Multiobjective intelligence optimal operation of PET polymerization

Author

Cao, Liulin ; Wang, Jing ; Jiang, Pei ; Jin, Qibing

Author_Institution

Coll. of Inf. Sci. & Technol., Beijing Univ. of Chem. Technol., Beijing, China

fYear

2011

fDate

21-25 June 2011

Firstpage

336

Lastpage

340

Abstract

A multiobjective intelligence optimal approach in polymerizing of PET with maximum yield and the best quality is proposed. The hybrid neural network based on B-spline and diagonal recursive neural network is used to model the PET process qualities, i.e. the Intrinsic Viscosity and Molecular Weight distribution. Then a hybrid NSGAII-PSO optimal algorithm with penalty functions is applied to solve the multiobjective optimal problem in order to get the best operation conditions. The simulation result indicates that the hybrid network model and model-based multiobjective optimal algorithm are effective.

Keywords

chemical engineering computing; chemical industry; neural nets; particle swarm optimisation; polymerisation; production engineering computing; splines (mathematics); B-spline; PET polymerization; diagonal recursive neural network; hybrid NSGAII-PSO optimal algorithm; hybrid neural network; intrinsic viscosity; molecular weight distribution; multiobjective intelligence optimal operation; multiobjective optimal problem; penalty function; Artificial neural networks; Inductors; Optimization; Polymers; Positron emission tomography; Predictive models; Viscosity; Multiobjective optimization; NSGAII-PSO algorithm; PET; hybrid neural network;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control and Automation (WCICA), 2011 9th World Congress on

Conference_Location

Taipei

Print_ISBN

978-1-61284-698-9

Type

conf

DOI

10.1109/WCICA.2011.5970754

Filename

5970754