---
_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'
...
---
_id: '22480'
abstract:
- lang: eng
text: In this publication important aspects for the implementation of inductive
locating are explained. The miniaturized sensor platform called Sens-o-Spheres
is used as an application of this locating method. The sensor platform is applied
in bioreactors in order to obtain the environmental parameters, which makes a
localization by magnetic fields necessary. Since the properties of magnetic fields
in the localization area are very different from the wave characteristics, the
principle of inductive localization is investigated in this publication and explained
by using electrical equivalent circuit diagrams. Thereby, inductive localization
uses the coupling or the mutual inductivities between coils, which is noticeable
by an induced voltage. Therefore some properties and procedures are explained
to extract the location of Sens-o-Spheres or other industrial sensor platforms
from the couplings of the coils. One method calculates the location from an adapted
ratio calculation and the other method uses neural networks and stochastic filters
to obtain the results. In the end, these results are evaluated and compared.
author:
- first_name: Sven
full_name: Lange, Sven
id: '38240'
last_name: Lange
- first_name: Dominik
full_name: Schröder, Dominik
last_name: Schröder
- first_name: Christian
full_name: Hedayat, Christian
last_name: Hedayat
- first_name: Harald
full_name: Kuhn, Harald
last_name: Kuhn
- first_name: Ulrich
full_name: Hilleringmann, Ulrich
last_name: Hilleringmann
citation:
ama: 'Lange S, Schröder D, Hedayat C, Kuhn H, Hilleringmann U. Development of Methods
for Coil-Based Localization by Magnetic Fields of Miniaturized Sensor Platforms
in Bioprocesses. In: 22nd IEEE International Conference on Industrial Technology
(ICIT). Valencia, Spain : IEEE; 2021. doi:10.1109/icit46573.2021.9453609'
apa: 'Lange, S., Schröder, D., Hedayat, C., Kuhn, H., & Hilleringmann, U. (2021).
Development of Methods for Coil-Based Localization by Magnetic Fields of Miniaturized
Sensor Platforms in Bioprocesses. In 22nd IEEE International Conference on
Industrial Technology (ICIT). Valencia, Spain : IEEE. https://doi.org/10.1109/icit46573.2021.9453609'
bibtex: '@inproceedings{Lange_Schröder_Hedayat_Kuhn_Hilleringmann_2021, place={
Valencia, Spain }, title={Development of Methods for Coil-Based Localization by
Magnetic Fields of Miniaturized Sensor Platforms in Bioprocesses}, DOI={10.1109/icit46573.2021.9453609},
booktitle={22nd IEEE International Conference on Industrial Technology (ICIT)},
publisher={IEEE}, author={Lange, Sven and Schröder, Dominik and Hedayat, Christian
and Kuhn, Harald and Hilleringmann, Ulrich}, year={2021} }'
chicago: 'Lange, Sven, Dominik Schröder, Christian Hedayat, Harald Kuhn, and Ulrich
Hilleringmann. “Development of Methods for Coil-Based Localization by Magnetic
Fields of Miniaturized Sensor Platforms in Bioprocesses.” In 22nd IEEE International
Conference on Industrial Technology (ICIT). Valencia, Spain : IEEE, 2021.
https://doi.org/10.1109/icit46573.2021.9453609.'
ieee: S. Lange, D. Schröder, C. Hedayat, H. Kuhn, and U. Hilleringmann, “Development
of Methods for Coil-Based Localization by Magnetic Fields of Miniaturized Sensor
Platforms in Bioprocesses,” in 22nd IEEE International Conference on Industrial
Technology (ICIT), Valencia, Spain , 2021.
mla: Lange, Sven, et al. “Development of Methods for Coil-Based Localization by
Magnetic Fields of Miniaturized Sensor Platforms in Bioprocesses.” 22nd IEEE
International Conference on Industrial Technology (ICIT), IEEE, 2021, doi:10.1109/icit46573.2021.9453609.
short: 'S. Lange, D. Schröder, C. Hedayat, H. Kuhn, U. Hilleringmann, in: 22nd IEEE
International Conference on Industrial Technology (ICIT), IEEE, Valencia, Spain
, 2021.'
conference:
end_date: 2021-03-12
location: 'Valencia, Spain '
name: 22nd IEEE International Conference on Industrial Technology (ICIT)
start_date: 2021-03-10
date_created: 2021-06-20T23:25:54Z
date_updated: 2022-01-06T06:55:33Z
department:
- _id: '59'
- _id: '485'
doi: 10.1109/icit46573.2021.9453609
keyword:
- Location awareness
- Coils
- Couplings
- Nonuniform electric fields
- Magnetic separation
- Neural networks
- Training data
language:
- iso: eng
main_file_link:
- url: https://ieeexplore.ieee.org/document/9453609
place: ' Valencia, Spain '
project:
- _id: '52'
name: Computing Resources Provided by the Paderborn Center for Parallel Computing
publication: 22nd IEEE International Conference on Industrial Technology (ICIT)
publication_identifier:
isbn:
- '9781728157306'
publication_status: published
publisher: IEEE
status: public
title: Development of Methods for Coil-Based Localization by Magnetic Fields of Miniaturized
Sensor Platforms in Bioprocesses
type: conference
user_id: '38240'
year: '2021'
...
---
_id: '11943'
abstract:
- lang: eng
text: A marginalized particle filter is proposed for performing single channel speech
enhancement with a non-linear dynamic state model. The system consists of a particle
filter for tracking line spectral pair (LSP) parameters and a Kalman filter per
particle for speech enhancement. The state model for the LSPs has been learnt
on clean speech training data. In our approach parameters and speech samples are
processed at different time scales by assuming the parameters to be constant for
small blocks of data. Further enhancement is obtained by an iteration which can
be applied on these small blocks. The experiments show that similar SNR gains
are obtained as with the Kalman-LM-iterative algorithm. However better values
of the noise level and the log-spectral distance are achieved
author:
- first_name: Stefan
full_name: Windmann, Stefan
last_name: Windmann
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Windmann S, Haeb-Umbach R. Iterative Speech Enhancement using a Non-Linear
Dynamic State Model of Speech and its Parameters. In: IEEE International Conference
on Acoustics, Speech and Signal Processing (ICASSP 2006). Vol 1. ; 2006:I.
doi:10.1109/ICASSP.2006.1660058'
apa: Windmann, S., & Haeb-Umbach, R. (2006). Iterative Speech Enhancement using
a Non-Linear Dynamic State Model of Speech and its Parameters. In IEEE International
Conference on Acoustics, Speech and Signal Processing (ICASSP 2006) (Vol.
1, p. I). https://doi.org/10.1109/ICASSP.2006.1660058
bibtex: '@inproceedings{Windmann_Haeb-Umbach_2006, title={Iterative Speech Enhancement
using a Non-Linear Dynamic State Model of Speech and its Parameters}, volume={1},
DOI={10.1109/ICASSP.2006.1660058},
booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing
(ICASSP 2006)}, author={Windmann, Stefan and Haeb-Umbach, Reinhold}, year={2006},
pages={I} }'
chicago: Windmann, Stefan, and Reinhold Haeb-Umbach. “Iterative Speech Enhancement
Using a Non-Linear Dynamic State Model of Speech and Its Parameters.” In IEEE
International Conference on Acoustics, Speech and Signal Processing (ICASSP 2006),
1:I, 2006. https://doi.org/10.1109/ICASSP.2006.1660058.
ieee: S. Windmann and R. Haeb-Umbach, “Iterative Speech Enhancement using a Non-Linear
Dynamic State Model of Speech and its Parameters,” in IEEE International Conference
on Acoustics, Speech and Signal Processing (ICASSP 2006), 2006, vol. 1, p.
I.
mla: Windmann, Stefan, and Reinhold Haeb-Umbach. “Iterative Speech Enhancement Using
a Non-Linear Dynamic State Model of Speech and Its Parameters.” IEEE International
Conference on Acoustics, Speech and Signal Processing (ICASSP 2006), vol.
