Title
Prediction of long-term creep modulus of thermoplastics using brief tests and interpretable machine learningAuthor
Author (from another institution)
xmlui.dri2xhtml.METS-1.0.item-contributorOtherinstitution
https://ror.org/02e24yw40https://ror.org/000xsnr85
Version
http://purl.org/coar/version/c_ab4af688f83e57aa
Rights
© 2024 ElsevierAccess
http://purl.org/coar/access_right/c_f1cfPublisher’s version
https://doi.org/10.1016/j.ijsolstr.2024.113014Published at
International Journal of Solids and Structures Vol. 304. N. art. 113014, 2024Publisher
ElsevierKeywords
creep
Machine learning
linear regression
thermoplastic materials ... [+]
Machine learning
linear regression
thermoplastic materials ... [+]
creep
Machine learning
linear regression
thermoplastic materials
materials informatics
ODS 9 Industria, innovación e infraestructura
ODS 12 Producción y consumo responsables [-]
Machine learning
linear regression
thermoplastic materials
materials informatics
ODS 9 Industria, innovación e infraestructura
ODS 12 Producción y consumo responsables [-]
Abstract
The prediction of creep behavior plays a critical role in the design of thermoplastic materials intended for prolonged use. The creep modulus, which describes the relationship between stress and strai ... [+]
The prediction of creep behavior plays a critical role in the design of thermoplastic materials intended for prolonged use. The creep modulus, which describes the relationship between stress and strain that a material experiences over time, is a key property to determine the long-term thermo-mechanical performance of thermoplastics. Due to the time-consuming and resource-intensive nature of testing for this property, the present work investigates the potential of data-driven techniques as an alternative approach. To accomplish this, a dataset comprising more than 400 distinct thermoplastic grades was obtained from CAMPUS® online open database. Then, various interpretable machine learning models (linear regression, decision trees, random forests, XGBoost, and LightGBM) were evaluated to predict the long-term creep modulus with data from brief tests. To accurately assess the models’ ability to generalize to new data, rigorous model evaluation techniques such as cross-validation and group-splitting were employed, showing that various algorithms can predict the creep modulus with
scores above 0.99. Interestingly, linear regression not only matches but, in some cases, also surpasses the performance of more complex models, while being the most simple and interpretable. The present work demonstrates that machine learning can bypass the most lengthy creep tests; reducing costs, energy consumption, material waste, and product development time. [-]
Collections
- Articles - Engineering [667]
The following license files are associated with this item: