Kojima Takashi, Washio Takashi, Hara Satoshi, Koishi Masataka, Amino Naoya
Research and Advanced Development Division, The Yokohama Rubber Co., Ltd., 2-1 Oiwake, Hiratsuka 254-8601, Kanagawa, Japan.
Department of Reasoning for Intelligence, The Institute of Scientific and Industrial Research, Osaka University, 8-1 Mihogaoka, Ibarakishi 567-0047, Osaka, Japan.
Polymers (Basel). 2021 Aug 11;13(16):2683. doi: 10.3390/polym13162683.
A better understanding of the microstructure-property relationship can be achieved by sampling and analyzing a microstructure leading to a desired material property. During the simulation of filled rubber, this approach includes extracting common aggregates from a complex filler morphology consisting of hundreds of filler particles. However, a method for extracting a core structure that determines the rubber mechanical properties has not been established yet. In this study, we analyzed complex filler morphologies that generated extremely high stress using two machine learning techniques. First, filler morphology was quantified by persistent homology and then vectorized using persistence image as the input data. After that, a binary classification model involving logistic regression analysis was developed by training a dataset consisting of the vectorized morphology and stress-based class. The filler aggregates contributing to the desired mechanical properties were extracted based on the trained regression coefficients. Second, a convolutional neural network was employed to establish a classification model by training a dataset containing the imaged filler morphology and class. The aggregates strongly contributing to stress generation were extracted by a kernel. The aggregates extracted by both models were compared, and their shapes and distributions producing high stress levels were discussed. Finally, we confirmed the effects of the extracted aggregates on the mechanical property, namely the validity of the proposed method for extracting stress-contributing fillers, by performing coarse-grained molecular dynamics simulations.
通过对导致所需材料性能的微观结构进行采样和分析，可以更好地理解微观结构与性能之间的关系。在填充橡胶的模拟过程中，这种方法包括从由数百个填料颗粒组成的复杂填料形态中提取常见的聚集体。然而，尚未建立一种用于提取决定橡胶力学性能的核心结构的方法。在本研究中，我们使用两种机器学习技术分析了产生极高应力的复杂填料形态。首先，通过持久同调对填料形态进行量化，然后使用持久图像将其矢量化作为输入数据。之后，通过训练由矢量化形态和基于应力的类别组成的数据集，开发了一个涉及逻辑回归分析的二元分类模型。基于训练得到的回归系数，提取对所需力学性能有贡献的填料聚集体。其次，采用卷积神经网络通过训练包含成像填料形态和类别的数据集来建立分类模型。通过一个内核提取对应力产生有强烈贡献的聚集体。比较了两种模型提取的聚集体，并讨论了它们产生高应力水平的形状和分布。最后，我们通过进行粗粒度分子动力学模拟，证实了提取的聚集体对力学性能的影响，即所提出的提取应力贡献填料方法的有效性。
