Designing Heat-Resistant and Moldable Polyester Resin by the Integration of Machine Learning Models with Expert Knowledge
Source abstract
Abstract
High Resolution Image Download MS PowerPoint Slide Polyester resin has advantages in transparency and chemical resistance and is widely used in films and containers. In industrial applications, multiple conflicting properties of polyester resin must be optimized. Nevertheless, few reports have been found dealing with the design of polyester resins with machine learning (ML) models. Herein, we report a multiobjective design strategy of heat tolerant and moldable polyester resin, represented by the glass-transition temperature ( T g ) and the softening point (SP). Our proposed workflow is an interplay between ML models and expert knowledge. Highly accurate interpretable linear regression models using chemical structural features were constructed for T g and SP, which were utilized for evaluating previously uninvestigated monomers. Insights into substructures with which highly correlated properties ( T g and SP) were compromised were obtained by analyzing the regression coefficients of a linear model for SP/ T g . Based on the insight from the SP/ T g model, four dicarboxylic monomers consisting of untested molecular scaffolds were proposed and with which polyester resins were actually synthesized. The synthesized resins exhibited desired properties, consistent with prediction results by ML models. The reported workflow successfully proposed the dicarboxylic monomers with which polyester resins had desirable multiple properties.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Machine Learning in Materials Science · Manufacturing Process and Optimization · Computational Drug Discovery Methods
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Material Science Research, Kao Corporation, 1334 Minato, Wakayama-shi, Wakayama 640-8580, Japan
Division of Information Science, Graduate School of Science and Technology, Nara Institute of Science and Technology, 8916-5 Takayama-cho, Ikoma, Nara 630-0192, Japan
Data Science Center and Graduate School of Science and Technology, Nara Institute of Science and Technology, 8916-5 Takayama-cho, Ikoma, Nara 630-0192, Japan
Performance Chemicals Research, Kao Corporation, 1334 Minato, Wakayama-shi, Wakayama 640-8580, Japan
References (29)
Show source-provided references
1. 10.1021/acsmacrolett.7b0022810.1021/acsmacrolett.7b00228 ↗
2. 10.1002/inf2.1216710.1002/inf2.12167 ↗
3. 10.1021/acs.jcim.1c0103110.1021/acs.jcim.1c01031 ↗
4. 10.1002/adts.20210056510.1002/adts.202100565 ↗
5. 10.1021/jacs.9b1144210.1021/jacs.9b11442 ↗
6. 10.1038/s41524-017-0056-510.1038/s41524-017-0056-5 ↗
7. 10.1021/ci010062o10.1021/ci010062o ↗
8. Bicerano J. · 200210.1201/9780203910115 ↗
9. 10.1021/ci950156w10.1021/ci950156w ↗
10. 10.1016/j.eurpolymj.2006.12.02910.1016/j.eurpolymj.2006.12.029 ↗
11. 10.1021/acsapm.9b0019810.1021/acsapm.9b00198 ↗
12. 10.1021/acsami.3c1369810.1021/acsami.3c13698 ↗
13. 10.1021/acsomega.2c0464910.1021/acsomega.2c04649 ↗
14. 10.1021/acspolymersau.1c0005010.1021/acspolymersau.1c00050 ↗
15. 10.1016/j.matpr.2021.02.73010.1016/j.matpr.2021.02.730 ↗
16. 10.1002/pol.2023071410.1002/pol.20230714 ↗
17. 10.1039/C7SC04679K10.1039/C7SC04679K ↗
18. 10.1002/978352761310610.1002/9783527613106 ↗
19. 10.1021/ci100050t10.1021/ci100050t ↗
20. 10.1021/acsomega.0c0449910.1021/acsomega.0c04499 ↗
21. Van Krevelen D. W. · 2009
22. 10.1246/bcsj.2020022010.1246/bcsj.20200220 ↗
23. 10.1002/pi.498016030610.1002/pi.4980160306 ↗
24. 10.1111/j.2517-6161.1996.tb02080.x10.1111/j.2517-6161.1996.tb02080.x ↗
25. 10.1023/B:STCO.0000035301.49549.8810.1023/B:STCO.0000035301.49549.88 ↗
26. 10.1023/A:101093340432410.1023/A:1010933404324 ↗
27. Probst P. · J. Mach. Learn. Res. · 2018 · 18 · 1
28. Pedregosa F. · J. Mach. Learn. Res. · 2011 · 12 · 2825
29. Landrum, G. Cheminformatics, RDKit: Open-Source, 2006 https://www.rdkit.org/(accessed Jan 4, 2024).