Using Artificial Intelligence Techniques to Design Ethylene/1‐Olefin Copolymers

Charoenpanich, Thanutchoke; Anantawaraskul, Siripon; Soares, João B. P.

doi:10.1002/mats.202000048

Cited by 9 publications

(5 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study allows people to quickly obtain the relationship between polymerization conditions and polymer properties in this catalytic system, which is helpful to accelerate product development and scale‐up research. Charoenpanich et al [ 45 ] used genetic, particle swarm optimization, improved ant colony, and improved artificial bee colony algorithms to establish a kinetic model for ethylene/ α ‐olefin copolymerization and explore the relationship between polymerization conditions and the polymer chain structure. This research is beneficial when assessing between product properties and production cost.…”

Section: Random Copolymer Poesmentioning

confidence: 99%

Synthesis and characterization of polyolefin thermoplastic elastomers: A review

et al. 2023

View full text Add to dashboard Cite

Polyolefin thermoplastic elastomers (TPE‐Os) are high‐performance polyolefins consisting of both plastic and rubber phases. Compared with other thermoplastic elastomers, the TPE‐Os possess better chemical stability, transparency, re‐processability, and electrical insulation, which renders their broad applications possible. By manipulating chain structures and topologies of the TPE‐Os, differently structured polyolefins with improved thermal and mechanical properties have been developed, including ethylene and α‐olefin random copolymers (POEs), olefin block copolymers (OBCs), comb‐shaped polyolefin elastomers (CPOEs), and dynamically cross‐linked polyolefin elastomers. Herein, we review the synthesis of the POE, OBC, CPOE, and dynamical cross‐linked polyolefin elastomer, including the catalyst systems, polymerization techniques, processes, and kinetic modelling. The characterization of the TPE‐Os and the relationships between the TPE‐O chain structure, aggregated state, and product performance are discussed. The future development of higher‐performance TPE‐Os is envisaged.

show abstract

Section: Random Copolymer Poesmentioning

confidence: 99%

Synthesis and characterization of polyolefin thermoplastic elastomers: A review

et al. 2023

View full text Add to dashboard Cite

show abstract

“…The application of REPP instead of a kMC simulator is advantageous, since the process is expected to be faster and may be modified for more complex output structures. Various global optimization techniques, genetic algorithm, particle swarm, improved ant colony, artificial bee colony and differential evolution algorithms, allow finding alternative conditions in the REPP task (Charoenpanich, Anantawaraskul, & Soares, 2020;Dragoi & Curteanu, 2016;Fernandes & Lona, 2005). As a simple solution, we use ML for initial solution of reverse engineering problems.…”

Section: Reverse Engineering Of Polymerization Processes (Repp)mentioning

confidence: 99%

Polymer Reaction Engineering meets Explainable Machine Learning

Fiošina

Sievers

Drache

et al. 2023

Preprint

View full text Add to dashboard Cite

Due to the complicated polymerization technique and statistical composition of the polymer, tailoring its characteristics is a challenging task. Modeling of the polymerizations can contribute to deeper insights into the process. This study applies state-of-the-art machine learning (ML) methods for modeling and reverse engineering of polymerization processes. ML methods (random forest, XGBoost and CatBoost) are trained on data sets generated by an in house developed kinetic Monte Carlo simulator. The applied ML models predict monomer concentration, average molar masses and full molar mass distributions with excellent accuracy (R2 > 0.96). Reverse engineering results delivering the polymerization recipe for a targeted molar mass distribution are less accurate, but still only minor deviations from the targeted molar mass distribution are seen. The influences of the input variables in ML models obtained by explainability methods correspond to the expert expectations.

show abstract

“…With respect to technical applications, it appears highly important to solve the reverse engineering problem as an optimization task with multiple contradicting objectives [13]. Various ML-based optimization strategies were addressed for the purpose of reverse engineering polymerization processes [21][22][23][24][25]. A genetic algorithm-based optimizer was proposed by Mohammadi et al [9] to generate a variety of polymerization recipes at random and to send them to the kMC simulator for error evaluation.…”

Section: Introductionmentioning

confidence: 99%

Reverse Engineering of Radical Polymerizations by Multi-Objective Optimization

Fiosina,

Sievers,

Kanagaraj

et al. 2024

Polymers

View full text Add to dashboard Cite

Reverse engineering is applied to identify optimum polymerization conditions for the synthesis of polymers with pre-defined properties. The proposed approach uses multi-objective optimization (MOO) and provides multiple candidate polymerization procedures to achieve the targeted polymer property. The objectives for optimization include the maximal similarity of molar mass distributions (MMDs) compared to the target MMDs, a minimal reaction time, and maximal monomer conversion. The method is tested for vinyl acetate radical polymerizations and can be adopted to other monomers. The data for the optimization procedure are generated by an in-house-developed kinetic Monte-Carlo (kMC) simulator for a selected recipe search space. The proposed reverse engineering algorithm comprises several steps: kMC simulations for the selected recipe search space to derive initial data, performing MOO for a targeted MMD, and the identification of the Pareto optimal space. The last step uses a weighted sum optimization function to calculate the weighted score of each candidate polymerization condition. To decrease the execution time, clustering of the search space based on MMDs is applied. The performance of the proposed approach is tested for various target MMDs. The suggested MOO-based reverse engineering provides multiple recipe candidates depending on competing objectives.

show abstract

Using Artificial Intelligence Techniques to Design Ethylene/1‐Olefin Copolymers

Cited by 9 publications

References 48 publications

Synthesis and characterization of polyolefin thermoplastic elastomers: A review

Synthesis and characterization of polyolefin thermoplastic elastomers: A review

Polymer Reaction Engineering meets Explainable Machine Learning

Reverse Engineering of Radical Polymerizations by Multi-Objective Optimization

Contact Info

Product

Resources

About