This paper presents a computational procedure for producing tailor made polymer resins, satisfying customers' needs while operating with maximum profit. The case study is an industrial large-scale polymerization reactor. The molecular properties considered are melt index (MI), which measures the...

This paper presents a computational procedure for producing tailor made polymer resins, satisfying customers' needs while operating with maximum profit. The case study is an industrial large-scale polymerization reactor. The molecular properties considered are melt index (MI), which measures the molecular weight distribution, and stress exponent (SE), which is related to polydispersity. An economic objective function is associated to a deterministic mathematical model and the resulting optimization problem is solved by genetic algorithm (GA), a stochastic method. The GA parameters for both binary and real codifications are tuned by means of the design of experiments. Attempting to achieve the global optimum, a hybrid method, which introduces process knowledge into GA random initial population, is proposed. The binary codification performs better than the real GA, especially with hybridization. Results show that the GA can satisfactorily predict tailor made polymer resins with profits up to 25% higher than the industrial practice

CONSELHO NACIONAL DE DESENVOLVIMENTO CIENTÍFICO E TECNOLÓGICO - CNPQ

COORDENAÇÃO DE APERFEIÇOAMENTO DE PESSOAL DE NÍVEL SUPERIOR - CAPES

FUNDAÇÃO DE AMPARO À PESQUISA DO ESTADO DA BAHIA - FAPESB

Fechado