Analysis on Microstructure–Property Linkages of Filled Rubber Using Machine Learning and Molecular Dynamics Simulations
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 consistin...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-08-01
|
| Series: | Polymers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4360/13/16/2683 |
| _version_ | 1797522297909673984 |
|---|---|
| author | Takashi Kojima Takashi Washio Satoshi Hara Masataka Koishi Naoya Amino |
| author_facet | Takashi Kojima Takashi Washio Satoshi Hara Masataka Koishi Naoya Amino |
| author_sort | Takashi Kojima |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T08:27:23Z |
| format | Article |
| id | doaj.art-763f0b036a594b89ba9aa93ef97d57e6 |
| institution | Directory Open Access Journal |
| issn | 2073-4360 |
| language | English |
| last_indexed | 2024-03-10T08:27:23Z |
| publishDate | 2021-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Polymers |
| spelling | doaj.art-763f0b036a594b89ba9aa93ef97d57e62023-11-22T09:22:48ZengMDPI AGPolymers2073-43602021-08-011316268310.3390/polym13162683Analysis on Microstructure–Property Linkages of Filled Rubber Using Machine Learning and Molecular Dynamics SimulationsTakashi Kojima0Takashi Washio1Satoshi Hara2Masataka Koishi3Naoya Amino4Research and Advanced Development Division, The Yokohama Rubber Co., Ltd., 2-1 Oiwake, Hiratsuka 254-8601, Kanagawa, JapanDepartment of Reasoning for Intelligence, The Institute of Scientific and Industrial Research, Osaka University, 8-1 Mihogaoka, Ibarakishi 567-0047, Osaka, JapanDepartment of Reasoning for Intelligence, The Institute of Scientific and Industrial Research, Osaka University, 8-1 Mihogaoka, Ibarakishi 567-0047, Osaka, JapanResearch and Advanced Development Division, The Yokohama Rubber Co., Ltd., 2-1 Oiwake, Hiratsuka 254-8601, Kanagawa, JapanResearch and Advanced Development Division, The Yokohama Rubber Co., Ltd., 2-1 Oiwake, Hiratsuka 254-8601, Kanagawa, JapanA 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.https://www.mdpi.com/2073-4360/13/16/2683filled rubbermicrostructurefiller morphologymolecular dynamics simulationsmachine learningconvolutional neural network |
| spellingShingle | Takashi Kojima Takashi Washio Satoshi Hara Masataka Koishi Naoya Amino Analysis on Microstructure–Property Linkages of Filled Rubber Using Machine Learning and Molecular Dynamics Simulations Polymers filled rubber microstructure filler morphology molecular dynamics simulations machine learning convolutional neural network |
| title | Analysis on Microstructure–Property Linkages of Filled Rubber Using Machine Learning and Molecular Dynamics Simulations |
| title_full | Analysis on Microstructure–Property Linkages of Filled Rubber Using Machine Learning and Molecular Dynamics Simulations |
| title_fullStr | Analysis on Microstructure–Property Linkages of Filled Rubber Using Machine Learning and Molecular Dynamics Simulations |
| title_full_unstemmed | Analysis on Microstructure–Property Linkages of Filled Rubber Using Machine Learning and Molecular Dynamics Simulations |
| title_short | Analysis on Microstructure–Property Linkages of Filled Rubber Using Machine Learning and Molecular Dynamics Simulations |
| title_sort | analysis on microstructure property linkages of filled rubber using machine learning and molecular dynamics simulations |
| topic | filled rubber microstructure filler morphology molecular dynamics simulations machine learning convolutional neural network |
| url | https://www.mdpi.com/2073-4360/13/16/2683 |
| work_keys_str_mv | AT takashikojima analysisonmicrostructurepropertylinkagesoffilledrubberusingmachinelearningandmoleculardynamicssimulations AT takashiwashio analysisonmicrostructurepropertylinkagesoffilledrubberusingmachinelearningandmoleculardynamicssimulations AT satoshihara analysisonmicrostructurepropertylinkagesoffilledrubberusingmachinelearningandmoleculardynamicssimulations AT masatakakoishi analysisonmicrostructurepropertylinkagesoffilledrubberusingmachinelearningandmoleculardynamicssimulations AT naoyaamino analysisonmicrostructurepropertylinkagesoffilledrubberusingmachinelearningandmoleculardynamicssimulations |