Prediction of physical properties of thermosetting resin by using machine learning and structural formulas of raw materi
- PDF / 761,751 Bytes
- 9 Pages / 432 x 648 pts Page_size
- 43 Downloads / 170 Views
MRS Advances © 2020 Materials Research Society DOI: 10.1557/adv.2020.266
Prediction of physical properties of thermosetting resin by using machine learning and structural formulas of raw materials Kokin Nakajin1,2, Takuya Minami2, Masaaki Kawata3, Toshio Fujita1,2, Katsumi Murofushi2, Hiroshi Uchida2, Kazuhiro Omori2, and Yoshishige Okuno2 1
Research Association of High-Throughput Design and Development for Advanced Functional Materials, Tsukuba, Ibaraki 305-8568, Japan 2
Showa Denko K.K., Minato-ku, Tokyo 105-0012, Japan.
3 National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Ibaraki 305-8568, Japan
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-hotencording. Therefore, we confirmed that the properties of thermosetting resins could be predicted using mixed raw materials by the proposed method. 1
Downloaded from https://www.cambridge.org/core. UCSD University of California San Diego, on 22 Jun 2020 at 21:39:10, subject to the Cambridge Core terms of use, available at https://www.cambridge.org/core/terms. https://doi.org/10.1557/adv.2020.266
INTRODUCTION: A physical property prediction is a practical approach for the efficient design of functional materials. The ab-initio calculation and molecular dynamics simulation have been frequently used for predicting properties of small organic molecules or inorganic crystals due to their high prediction accuracy. However, in general, these approaches are challenging to apply for high molecular weight polymers due to their high computational costs. On the other hand, ML has recently attracted attention as an alternative approach [1,2]. Because ML can reduce computational time, and it can find target materials which satisfy the required properties from the massive amount of data. Several case studies have been reported for, such as inorganic materials [3], thermoplastic polymers [4,5], and catalysts [6,7]. I
Data Loading...
