A machine learning investigation of low-density polylactide batch foams
Developing novel foams with tailored properties is a challenge. If properly addressed, efficient screening can potentially accelerate material discovery and reduce material waste, improving sustainability and efficiency in the development phase. In this work, we address this problem using a hybrid e...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
De Gruyter
2022-03-01
|
| Series: | e-Polymers |
| Subjects: | |
| Online Access: | https://doi.org/10.1515/epoly-2022-0031 |
| _version_ | 1828108550279266304 |
|---|---|
| author | Albuquerque Rodrigo Q. Brütting Christian Standau Tobias Ruckdäschel Holger |
| author_facet | Albuquerque Rodrigo Q. Brütting Christian Standau Tobias Ruckdäschel Holger |
| author_sort | Albuquerque Rodrigo Q. |
| collection | DOAJ |
| description | Developing novel foams with tailored properties is a challenge. If properly addressed, efficient screening can potentially accelerate material discovery and reduce material waste, improving sustainability and efficiency in the development phase. In this work, we address this problem using a hybrid experimental and theoretical approach. Machine learning (ML) models were trained to predict the density of polylactide (PLA) foams based on their processing parameters. The final ML ensemble model was a linear combination of gradient boosting, random forest, kernel ridge, and support vector regression models. Comparison of the actual and predicted densities of PLA systems resulted in a mean absolute error of 30 kg·m−3 and a coefficient of determination (R
2) of 0.94. The final ensemble model was then used to explore the ranges of predicted density in the space of processing parameters (temperature, pressure, and time) and to suggest some parameter sets that could lead to low-density PLA foams. The new PLA foams were produced and showed experimental densities in the range of 36–48 kg·m−3, which agreed well with the corresponding predicted values, which ranged between 38 and 54 kg·m−3. The experimental–theoretical procedure described here could be applied to other materials and pave the way to more sustainable and efficient foam development processes. |
| first_indexed | 2024-04-11T10:48:28Z |
| format | Article |
| id | doaj.art-18058d254ac74dcf8792d422a1ad1189 |
| institution | Directory Open Access Journal |
| issn | 1618-7229 |
| language | English |
| last_indexed | 2024-04-11T10:48:28Z |
| publishDate | 2022-03-01 |
| publisher | De Gruyter |
| record_format | Article |
| series | e-Polymers |
| spelling | doaj.art-18058d254ac74dcf8792d422a1ad11892022-12-22T04:28:59ZengDe Gruytere-Polymers1618-72292022-03-0122131833110.1515/epoly-2022-0031A machine learning investigation of low-density polylactide batch foamsAlbuquerque Rodrigo Q.0Brütting Christian1Standau Tobias2Ruckdäschel Holger3Department of Polymer Engineering, University of Bayreuth, Universitätsstraße 30, 95447 Bayreuth, GermanyDepartment of Polymer Engineering, University of Bayreuth, Universitätsstraße 30, 95447 Bayreuth, GermanyDepartment of Polymer Engineering, University of Bayreuth, Universitätsstraße 30, 95447 Bayreuth, GermanyDepartment of Polymer Engineering, University of Bayreuth, Universitätsstraße 30, 95447 Bayreuth, GermanyDeveloping novel foams with tailored properties is a challenge. If properly addressed, efficient screening can potentially accelerate material discovery and reduce material waste, improving sustainability and efficiency in the development phase. In this work, we address this problem using a hybrid experimental and theoretical approach. Machine learning (ML) models were trained to predict the density of polylactide (PLA) foams based on their processing parameters. The final ML ensemble model was a linear combination of gradient boosting, random forest, kernel ridge, and support vector regression models. Comparison of the actual and predicted densities of PLA systems resulted in a mean absolute error of 30 kg·m−3 and a coefficient of determination (R 2) of 0.94. The final ensemble model was then used to explore the ranges of predicted density in the space of processing parameters (temperature, pressure, and time) and to suggest some parameter sets that could lead to low-density PLA foams. The new PLA foams were produced and showed experimental densities in the range of 36–48 kg·m−3, which agreed well with the corresponding predicted values, which ranged between 38 and 54 kg·m−3. The experimental–theoretical procedure described here could be applied to other materials and pave the way to more sustainable and efficient foam development processes.https://doi.org/10.1515/epoly-2022-0031polylactide foamsbiopolymerssustainabilitymachine learningmodel prediction |
| spellingShingle | Albuquerque Rodrigo Q. Brütting Christian Standau Tobias Ruckdäschel Holger A machine learning investigation of low-density polylactide batch foams e-Polymers polylactide foams biopolymers sustainability machine learning model prediction |
| title | A machine learning investigation of low-density polylactide batch foams |
| title_full | A machine learning investigation of low-density polylactide batch foams |
| title_fullStr | A machine learning investigation of low-density polylactide batch foams |
| title_full_unstemmed | A machine learning investigation of low-density polylactide batch foams |
| title_short | A machine learning investigation of low-density polylactide batch foams |
| title_sort | machine learning investigation of low density polylactide batch foams |
| topic | polylactide foams biopolymers sustainability machine learning model prediction |
| url | https://doi.org/10.1515/epoly-2022-0031 |
| work_keys_str_mv | AT albuquerquerodrigoq amachinelearninginvestigationoflowdensitypolylactidebatchfoams AT bruttingchristian amachinelearninginvestigationoflowdensitypolylactidebatchfoams AT standautobias amachinelearninginvestigationoflowdensitypolylactidebatchfoams AT ruckdaschelholger amachinelearninginvestigationoflowdensitypolylactidebatchfoams AT albuquerquerodrigoq machinelearninginvestigationoflowdensitypolylactidebatchfoams AT bruttingchristian machinelearninginvestigationoflowdensitypolylactidebatchfoams AT standautobias machinelearninginvestigationoflowdensitypolylactidebatchfoams AT ruckdaschelholger machinelearninginvestigationoflowdensitypolylactidebatchfoams |