---
_id: '62078'
abstract:
- lang: eng
text: 'Fiber reinforced plastics (FRP) exhibit strongly non-linear deformation behavior.
To capture this in simulations, intricate models with a variety of parameters
are typically used. The identification of values for such parameters is highly
challenging and requires in depth understanding of the model itself. Machine learning
(ML) is a promising approach for alleviating this challenge by directly predicting
parameters based on experimental results. So far, this works mostly for purely
artificial data. In this work, two approaches to generalize to experimental data
are investigated: a sequential approach, leveraging understanding of the constitutive
model and a direct, purely data driven approach. This is exemplary carried out
for a highly non-linear strain rate dependent constitutive model for the shear
behavior of FRP.The sequential model is found to work better on both artificial
and experimental data. It is capable of extracting well suited parameters from
the artificial data under realistic conditions. For the experimental data, the
model performance depends on the composition of the experimental curves, varying
between excellently suiting and reasonable predictions. Taking the expert knowledge
into account for ML-model training led to far better results than the purely data
driven approach. Robustifying the model predictions on experimental data promises
further improvement. '
author:
- first_name: Johannes
full_name: Gerritzen, Johannes
id: '105344'
last_name: Gerritzen
orcid: 0000-0002-0169-8602
- first_name: Andreas
full_name: Hornig, Andreas
last_name: Hornig
- first_name: Peter
full_name: Winkler, Peter
last_name: Winkler
- first_name: Maik
full_name: Gude, Maik
last_name: Gude
citation:
ama: 'Gerritzen J, Hornig A, Winkler P, Gude M. Direct parameter identification
for highly nonlinear strain rate dependent constitutive models using machine learning.
In: ECCM21 - Proceedings of the 21st European Conference on Composite Materials.
Vol 3. European Society for Composite Materials (ESCM); 2024:1252–1259. doi:10.60691/yj56-np80'
apa: Gerritzen, J., Hornig, A., Winkler, P., & Gude, M. (2024). Direct parameter
identification for highly nonlinear strain rate dependent constitutive models
using machine learning. ECCM21 - Proceedings of the 21st European Conference
on Composite Materials, 3, 1252–1259. https://doi.org/10.60691/yj56-np80
bibtex: '@inproceedings{Gerritzen_Hornig_Winkler_Gude_2024, title={Direct parameter
identification for highly nonlinear strain rate dependent constitutive models
using machine learning}, volume={3}, DOI={10.60691/yj56-np80},
booktitle={ECCM21 - Proceedings of the 21st European Conference on Composite Materials},
publisher={European Society for Composite Materials (ESCM)}, author={Gerritzen,
Johannes and Hornig, Andreas and Winkler, Peter and Gude, Maik}, year={2024},
pages={1252–1259} }'
chicago: Gerritzen, Johannes, Andreas Hornig, Peter Winkler, and Maik Gude. “Direct
Parameter Identification for Highly Nonlinear Strain Rate Dependent Constitutive
Models Using Machine Learning.” In ECCM21 - Proceedings of the 21st European
Conference on Composite Materials, 3:1252–1259. European Society for Composite
Materials (ESCM), 2024. https://doi.org/10.60691/yj56-np80.
ieee: 'J. Gerritzen, A. Hornig, P. Winkler, and M. Gude, “Direct parameter identification
for highly nonlinear strain rate dependent constitutive models using machine learning,”
in ECCM21 - Proceedings of the 21st European Conference on Composite Materials,
2024, vol. 3, pp. 1252–1259, doi: 10.60691/yj56-np80.'
mla: Gerritzen, Johannes, et al. “Direct Parameter Identification for Highly Nonlinear
Strain Rate Dependent Constitutive Models Using Machine Learning.” ECCM21 -
Proceedings of the 21st European Conference on Composite Materials, vol. 3,
European Society for Composite Materials (ESCM), 2024, pp. 1252–1259, doi:10.60691/yj56-np80.
short: 'J. Gerritzen, A. Hornig, P. Winkler, M. Gude, in: ECCM21 - Proceedings of
the 21st European Conference on Composite Materials, European Society for Composite
Materials (ESCM), 2024, pp. 1252–1259.'
