SCI和EI收录∣中国化工学会会刊

›› 2010, Vol. 18 ›› Issue (5): 817-823.

• • 上一篇    下一篇

Prediction of Flash Point Temperature of Organic Compounds Using a Hybrid Method of Group Contribution+Neural Network+Particle Swarm Optimization

Juan A. Lazzús   

  1. Department of Physics, University of La Serena, Casilla 554, La Serena, Chile
  • 收稿日期:2009-09-18 修回日期:2010-05-20 出版日期:2010-10-28 发布日期:2010-10-28
  • 通讯作者: Juan A. Lazzús,E-mail:jlazzus@dfuls.cl E-mail:jlazzus@dfuls.cl

Prediction of Flash Point Temperature of Organic Compounds Using a Hybrid Method of Group Contribution+Neural Network+Particle Swarm Optimization

Juan A. Lazzús   

  1. Department of Physics, University of La Serena, Casilla 554, La Serena, Chile
  • Received:2009-09-18 Revised:2010-05-20 Online:2010-10-28 Published:2010-10-28

摘要: The flash points of organic compounds were estimated using a hybrid method that includes a simple group contribution method (GCM) implemented in an artificial neural network (ANN) with particle swarm optimization (PSO). Different topologies of a multilayer neural network were studied and the optimum architecture was determined. Property data of 350 compounds were used for training the network. To discriminate different substances the molecular structures defined by the concept of the classical group contribution method were given as input variables. The capabilities of the network were tested with 155 substances not considered in the training step. The study shows that the proposed GCM+ANN+PSO method represent an excellent alternative for the estimation of flash points of organic compounds with acceptable accuracy (AARD=1.8%;AAE=6.2 K).

关键词: flash point, group contribution method, artificial neural networks, particle swarm optimization, property estimation

Abstract: The flash points of organic compounds were estimated using a hybrid method that includes a simple group contribution method (GCM) implemented in an artificial neural network (ANN) with particle swarm optimization (PSO). Different topologies of a multilayer neural network were studied and the optimum architecture was determined. Property data of 350 compounds were used for training the network. To discriminate different substances the molecular structures defined by the concept of the classical group contribution method were given as input variables. The capabilities of the network were tested with 155 substances not considered in the training step. The study shows that the proposed GCM+ANN+PSO method represent an excellent alternative for the estimation of flash points of organic compounds with acceptable accuracy (AARD=1.8%;AAE=6.2 K).

Key words: flash point, group contribution method, artificial neural networks, particle swarm optimization, property estimation