1, 2006, p. I, doi:10.1109/ICASSP.2006.1660058.
short: 'S. Windmann, R. Haeb-Umbach, in: IEEE International Conference on Acoustics,
Speech and Signal Processing (ICASSP 2006), 2006, p. I.'
date_created: 2019-07-12T05:31:15Z
date_updated: 2022-01-06T06:51:12Z
department:
- _id: '54'
doi: 10.1109/ICASSP.2006.1660058
intvolume: ' 1'
keyword:
- clean speech training data
- iterative methods
- iterative speech enhancement
- Kalman filter
- Kalman filters
- Kalman-LM-iterative algorithm
- line spectral pair parameters
- log-spectral distance
- marginalized particle filter
- noise level
- nonlinear dynamic state speech model
- particle filtering (numerical methods)
- single channel speech enhancement
- SNR gains
- speech enhancement
- speech samples
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2006/WiHa06-2.pdf
oa: '1'
page: I
publication: IEEE International Conference on Acoustics, Speech and Signal Processing
(ICASSP 2006)
status: public
title: Iterative Speech Enhancement using a Non-Linear Dynamic State Model of Speech
and its Parameters
type: conference
user_id: '44006'
volume: 1
year: '2006'
...
---
_id: '11778'
abstract:
- lang: eng
text: In this paper, it is shown that a correlation criterion is the appropriate
criterion for bottom-up clustering to obtain broad phonetic class regression trees
for maximum likelihood linear regression (MLLR)-based speaker adaptation. The
correlation structure among speech units is estimated on the speaker-independent
training data. In adaptation experiments the tree outperformed a regression tree
obtained from clustering according to closeness in acoustic space and achieved
results comparable with those of a manually designed broad phonetic class tree
author:
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: Haeb-Umbach R. Automatic generation of phonetic regression class trees for
MLLR adaptation. IEEE Transactions on Speech and Audio Processing. 2001;9(3):299-302.
doi:10.1109/89.906003
apa: Haeb-Umbach, R. (2001). Automatic generation of phonetic regression class trees
for MLLR adaptation. IEEE Transactions on Speech and Audio Processing,
9(3), 299–302. https://doi.org/10.1109/89.906003
bibtex: '@article{Haeb-Umbach_2001, title={Automatic generation of phonetic regression
class trees for MLLR adaptation}, volume={9}, DOI={10.1109/89.906003},
number={3}, journal={IEEE Transactions on Speech and Audio Processing}, author={Haeb-Umbach,
Reinhold}, year={2001}, pages={299–302} }'
chicago: 'Haeb-Umbach, Reinhold. “Automatic Generation of Phonetic Regression Class
Trees for MLLR Adaptation.” IEEE Transactions on Speech and Audio Processing
9, no. 3 (2001): 299–302. https://doi.org/10.1109/89.906003.'
ieee: R. Haeb-Umbach, “Automatic generation of phonetic regression class trees for
MLLR adaptation,” IEEE Transactions on Speech and Audio Processing, vol.
9, no. 3, pp. 299–302, 2001.
mla: Haeb-Umbach, Reinhold. “Automatic Generation of Phonetic Regression Class Trees
for MLLR Adaptation.” IEEE Transactions on Speech and Audio Processing,
vol. 9, no. 3, 2001, pp. 299–302, doi:10.1109/89.906003.
short: R. Haeb-Umbach, IEEE Transactions on Speech and Audio Processing 9 (2001)
299–302.
date_created: 2019-07-12T05:28:04Z
date_updated: 2022-01-06T06:51:08Z
department:
- _id: '54'
doi: 10.1109/89.906003
intvolume: ' 9'
issue: '3'
keyword:
- acoustic space
- adaptation experiments
- automatic generation
- bottom-up clustering
- broad phonetic class regression trees
- correlation criterion
- correlation methods
- maximum likelihood estimation
- maximum likelihood linear regression based speaker adaptation
- MLLR adaptation
- pattern clustering
- phonetic regression class trees
- speaker-independent training data
- speech recognition
- speech units
- statistical analysis
- trees (mathematics)
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2001/Ha01.pdf
oa: '1'
page: 299-302
publication: IEEE Transactions on Speech and Audio Processing
status: public
title: Automatic generation of phonetic regression class trees for MLLR adaptation
type: journal_article
user_id: '44006'
volume: 9
year: '2001'
...