Artificial neural networks and support vector regression modeling for prediction of some silver colloidal suspensions rheological behavior

For processing purposes of silver colloidal suspensions in view of specific applications, this study evaluates the suitability of using alginate/lignosulfonate mixtures as an efficient dispersion matrix for the silver nanoparticles. The rheological behavior of the in situ obtained silver nanoparticle suspensions was investigated by rotational measurements performed using cone-plate geometry, considering the dispersion composition. All the studied nanoparticle suspensions showed a non-Newtonian behavior, irrespective of nanoparticle content. For a theoretical estimation of the experimental data, artificial neural networks and support vector regression are used as modeling tools. The comparative investigation of the experimental data with simulation results showed a high accuracy with both artificial neural networks and support vector regression models, especially for shear stress - shear rate dependence.