Premium
Using Neural Networks or Linear Models to Predict the Characteristics of Microcapsules Containing Phase Change Materials
Author(s) -
Sánchez Luz,
Sánchez Paula,
De Lucas Antonio,
Carmona Manuel,
Rodríguez Juan Francisco
Publication year - 2010
Publication title -
macromolecular symposia
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.257
H-Index - 76
eISSN - 1521-3900
pISSN - 1022-1360
DOI - 10.1002/masy.201050123
Subject(s) - phase change , materials science , artificial neural network , biological system , computer science , thermodynamics , artificial intelligence , physics , biology
Summary: Microcapsules with large amount of PRS® paraffin wax encapsulated and narrow size distribution were prepared by shirasu porous glass (SPG) emulsification technique and a subsequent suspension like polymerization process and then examined by DSC, laser diffraction and SEM analyses. An experimental design approach, based on a central composite design, was used to determine quantitatively the effect of PRS® paraffin wax/styrene mass ratio (PRS/St), percentage of polyvinylpyrrolidone/styrene mass ratio (%PVP/St) and water/styrene mass ratio (H 2 O/St) on the microparticles properties. The results were fitted using two black‐box models. The empirical equations allow the prediction of the amount of the paraffin wax encapsulated and the mean particle size in number as a function of aforementioned synthesis variables. It was observed that both models allowed to drawn the same conclusions. %PVP/St mass ratio was the most important parameter affecting the particle size distribution decreasing the average particle size with the increase of %PVP/St. On the other hand, PRS/St mass ratio has a direct influence on the latent heat of fusion.