A Neural Network model for estimating the particle size distribution of a polymer latex from combined ELS and DLS measurements

17) STEGMAYER G., GUGLIOTTA L., CHIOTTI O., VEGA J.,

Rio de Janeiro

Congreso; Macro 2006 - World Polymer Congress, 41 Simposio Internacional de Macromoléculas; 2006

A method is proposed for estimating the particle size distribution (PSD) of a latex from combined elastic light scattering (ELS) and dynamic light scattering (DLS) measurements. The method is implemented through a generalized regression neural network (GRNN), that estimates the PSD from the ELS measurements carried out at several angles together with the average diameters of the PSD predicted by DLS at the same angles. The GRNN was trained with several measurements simulated on the basis of typical asymmetric PSDs. The ability of the trained GRNN was tested through two synthetic examples. The estimated PSDs are more accurate than those obtained through standard regularization techniques used for solving “ill-conditioned” inverse problems.