date_created: 2025-11-04T12:47:06Z
date_updated: 2026-02-27T06:46:21Z
doi: 10.60691/yj56-np80
intvolume: ' 3'
keyword:
- Direct parameter identification
- Machine learning
- Convolutional neural networks
- Strain rate dependency
- Fiber reinforced plastics
- woven composites
- segmentation
- synthetic training data
- x-ray computed tomography
language:
- iso: eng
page: 1252–1259
project:
- _id: '130'
name: 'TRR 285: Methodenentwicklung zur mechanischen Fügbarkeit in wandlungsfähigen
Prozessketten'
- _id: '137'
name: TRR 285 - Subproject A03
- _id: '131'
name: TRR 285 - Project Area A
publication: ECCM21 - Proceedings of the 21st European Conference on Composite Materials
publication_identifier:
isbn:
- 978-2-912985-01-9
publisher: European Society for Composite Materials (ESCM)
status: public
title: Direct parameter identification for highly nonlinear strain rate dependent
constitutive models using machine learning
type: conference
user_id: '105344'
volume: 3
year: '2024'
...
---
_id: '52816'
abstract:
- lang: eng
text: "Manufacturing companies face the challenge of reaching required quality standards.
Using\r\noptical sensors and deep learning might help. However, training deep
learning algorithms\r\nrequire large amounts of visual training data. Using domain
randomization to generate synthetic\r\nimage data can alleviate this bottleneck.
This paper presents the application of synthetic\r\nimage training data for optical
quality inspections using visual sensor technology. The results\r\nshow synthetically
generated training data are appropriate for visual quality inspections."
author:
- first_name: Iris
full_name: Gräßler, Iris
id: '47565'
last_name: Gräßler
orcid: 0000-0001-5765-971X
- first_name: Michael
full_name: Hieb, Michael
id: '72252'
last_name: Hieb
citation:
ama: 'Gräßler I, Hieb M. Creating Synthetic Training Datasets for Inspection in
Machine Vision Quality Gates in Manufacturing. In: Lectures. AMA Service
GmbH, Von-Münchhausen-Str. 49, 31515 Wunstorf, Germany; 2023:253-524. doi:10.5162/smsi2023/d7.4'
apa: Gräßler, I., & Hieb, M. (2023). Creating Synthetic Training Datasets for
Inspection in Machine Vision Quality Gates in Manufacturing. Lectures,
253–524. https://doi.org/10.5162/smsi2023/d7.4
bibtex: '@inproceedings{Gräßler_Hieb_2023, title={Creating Synthetic Training Datasets
for Inspection in Machine Vision Quality Gates in Manufacturing}, DOI={10.5162/smsi2023/d7.4},
booktitle={Lectures}, publisher={AMA Service GmbH, Von-Münchhausen-Str. 49, 31515
Wunstorf, Germany}, author={Gräßler, Iris and Hieb, Michael}, year={2023}, pages={253–524}
}'
chicago: Gräßler, Iris, and Michael Hieb. “Creating Synthetic Training Datasets
for Inspection in Machine Vision Quality Gates in Manufacturing.” In Lectures,
253–524. AMA Service GmbH, Von-Münchhausen-Str. 49, 31515 Wunstorf, Germany, 2023.
https://doi.org/10.5162/smsi2023/d7.4.
ieee: 'I. Gräßler and M. Hieb, “Creating Synthetic Training Datasets for Inspection
in Machine Vision Quality Gates in Manufacturing,” in Lectures, Nuremberg,
2023, pp. 253–524, doi: 10.5162/smsi2023/d7.4.'
mla: Gräßler, Iris, and Michael Hieb. “Creating Synthetic Training Datasets for
Inspection in Machine Vision Quality Gates in Manufacturing.” Lectures,
AMA Service GmbH, Von-Münchhausen-Str. 49, 31515 Wunstorf, Germany, 2023, pp.
253–524, doi:10.5162/smsi2023/d7.4.
short: 'I. Gräßler, M. Hieb, in: Lectures, AMA Service GmbH, Von-Münchhausen-Str.
49, 31515 Wunstorf, Germany, 2023, pp. 253–524.'
conference:
end_date: 2023-05-11
location: Nuremberg
name: SMSI 2023. Sensor and Measurement Science International
start_date: 2023-05-08
date_created: 2024-03-25T10:16:24Z
date_updated: 2024-03-25T11:05:53Z
department:
- _id: '152'
doi: 10.5162/smsi2023/d7.4
keyword:
- synthetic training data
- machine vision quality gates
- deep learning
- automated inspection and quality control
- production control
language:
- iso: eng
page: 253-524
publication: Lectures
publication_status: published
publisher: AMA Service GmbH, Von-Münchhausen-Str. 49, 31515 Wunstorf, Germany
quality_controlled: '1'
status: public
title: Creating Synthetic Training Datasets for Inspection in Machine Vision Quality
Gates in Manufacturing
type: conference
user_id: '5905'
year: '2023'
...