Graph-based tensile strength approximation of random nonwoven materials by interpretable regression

Machine Learning with Applications

Nicole Marheineke¹  Marc Harmening²  Pascal Welke³  Dario Antweiler⁴  Andre Schmeißer⁵  Raimund Wegener⁵ 

[1] Corresponding author at: Fraunhofer IAIS, Schloss Birlinghoven, Sankt Augustin, 53757, Germany.;Fraunhofer Center for Machine Learning, Schloss Birlinghoven, Sankt Augustin, 53757, Germany;Fraunhofer Center for Machine Learning, Schloss Birlinghoven, Sankt Augustin, 53757, Germany;Fraunhofer IAIS, Schloss Birlinghoven, Sankt Augustin, 53757, Germany;Trier University, Universitaetsring 15, Trier, 54296, Germany;

关键词: Nonwoven fiber material;    Manufacturing;    Textile fabrics;    Material property prediction;    Graph representation;    Interpretable machine learning;   

DOI  :  

来源: DOAJ

【 摘 要 】

Nonwoven materials consist of random fiber structures. They are essential to diverse application areas such as clothing, insulation and filtering. A long term goal in industry is the simulation-based optimization of material properties in dependence of the manufacturing parameters. Recent works developed a framework to predict tensile strength properties representing the fiber structure as a stochastic graph. In this paper we present an efficient machine learning approach using a regression model trained on features extracted from the graph, for which we develop a novel graph stretching algorithm. We demonstrate that applying our method to a practically relevant dataset yields similar prediction results as the original ODE approach (R2=0.98), while achieving a significant speedup by up to three orders of magnitude. This opens the field to optimization, as Monte Carlo simulations accounting for the stochastic nature of nonwovens become easily accessible. Our model generalizes well to unseen parameter combinations. Additionally, our approach produces interpretable results by using a simple linear model for the regression task.

【 授权许可】

Unknown