Home > Research > Publications & Outputs > A Regression-Based Predictive Model Hierarchy f...

Research

Links

Text available via DOI:

View graph of relations

A Regression-Based Predictive Model Hierarchy for Nonwoven Tensile Strength Inference

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Chapter

Published

Standard

A Regression-Based Predictive Model Hierarchy for Nonwoven Tensile Strength Inference. / Antweiler, Dario; Burgard, Jan Pablo; Harmening, Marc et al.
Informed Machine Learning. ed. / Daniel Schulz; Christian Bauckhage. Cham: Springer, 2025. p. 63-90.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Chapter

Harvard

Antweiler, D, Burgard, JP, Harmening, M, Marheineke, N, Schmeißer, A, Wegener, R & Welke, P 2025, A Regression-Based Predictive Model Hierarchy for Nonwoven Tensile Strength Inference. in D Schulz & C Bauckhage (eds), Informed Machine Learning. Springer, Cham, pp. 63-90. https://doi.org/10.1007/978-3-031-83097-6_4

APA

Antweiler, D., Burgard, J. P., Harmening, M., Marheineke, N., Schmeißer, A., Wegener, R., & Welke, P. (2025). A Regression-Based Predictive Model Hierarchy for Nonwoven Tensile Strength Inference. In D. Schulz, & C. Bauckhage (Eds.), Informed Machine Learning (pp. 63-90). Springer. https://doi.org/10.1007/978-3-031-83097-6_4

Vancouver

Antweiler D, Burgard JP, Harmening M, Marheineke N, Schmeißer A, Wegener R et al. A Regression-Based Predictive Model Hierarchy for Nonwoven Tensile Strength Inference. In Schulz D, Bauckhage C, editors, Informed Machine Learning. Cham: Springer. 2025. p. 63-90 doi: 10.1007/978-3-031-83097-6_4

Author

Antweiler, Dario ; Burgard, Jan Pablo ; Harmening, Marc et al. / A Regression-Based Predictive Model Hierarchy for Nonwoven Tensile Strength Inference. Informed Machine Learning. editor / Daniel Schulz ; Christian Bauckhage. Cham : Springer, 2025. pp. 63-90

Bibtex

@inbook{39eff5810d4747ed85630ff33d21f4f6,
title = "A Regression-Based Predictive Model Hierarchy for Nonwoven Tensile Strength Inference",
abstract = "Nonwoven materials, characterized by a random fiber structure, are essential for various applications including insulation and filtering. An industrial long-term goal is to establish a framework for the simulation-based design of nonwovens. Due to the random structures, simulations of material properties on fiber network level are computational expensive. We propose a predictive model hierarchy for inferring an important material property---the nonwoven tensile strength behavior. The model hierarchy is built using regression-based approaches, including linear and polynomial models, which provide interpretable results. This allows for significant speedup (six orders of magnitude) over the conventional simulations, while achieving good prediction results (R2=0.95R^2=0.95). The proposed models open the application to nonwoven material design, as they provide accurate and cost-effective surrogates for predicting material properties. In this way, our work serves as a proof of concept.",
author = "Dario Antweiler and Burgard, {Jan Pablo} and Marc Harmening and Nicole Marheineke and Andre Schmei{\ss}er and Raimund Wegener and Pascal Welke",
year = "2025",
month = apr,
day = "10",
doi = "10.1007/978-3-031-83097-6_4",
language = "English",
isbn = "9783031830969",
pages = "63--90",
editor = "Daniel Schulz and Christian Bauckhage",
booktitle = "Informed Machine Learning",
publisher = "Springer",

}

RIS

TY - CHAP

T1 - A Regression-Based Predictive Model Hierarchy for Nonwoven Tensile Strength Inference

AU - Antweiler, Dario

AU - Burgard, Jan Pablo

AU - Harmening, Marc

AU - Marheineke, Nicole

AU - Schmeißer, Andre

AU - Wegener, Raimund

AU - Welke, Pascal

PY - 2025/4/10

Y1 - 2025/4/10

N2 - Nonwoven materials, characterized by a random fiber structure, are essential for various applications including insulation and filtering. An industrial long-term goal is to establish a framework for the simulation-based design of nonwovens. Due to the random structures, simulations of material properties on fiber network level are computational expensive. We propose a predictive model hierarchy for inferring an important material property---the nonwoven tensile strength behavior. The model hierarchy is built using regression-based approaches, including linear and polynomial models, which provide interpretable results. This allows for significant speedup (six orders of magnitude) over the conventional simulations, while achieving good prediction results (R2=0.95R^2=0.95). The proposed models open the application to nonwoven material design, as they provide accurate and cost-effective surrogates for predicting material properties. In this way, our work serves as a proof of concept.

AB - Nonwoven materials, characterized by a random fiber structure, are essential for various applications including insulation and filtering. An industrial long-term goal is to establish a framework for the simulation-based design of nonwovens. Due to the random structures, simulations of material properties on fiber network level are computational expensive. We propose a predictive model hierarchy for inferring an important material property---the nonwoven tensile strength behavior. The model hierarchy is built using regression-based approaches, including linear and polynomial models, which provide interpretable results. This allows for significant speedup (six orders of magnitude) over the conventional simulations, while achieving good prediction results (R2=0.95R^2=0.95). The proposed models open the application to nonwoven material design, as they provide accurate and cost-effective surrogates for predicting material properties. In this way, our work serves as a proof of concept.

U2 - 10.1007/978-3-031-83097-6_4

DO - 10.1007/978-3-031-83097-6_4

M3 - Chapter

SN - 9783031830969

SP - 63

EP - 90

BT - Informed Machine Learning

A2 - Schulz, Daniel

A2 - Bauckhage, Christian

PB - Springer

CY - Cham

ER -