.png){kind=icon}
Return
Polymer reaction engineering meets explainable machine learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.compchemeng.2023.108356.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Due to the complex polymerization technique and statistical composition of the polymer, tailoring its charac-teristics 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.
Keywords:
Polymers
Machine learning
Kinetic Monte Carlo simulation
Multi-target-regression
Reverse engineering
explainable AI
Journal
C
IF:
3.9
Papers:
8.1K
Citations:
1.7W
Organization
Cited Papers
ShareSaveBleaching microcrystalline cellulose using hydrogen peroxide, peracetic acid, and ozone.png)
BioResources
OAAI
BioResourcesIF0
OAAIShareSaveMulti-target regression via input space expansion: treating targets as inputsMACHINE LEARNING
OAAI
MACHINE LEARNINGIF2.9
OAAIShareSaveConditional Monte Carlo sampling to find branching architectures of polymers from radical polymerizations with transfer to polymerMACROMOLECULES
MACROMOLECULESIF5.2
PREAI
ShareSaveShareSaveShareSave
View more