COMPARISON OF A RADIAL NEURAL NETWORK MODEL WITH A GENETIC ALGORITHM FOR ESTIMATING THE PARTICLE SIZE DISTRIBUTION OF A LATEX

GEORGINA STEGMAYER, LUIS A. CLEMENTI, JORGE R. VEGA

Santa Fe, Argentina

Conferencia; XXXIV Conferencia Latinoamericana de Informatica; 2008

This paper presents the comparison of an Artificial Neural Network (ANN)-based model and a Genetic Algorithm (GA) as independent tools for estimating the particle size distribution (PSD) of a polymer latex, which is an important physical characteristic that determines some end-use properties of the material. The PSD of a dilute latex is estimated from dynamic light scattering (DLS) measurements, taken at several angles. To this effect, an ANN-based model and GAs are used as a tool for solving the involved ill-conditioned inverse problem. Both models are trained with a large set of measurements simulated from typical asymmetric PSDs, represented by unimodal and bimodal normal-logarithmic distributions of variable geometric mean diameters and variances. The proposed approaches are evaluated on the basis of both simulated and experimental examples.