Premium
Using Artificial Intelligence Techniques to Design Ethylene/1‐Olefin Copolymers
Author(s) -
Charoenpanich Thanutchoke,
Anantawaraskul Siripon,
Soares João B. P.
Publication year - 2020
Publication title -
macromolecular theory and simulations
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.37
H-Index - 56
eISSN - 1521-3919
pISSN - 1022-1344
DOI - 10.1002/mats.202000048
Subject(s) - comonomer , polymer , branching (polymer chemistry) , molar mass distribution , copolymer , materials science , polymerization , olefin fiber , polymer chemistry , chemical engineering , composite material , engineering
Four global optimization techniques, genetic algorithm, particle swarm, improved ant colony, and modified artificial bee colony, are compared to find alternative polymerization conditions to make ethylene/1‐olefin copolymers with targeted microstructures and polymerization yields. The polymer microstructure targets are divided in three groups: 1) molecular weight distribution, chemical composition distribution, and polymer yield; 2) number and weight average molecular weights, average comonomer content, and polymer yield; and 3) molecular weight distribution, short chain branching distribution, and polymer yield. The modified artificial bee colony optimization generated the fewest number of incorrect solutions, while the polymer microstructure target group 1 generated the most successful solutions.