USE OF NEURAL NETWORKS IN THE ANALYSIS OF PARTICLE-SIZE DISTRIBUTIONSBY LASER DIFFRACTION

The use of techniques based on laser diffraction for measuring particl e size distributions has become increasingly popular in recent years. However, the models used to compute the results from light scattering data still do not enable the accurate application of such techniques i n highly concentrated suspensions of particles in fluids, as well as i n cases of non-spherical particles, In this paper a neural network mod el is applied to light scattering data obtained with particles in liqu id suspensions at different solid concentrations and compared with a c onventional algorithm based on Fraunhofer diffraction. The results sho w that neural network models can be successfully used to compute parti cle size distributions from laser diffraction measurements and that th is approach may expand the range of application of such techniques.