Enhancing damage prediction in bulk metal forming through machine learning-assisted parameter identification
(2024) In Archive of Applied Mechanics 94(8). p.2217-2242- Abstract
The open-source parameter identification tool ADAPT (A diversely applicable parameter identification Tool) is integrated with a machine learning-based approach for start value prediction in order to calibrate a Gurson–Tvergaard–Needleman (GTN) and a Lemaitre damage model. As representative example case-hardened steel 16MnCrS5 is elaborated. An artificial neural network (ANN) is initially trained by using load–displacement curves derived from simulations of a boundary value problem—instead of using data generated for homogeneous states of deformation at material point or one-element level—with varying material parameter combinations. The ANN is then employed so as to predict sets of material parameters that already provide close... (More)
The open-source parameter identification tool ADAPT (A diversely applicable parameter identification Tool) is integrated with a machine learning-based approach for start value prediction in order to calibrate a Gurson–Tvergaard–Needleman (GTN) and a Lemaitre damage model. As representative example case-hardened steel 16MnCrS5 is elaborated. An artificial neural network (ANN) is initially trained by using load–displacement curves derived from simulations of a boundary value problem—instead of using data generated for homogeneous states of deformation at material point or one-element level—with varying material parameter combinations. The ANN is then employed so as to predict sets of material parameters that already provide close solutions to the experiment. These predicted parameter sets serve as starting values for a subsequent multi-objective parameter identification by using ADAPT. ADAPT allows for the consideration of input data from multiple scales, including integral data such as load–displacement curves, full-field data such as displacement and strain fields, and high-resolution experimental void data at the micro-scale. The influence of each data set on prediction quality is analyzed. Using various types of input data introduces additional information, enhancing prediction accuracy. The validation is carried out with respect to experimental void measurements of forward rod extruded parts. The results demonstrate, by incorporating void measurements in the optimization process, that it is possible to improve the quantitative prediction of ductile damage in the sense of void area fractions by factor 28 in forward rod extrusion.
(Less)
- author
- Gerlach, Jan ; Schulte, Robin ; Schowtjak, Alexander ; Clausmeyer, Till ; Ostwald, Richard ; Tekkaya, A. Erman and Menzel, Andreas LU
- organization
- publishing date
- 2024-08
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Bulk metal forming, Ductile damage, finite element method, Machine learning, Parameter identification
- in
- Archive of Applied Mechanics
- volume
- 94
- issue
- 8
- pages
- 26 pages
- publisher
- Springer
- external identifiers
-
- scopus:85198396194
- ISSN
- 0939-1533
- DOI
- 10.1007/s00419-024-02634-1
- language
- English
- LU publication?
- yes
- id
- f19a87bd-925d-4e21-b055-c36de06068ba
- date added to LUP
- 2024-09-24 14:39:36
- date last changed
- 2024-09-24 14:39:36
@article{f19a87bd-925d-4e21-b055-c36de06068ba,
abstract = {{<p>The open-source parameter identification tool ADAPT (A diversely applicable parameter identification Tool) is integrated with a machine learning-based approach for start value prediction in order to calibrate a Gurson–Tvergaard–Needleman (GTN) and a Lemaitre damage model. As representative example case-hardened steel 16MnCrS5 is elaborated. An artificial neural network (ANN) is initially trained by using load–displacement curves derived from simulations of a boundary value problem—instead of using data generated for homogeneous states of deformation at material point or one-element level—with varying material parameter combinations. The ANN is then employed so as to predict sets of material parameters that already provide close solutions to the experiment. These predicted parameter sets serve as starting values for a subsequent multi-objective parameter identification by using ADAPT. ADAPT allows for the consideration of input data from multiple scales, including integral data such as load–displacement curves, full-field data such as displacement and strain fields, and high-resolution experimental void data at the micro-scale. The influence of each data set on prediction quality is analyzed. Using various types of input data introduces additional information, enhancing prediction accuracy. The validation is carried out with respect to experimental void measurements of forward rod extruded parts. The results demonstrate, by incorporating void measurements in the optimization process, that it is possible to improve the quantitative prediction of ductile damage in the sense of void area fractions by factor 28 in forward rod extrusion.</p>}},
author = {{Gerlach, Jan and Schulte, Robin and Schowtjak, Alexander and Clausmeyer, Till and Ostwald, Richard and Tekkaya, A. Erman and Menzel, Andreas}},
issn = {{0939-1533}},
keywords = {{Bulk metal forming; Ductile damage; finite element method; Machine learning; Parameter identification}},
language = {{eng}},
number = {{8}},
pages = {{2217--2242}},
publisher = {{Springer}},
series = {{Archive of Applied Mechanics}},
title = {{Enhancing damage prediction in bulk metal forming through machine learning-assisted parameter identification}},
url = {{http://dx.doi.org/10.1007/s00419-024-02634-1}},
doi = {{10.1007/s00419-024-02634-1}},
volume = {{94}},
year = {{2024}},
}