Predicción de la temperatura superior de disolución crítica mediante redes neuronales artificiales

  1. Gonzalo Astray 1
  2. Jorge Morales 1
  3. Juan Carlos Mejuto 1
  4. Aida Vázquez Gil 1
  1. 1 Universidade de Vigo
    info

    Universidade de Vigo

    Vigo, España

    ROR https://ror.org/05rdf8595

Journal:
Revista Iberoamericana de Polímeros

ISSN: 0121-6651 1988-4206

Year of publication: 2012

Volume: 13

Issue: 6

Pages: 295-306

Type: Article

More publications in: Revista Iberoamericana de Polímeros

Abstract

The polymer solutions are widely used in rheology and in the stabilization of commercial systems. These solutions are strongly conditioned by the system temperature and they could form a single phase or a homogeneous liquid phase mixture. To determine the upper critical solution temperature (UCST) value it has been developed a model based on Neural Networks that is able to reliably predict this temperature, making an average error in its calculation of 4.47%.