Optimizing interlaminar toughening of carbon-based filler/polymer nanocomposites by machine learning
Currently, most designs for interlayer toughening of carbon-based filler/polymer nanocomposites are highly dependent on experimental iterative trial and error, and there is no rational design framework. This work uses machine learning to build a fast and accurate predictive model and assess the exte...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-11-01
|
| Series: | Polymer Testing |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0142941823003021 |
| _version_ | 1827803650908487680 |
|---|---|
| author | ChengLin Han Hongxing Zhao Tianzhi Yang Xueqing Liu Mingchi Yu Gong-Dong Wang |
| author_facet | ChengLin Han Hongxing Zhao Tianzhi Yang Xueqing Liu Mingchi Yu Gong-Dong Wang |
| author_sort | ChengLin Han |
| collection | DOAJ |
| description | Currently, most designs for interlayer toughening of carbon-based filler/polymer nanocomposites are highly dependent on experimental iterative trial and error, and there is no rational design framework. This work uses machine learning to build a fast and accurate predictive model and assess the extent to which key features affect performance, giving researchers ideas for designing new materials and greatly improving efficiency. A training database is built by first collecting the features of the domain that affect the interlaminar performance. A stacking model fusion of the three machine learning models was then performed to construct a highly accurate fast prediction model. Besides, the importance of key features is evaluated during model training using the Random Forest Algorithm (RFA). Finally, by predicting the performance of materials and analyzing the importance of characteristics to guide material preparation, the development cycle is shortened and costs are reduced. |
| first_indexed | 2024-03-11T20:57:27Z |
| format | Article |
| id | doaj.art-246df60d25104266aa706651ed759241 |
| institution | Directory Open Access Journal |
| issn | 0142-9418 |
| language | English |
| last_indexed | 2024-03-11T20:57:27Z |
| publishDate | 2023-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Polymer Testing |
| spelling | doaj.art-246df60d25104266aa706651ed7592412023-09-30T04:53:51ZengElsevierPolymer Testing0142-94182023-11-01128108222Optimizing interlaminar toughening of carbon-based filler/polymer nanocomposites by machine learningChengLin Han0Hongxing Zhao1Tianzhi Yang2Xueqing Liu3Mingchi Yu4Gong-Dong Wang5School of Mechanical Engineering and Automation, Northeastern University, Shenyang, PR ChinaDepartment of Aeronautical Engineering, School of Aerospace Engineering, Shenyang Aerospace University, Shenyang, PR ChinaSchool of Mechanical Engineering and Automation, Northeastern University, Shenyang, PR China; Corresponding author.Department of Aeronautical Engineering, School of Aerospace Engineering, Shenyang Aerospace University, Shenyang, PR ChinaDepartment of Aeronautical Engineering, School of Aerospace Engineering, Shenyang Aerospace University, Shenyang, PR ChinaDepartment of Aeronautical Engineering, School of Aerospace Engineering, Shenyang Aerospace University, Shenyang, PR China; Corresponding author.Currently, most designs for interlayer toughening of carbon-based filler/polymer nanocomposites are highly dependent on experimental iterative trial and error, and there is no rational design framework. This work uses machine learning to build a fast and accurate predictive model and assess the extent to which key features affect performance, giving researchers ideas for designing new materials and greatly improving efficiency. A training database is built by first collecting the features of the domain that affect the interlaminar performance. A stacking model fusion of the three machine learning models was then performed to construct a highly accurate fast prediction model. Besides, the importance of key features is evaluated during model training using the Random Forest Algorithm (RFA). Finally, by predicting the performance of materials and analyzing the importance of characteristics to guide material preparation, the development cycle is shortened and costs are reduced.http://www.sciencedirect.com/science/article/pii/S0142941823003021NanocompositesFracture toughnessComputational modelling |
| spellingShingle | ChengLin Han Hongxing Zhao Tianzhi Yang Xueqing Liu Mingchi Yu Gong-Dong Wang Optimizing interlaminar toughening of carbon-based filler/polymer nanocomposites by machine learning Polymer Testing Nanocomposites Fracture toughness Computational modelling |
| title | Optimizing interlaminar toughening of carbon-based filler/polymer nanocomposites by machine learning |
| title_full | Optimizing interlaminar toughening of carbon-based filler/polymer nanocomposites by machine learning |
| title_fullStr | Optimizing interlaminar toughening of carbon-based filler/polymer nanocomposites by machine learning |
| title_full_unstemmed | Optimizing interlaminar toughening of carbon-based filler/polymer nanocomposites by machine learning |
| title_short | Optimizing interlaminar toughening of carbon-based filler/polymer nanocomposites by machine learning |
| title_sort | optimizing interlaminar toughening of carbon based filler polymer nanocomposites by machine learning |
| topic | Nanocomposites Fracture toughness Computational modelling |
| url | http://www.sciencedirect.com/science/article/pii/S0142941823003021 |
| work_keys_str_mv | AT chenglinhan optimizinginterlaminartougheningofcarbonbasedfillerpolymernanocompositesbymachinelearning AT hongxingzhao optimizinginterlaminartougheningofcarbonbasedfillerpolymernanocompositesbymachinelearning AT tianzhiyang optimizinginterlaminartougheningofcarbonbasedfillerpolymernanocompositesbymachinelearning AT xueqingliu optimizinginterlaminartougheningofcarbonbasedfillerpolymernanocompositesbymachinelearning AT mingchiyu optimizinginterlaminartougheningofcarbonbasedfillerpolymernanocompositesbymachinelearning AT gongdongwang optimizinginterlaminartougheningofcarbonbasedfillerpolymernanocompositesbymachinelearning |