Home > Research > Publications & Outputs > Machine learning framework to predict nonwoven ...

Research

Links

Text available via DOI:

View graph of relations

Machine learning framework to predict nonwoven material properties from fiber graph representations

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Machine learning framework to predict nonwoven material properties from fiber graph representations. / Antweiler, Dario; Harmening, Marc; Marheineke, Nicole et al.
In: Software Impacts, Vol. 14, 100423, 31.12.2022.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Antweiler, D, Harmening, M, Marheineke, N, Schmeißer, A, Wegener, R & Welke, P 2022, 'Machine learning framework to predict nonwoven material properties from fiber graph representations', Software Impacts, vol. 14, 100423. https://doi.org/10.1016/J.SIMPA.2022.100423

APA

Antweiler, D., Harmening, M., Marheineke, N., Schmeißer, A., Wegener, R., & Welke, P. (2022). Machine learning framework to predict nonwoven material properties from fiber graph representations. Software Impacts, 14, Article 100423. https://doi.org/10.1016/J.SIMPA.2022.100423

Vancouver

Antweiler D, Harmening M, Marheineke N, Schmeißer A, Wegener R, Welke P. Machine learning framework to predict nonwoven material properties from fiber graph representations. Software Impacts. 2022 Dec 31;14:100423. Epub 2022 Sept 23. doi: 10.1016/J.SIMPA.2022.100423

Author

Antweiler, Dario ; Harmening, Marc ; Marheineke, Nicole et al. / Machine learning framework to predict nonwoven material properties from fiber graph representations. In: Software Impacts. 2022 ; Vol. 14.

Bibtex

@article{d8e2ed119fbf4bacb728478e61c94209,
title = "Machine learning framework to predict nonwoven material properties from fiber graph representations",
abstract = "Nonwoven fiber materials are omnipresent in diverse applications including insulation, clothing and filtering. Simulation of material properties from production parameters is an industry goal but a challenging task. We developed a machine learning based approach to predict the tensile strength of nonwovens from fiber lay-down settings via a regression model. Here we present an open source framework implementing the following two-step approach: First, a graph generation algorithm constructs stochastic graphs, that resemble the adhered fiber structure of the nonwovens, given a parameter space. Secondly, our regression model, learned from ODE-simulation results, predicts the tensile strength for unseen parameter combinations.",
author = "Dario Antweiler and Marc Harmening and Nicole Marheineke and Andre Schmei{\ss}er and Raimund Wegener and Pascal Welke",
note = "DBLP's bibliographic metadata records provided through http://dblp.org/search/publ/api are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.",
year = "2022",
month = dec,
day = "31",
doi = "10.1016/J.SIMPA.2022.100423",
language = "English",
volume = "14",
journal = "Software Impacts",
issn = "2665-9638",
publisher = "Elsevier B.V.",

}

RIS

TY - JOUR

T1 - Machine learning framework to predict nonwoven material properties from fiber graph representations

AU - Antweiler, Dario

AU - Harmening, Marc

AU - Marheineke, Nicole

AU - Schmeißer, Andre

AU - Wegener, Raimund

AU - Welke, Pascal

N1 - DBLP's bibliographic metadata records provided through http://dblp.org/search/publ/api are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.

PY - 2022/12/31

Y1 - 2022/12/31

N2 - Nonwoven fiber materials are omnipresent in diverse applications including insulation, clothing and filtering. Simulation of material properties from production parameters is an industry goal but a challenging task. We developed a machine learning based approach to predict the tensile strength of nonwovens from fiber lay-down settings via a regression model. Here we present an open source framework implementing the following two-step approach: First, a graph generation algorithm constructs stochastic graphs, that resemble the adhered fiber structure of the nonwovens, given a parameter space. Secondly, our regression model, learned from ODE-simulation results, predicts the tensile strength for unseen parameter combinations.

AB - Nonwoven fiber materials are omnipresent in diverse applications including insulation, clothing and filtering. Simulation of material properties from production parameters is an industry goal but a challenging task. We developed a machine learning based approach to predict the tensile strength of nonwovens from fiber lay-down settings via a regression model. Here we present an open source framework implementing the following two-step approach: First, a graph generation algorithm constructs stochastic graphs, that resemble the adhered fiber structure of the nonwovens, given a parameter space. Secondly, our regression model, learned from ODE-simulation results, predicts the tensile strength for unseen parameter combinations.

U2 - 10.1016/J.SIMPA.2022.100423

DO - 10.1016/J.SIMPA.2022.100423

M3 - Journal article

VL - 14

JO - Software Impacts

JF - Software Impacts

SN - 2665-9638

M1 - 100423

ER -