Polyolefin ductile-brittle transition temperature predictions by machine learning
Polymers show a transition from ductile-to brittle fracture behavior at decreasing temperatures. Consequently, the material toughness has to be determined across wide temperature ranges in order to determine the Ductile-Brittle Transition Temperature This usually necessitates multiple impact experim...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-01-01
|
| Series: | Frontiers in Materials |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmats.2023.1275640/full |
| _version_ | 1797347185017225216 |
|---|---|
| author | Florian Kiehas Martin Reiter Juan Pablo Torres Michael Jerabek Zoltán Major |
| author_facet | Florian Kiehas Martin Reiter Juan Pablo Torres Michael Jerabek Zoltán Major |
| author_sort | Florian Kiehas |
| collection | DOAJ |
| description | Polymers show a transition from ductile-to brittle fracture behavior at decreasing temperatures. Consequently, the material toughness has to be determined across wide temperature ranges in order to determine the Ductile-Brittle Transition Temperature This usually necessitates multiple impact experiments. We present a machine-learning methodology for the prediction of DBTTs from single Instrumented Puncture Tests Our dataset consists of 7,587 IPTs that comprise 181 Polyethylene and Polypropylene compounds. Based on a combination of feature engineering and Principal Component Analysis, relevant information of instrumentation signals is extracted. The transformed data is explored by unsupervised machine learning algorithms and is used as input for Random Forest Regressors to predict DBTTs. The proposed methodology allows for fast screening of new materials. Additionally, it offers estimations of DBTTs without thermal specimen conditioning. Considering only IPTs tested at room temperature, predictions on the test set hold an average error of 5.3°C when compared to the experimentally determined DBTTs. |
| first_indexed | 2024-03-08T11:44:02Z |
| format | Article |
| id | doaj.art-f94c58de01574989ac035d88bdc9327d |
| institution | Directory Open Access Journal |
| issn | 2296-8016 |
| language | English |
| last_indexed | 2024-03-08T11:44:02Z |
| publishDate | 2024-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Materials |
| spelling | doaj.art-f94c58de01574989ac035d88bdc9327d2024-01-25T04:37:15ZengFrontiers Media S.A.Frontiers in Materials2296-80162024-01-011010.3389/fmats.2023.12756401275640Polyolefin ductile-brittle transition temperature predictions by machine learningFlorian Kiehas0Martin Reiter1Juan Pablo Torres2Michael Jerabek3Zoltán Major4Institute of Polymer Product Engineering, Johannes Kepler University, Linz, AustriaInstitute of Polymer Product Engineering, Johannes Kepler University, Linz, AustriaBorealis Polyolefine GmbH, Linz, AustriaBorealis Polyolefine GmbH, Linz, AustriaInstitute of Polymer Product Engineering, Johannes Kepler University, Linz, AustriaPolymers show a transition from ductile-to brittle fracture behavior at decreasing temperatures. Consequently, the material toughness has to be determined across wide temperature ranges in order to determine the Ductile-Brittle Transition Temperature This usually necessitates multiple impact experiments. We present a machine-learning methodology for the prediction of DBTTs from single Instrumented Puncture Tests Our dataset consists of 7,587 IPTs that comprise 181 Polyethylene and Polypropylene compounds. Based on a combination of feature engineering and Principal Component Analysis, relevant information of instrumentation signals is extracted. The transformed data is explored by unsupervised machine learning algorithms and is used as input for Random Forest Regressors to predict DBTTs. The proposed methodology allows for fast screening of new materials. Additionally, it offers estimations of DBTTs without thermal specimen conditioning. Considering only IPTs tested at room temperature, predictions on the test set hold an average error of 5.3°C when compared to the experimentally determined DBTTs.https://www.frontiersin.org/articles/10.3389/fmats.2023.1275640/fullpolyolefincompoundsimpact testsductile-brittle transition temperaturemachine learningfeature engineering |
| spellingShingle | Florian Kiehas Martin Reiter Juan Pablo Torres Michael Jerabek Zoltán Major Polyolefin ductile-brittle transition temperature predictions by machine learning Frontiers in Materials polyolefin compounds impact tests ductile-brittle transition temperature machine learning feature engineering |
| title | Polyolefin ductile-brittle transition temperature predictions by machine learning |
| title_full | Polyolefin ductile-brittle transition temperature predictions by machine learning |
| title_fullStr | Polyolefin ductile-brittle transition temperature predictions by machine learning |
| title_full_unstemmed | Polyolefin ductile-brittle transition temperature predictions by machine learning |
| title_short | Polyolefin ductile-brittle transition temperature predictions by machine learning |
| title_sort | polyolefin ductile brittle transition temperature predictions by machine learning |
| topic | polyolefin compounds impact tests ductile-brittle transition temperature machine learning feature engineering |
| url | https://www.frontiersin.org/articles/10.3389/fmats.2023.1275640/full |
| work_keys_str_mv | AT floriankiehas polyolefinductilebrittletransitiontemperaturepredictionsbymachinelearning AT martinreiter polyolefinductilebrittletransitiontemperaturepredictionsbymachinelearning AT juanpablotorres polyolefinductilebrittletransitiontemperaturepredictionsbymachinelearning AT michaeljerabek polyolefinductilebrittletransitiontemperaturepredictionsbymachinelearning AT zoltanmajor polyolefinductilebrittletransitiontemperaturepredictionsbymachinelearning |