectroscopy combined with artificial neural network

Abstract

A method for quantitative analysis of diclofenac sodium powder on the basis of near-infrared (NIR) spectroscopy is investigated by using of orthogonal projection to latent structures (O-PLS) combined with artificial neural network (ANN). 148 batches of different concentrations diclofenac sodium samples were divided into three groups: 80 training samples, 46 validation samples and 22 test samples. The average concentration of diclofenac sodium was 27.80%, and the concentration range of all the samples was 15.01–40.55%. O-PLS method was applied to remove systematic orthogonal variation from original NIR spectra of diclofenac sodium samples, and the filtered signal was used to establish ANN model. In this model, the concentration of diclofenac sodium was determined. The degree of approximation was employed as selective criterion of the optimum network parameters. In order to compare with O-PLS–ANN model, principal component artificial neural network (PC-ANN) model and calibration models that use different preprocessing methods (first derivative, standard normal variate (SNV) and multiplicative scatter correction (MSC)) of the original spectra were also designed. In addition, partial least squares regression (PLS) models were also established to compare with ANN models. Experimental results show that O-PLS–ANN model is the best.