Melt Instability Identification Using Unsupervised Machine Learning Algorithms
Abstract In industrial extrusion processes, increasing shear rates can lead to higher production rates. However, at high shear rates, extruded polymers and polymer compounds often exhibit melt instabilities ranging from stick‐slip to sharkskin to gross melt fracture. These instabilities result in ch...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley-VCH
2023-06-01
|
| Series: | Macromolecular Materials and Engineering |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/mame.202200628 |
| _version_ | 1827865663224414208 |
|---|---|
| author | Alex Gansen Julian Hennicker Clemens Sill Jean Dheur Jack S. Hale Jörg Baller |
| author_facet | Alex Gansen Julian Hennicker Clemens Sill Jean Dheur Jack S. Hale Jörg Baller |
| author_sort | Alex Gansen |
| collection | DOAJ |
| description | Abstract In industrial extrusion processes, increasing shear rates can lead to higher production rates. However, at high shear rates, extruded polymers and polymer compounds often exhibit melt instabilities ranging from stick‐slip to sharkskin to gross melt fracture. These instabilities result in challenges to meet the specifications on the extrudate shape. Starting with an existing published data set on melt instabilities in polymer extrusion, we assess the suitability of clustering, unsupervised machine learning algorithms combined with feature selection, to extract and identify hidden and important features from this data set, and their possible relationship with melt instabilities. The data set consists of both intrinsic features of the polymer as well as extrinsic features controlled and measured during an extrusion experiment. Using a range of commonly available clustering algorithms, it is demonstrated that the features related to only the intrinsic properties of the data set can be reliably divided into two clusters, and that in turn, these two clusters may be associated with either the stick‐slip or sharkskin instability. Furthermore, using a feature ranking on both the intrinsic and extrinsic features of the data set, it is shown that the intrinsic properties of molecular weight and polydispersity are the strongest indicators of clustering. |
| first_indexed | 2024-03-12T14:51:31Z |
| format | Article |
| id | doaj.art-3bdd743bdb82436db4c137e76bf4d1a6 |
| institution | Directory Open Access Journal |
| issn | 1438-7492 1439-2054 |
| language | English |
| last_indexed | 2024-03-12T14:51:31Z |
| publishDate | 2023-06-01 |
| publisher | Wiley-VCH |
| record_format | Article |
| series | Macromolecular Materials and Engineering |
| spelling | doaj.art-3bdd743bdb82436db4c137e76bf4d1a62023-08-15T09:10:25ZengWiley-VCHMacromolecular Materials and Engineering1438-74921439-20542023-06-013086n/an/a10.1002/mame.202200628Melt Instability Identification Using Unsupervised Machine Learning AlgorithmsAlex Gansen0Julian Hennicker1Clemens Sill2Jean Dheur3Jack S. Hale4Jörg Baller5Department of Physics and Materials Science University of Luxembourg 162A Avenue de la Faiencerie Luxembourg L‐1511 Grand Duchy of LuxembourgDepartment of Engineering University of Luxembourg Maison du Nombre 6, Avenue de la Fonte Esch‐sur‐Alzette L‐4364 Grand Duchy of LuxembourgGoodyear Innovation Center Luxembourg Avenue Gordon Smith Colmar‐Berg L‐7750 Grand Duchy of LuxembourgGoodyear Innovation Center Luxembourg Avenue Gordon Smith Colmar‐Berg L‐7750 Grand Duchy of LuxembourgDepartment of Engineering University of Luxembourg Maison du Nombre 6, Avenue de la Fonte Esch‐sur‐Alzette L‐4364 Grand Duchy of LuxembourgDepartment of Physics and Materials Science University of Luxembourg 162A Avenue de la Faiencerie Luxembourg L‐1511 Grand Duchy of LuxembourgAbstract In industrial extrusion processes, increasing shear rates can lead to higher production rates. However, at high shear rates, extruded polymers and polymer compounds often exhibit melt instabilities ranging from stick‐slip to sharkskin to gross melt fracture. These instabilities result in challenges to meet the specifications on the extrudate shape. Starting with an existing published data set on melt instabilities in polymer extrusion, we assess the suitability of clustering, unsupervised machine learning algorithms combined with feature selection, to extract and identify hidden and important features from this data set, and their possible relationship with melt instabilities. The data set consists of both intrinsic features of the polymer as well as extrinsic features controlled and measured during an extrusion experiment. Using a range of commonly available clustering algorithms, it is demonstrated that the features related to only the intrinsic properties of the data set can be reliably divided into two clusters, and that in turn, these two clusters may be associated with either the stick‐slip or sharkskin instability. Furthermore, using a feature ranking on both the intrinsic and extrinsic features of the data set, it is shown that the intrinsic properties of molecular weight and polydispersity are the strongest indicators of clustering.https://doi.org/10.1002/mame.202200628extrusionfeature rankingmelt instabilitiesunsupervised machine learning |
| spellingShingle | Alex Gansen Julian Hennicker Clemens Sill Jean Dheur Jack S. Hale Jörg Baller Melt Instability Identification Using Unsupervised Machine Learning Algorithms Macromolecular Materials and Engineering extrusion feature ranking melt instabilities unsupervised machine learning |
| title | Melt Instability Identification Using Unsupervised Machine Learning Algorithms |
| title_full | Melt Instability Identification Using Unsupervised Machine Learning Algorithms |
| title_fullStr | Melt Instability Identification Using Unsupervised Machine Learning Algorithms |
| title_full_unstemmed | Melt Instability Identification Using Unsupervised Machine Learning Algorithms |
| title_short | Melt Instability Identification Using Unsupervised Machine Learning Algorithms |
| title_sort | melt instability identification using unsupervised machine learning algorithms |
| topic | extrusion feature ranking melt instabilities unsupervised machine learning |
| url | https://doi.org/10.1002/mame.202200628 |
| work_keys_str_mv | AT alexgansen meltinstabilityidentificationusingunsupervisedmachinelearningalgorithms AT julianhennicker meltinstabilityidentificationusingunsupervisedmachinelearningalgorithms AT clemenssill meltinstabilityidentificationusingunsupervisedmachinelearningalgorithms AT jeandheur meltinstabilityidentificationusingunsupervisedmachinelearningalgorithms AT jackshale meltinstabilityidentificationusingunsupervisedmachinelearningalgorithms AT jorgballer meltinstabilityidentificationusingunsupervisedmachinelearningalgorithms |