I-optimal designs for antoines equationA genetic algorithm approach

  1. Carlos de la Calle Arroyo
  2. Miguel Ángel González Fernández
  3. Jesús López Fidalgo
  4. Licesio Jesús Rodríguez Aragón
Libro:
Proceedings of the 35th International Workshop on Statistical Modelling : July 20-24, 2020 Bilbao, Basque Country, Spain
  1. Itziar Irigoien (ed. lit.)
  2. Dae-Jin Lee (ed. lit.)
  3. Joaquín Martínez-Minaya (ed. lit.)
  4. María Xosé Rodríguez- Álvarez (ed. lit.)

Editorial: Servicio Editorial = Argitalpen Zerbitzua ; Universidad del País Vasco = Euskal Herriko Unibertsitatea

ISBN: 978-84-1319-267-3

Año de publicación: 2020

Páginas: 322-325

Congreso: International Workshop on Statistical Modelling (35. 2020. Bilbao)

Tipo: Aportación congreso

Resumen

In the distillation processes it is very important to know precisely the relationship between temperature and vapor pressure. The vapor pressures not only depend on the temperature but vary enormously for di erent substances. The study of optimal designs for the estimation of the parameters of Antoine equation, according to the I-optimality criterion is shown. It is particularly interesting for this model due to the importance of prediction on boundary regions of the space of the design, which usually correspond to the proximity of state change points. Genetic algorithms are one of the several nature-inspired algorithms, mainly used for the calculation of optimal solutions to problems that are hard to solve through direct algorithms. A genetic algorithm that nd optimizes the designs presented in this work has been developed.