Hostname: page-component-586b7cd67f-2brh9 Total loading time: 0 Render date: 2024-11-28T02:27:30.503Z Has data issue: false hasContentIssue false
  • English
  • Français

Prediction of physical properties of thermosetting resin by using machine learning and structural formulas of raw materials

Published online by Cambridge University Press:  04 June 2020

Kokin Nakajin ,
Takuya Minami ,
Masaaki Kawata ,
Toshio Fujita ,
Katsumi Murofushi ,
Hiroshi Uchida ,
Kazuhiro Omori  and
Yoshishige Okuno
Kokin Nakajin
Affiliation:
Research Association of High-Throughput Design and Development for Advanced Functional Materials, Tsukuba, Ibaraki305-8568, Japan Showa Denko K.K., Minato-ku, Tokyo105-0012, Japan.
Takuya Minami
Affiliation:
Showa Denko K.K., Minato-ku, Tokyo105-0012, Japan.
Masaaki Kawata
Affiliation:
National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Ibaraki305-8568, Japan
Toshio Fujita
Affiliation:
Research Association of High-Throughput Design and Development for Advanced Functional Materials, Tsukuba, Ibaraki305-8568, Japan Showa Denko K.K., Minato-ku, Tokyo105-0012, Japan.
Katsumi Murofushi
Affiliation:
Showa Denko K.K., Minato-ku, Tokyo105-0012, Japan.
Hiroshi Uchida
Affiliation:
Showa Denko K.K., Minato-ku, Tokyo105-0012, Japan.
Kazuhiro Omori
Affiliation:
Showa Denko K.K., Minato-ku, Tokyo105-0012, Japan.
Yoshishige Okuno
Affiliation:
Showa Denko K.K., Minato-ku, Tokyo105-0012, Japan.
Get access

Abstract

Thermosetting resins are one of the most widely used functional materials in industrial applications. Although some of the physical properties of thermosetting resins are controlled by changing the functional groups of the raw materials or adjusting their mixing ratios, it was conventionally challenging to construct machine learning (ML) models, which include both mixing ratio and chemical information such as functional groups. To overcome this problem, we propose a machine learning approach based on extended circular fingerprint (ECFP) in this study. First, we predicted the classification of raw materials by the random forest, where ECFP was used as the explanatory variable. Then, we aggregated ECFP for each classification predicted by the random forest. After that, we constructed the prediction model by using the aggregated ECFP, feature quantities of reaction intermediates, and curing conditions of resin as explanatory variables. As a result, the model was able to predict in high accuracy (R^2 = 0.8), for example, the elastic modulus of thermosetting resins. Furthermore, we also show the result of verification of prediction accuracy in first step, such as using the one-hot-encording. Therefore, we confirmed that the properties of thermosetting resins could be predicted using mixed raw materials by the proposed method.

Type
Articles
Information
MRS Advances , Volume 5 , Issue 29-30: Materials Theory, Computation and Characterization , 2020 , pp. 1567 - 1575
Check for updates
Copyright
Copyright © Materials Research Society 2020

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Mannodi-Kanakkithodi, , et al. , Materials Today, 21, 785 (2017)CrossRefGoogle Scholar
Ramprasad, R. et al. , NPJ Comput. Mater. 3, 54 (2017)10.1038/s41524-017-0056-5CrossRefGoogle Scholar
Seko, A., Phys. Rev. Lett. 115, 205901 (2015).10.1103/PhysRevLett.115.205901CrossRefGoogle Scholar
Minami, T., Okuno, Y., MRS Advances, 3 (49), 2975-2980 (2018).10.1557/adv.2018.454CrossRefGoogle Scholar
Minami, T., Okuno, Y., MRS Advances, 4(19), 1125-1130 (2019).10.1557/adv.2019.57CrossRefGoogle Scholar
Yada, A., et al. , Chem. Phys. Lett. 47, 284 (2018).Google Scholar
Sigman, M. S. et al. , Acc. Chem. Res. 49, 1292 (2016)10.1021/acs.accounts.6b00194CrossRefGoogle Scholar
Rogers, D., Hahn, M., Chem, J.. Inf. Model. 50, 742 (2010).10.1021/ci100050tCrossRefGoogle Scholar
Uchida, H., Journal of thermosetting plastics, Japan, 15, 1 (1994).Google Scholar
RDKit: Open-Source Cheminformatics. Available at http://www.rdkit.org (accessed 15 April 2017)Google Scholar
Breiman, L., Machine Learning. 45, 5 (2001).CrossRefGoogle Scholar
Pedregosa, F. et al. , JMLR. 12, 2825 (2011).Google Scholar
MacKay, D. J. C., Neural Computation, 4, 415 (1992).10.1162/neco.1992.4.3.415CrossRefGoogle Scholar
Weininger, D., Chem, J.. Inf. Comput. Sci., 28, 31 (1988)Google Scholar
Ye, Nan., et al. , arXiv preprint arXiv: 1206. 4625 (2012)Google Scholar
Dembczynski, K. J. et al. , NeurIPS. 1404-1412 (2011)Google Scholar