| bibtype |
J -
Journal Article
|
| ARLID |
0636164 |
| utime |
20250620105931.6 |
| mtime |
20250610235959.9 |
| DOI |
10.1007/s00707-025-04385-8 |
| title
(primary) (eng) |
Parameter estimation in cyclic plastic loading |
| specification |
| page_count |
18 s. |
| media_type |
E |
|
| serial |
| ARLID |
cav_un_epca*0256062 |
| ISSN |
0001-5970 |
| title
|
Acta Mechanica |
| publisher |
|
|
| keyword |
Neural Network |
| keyword |
Cyclic Plastic Loading |
| keyword |
Parameter Estimation |
| keyword |
Non-gradient optimization |
| author
(primary) |
| ARLID |
cav_un_auth*0488850 |
| name1 |
Kovanda |
| name2 |
Martin |
| institution |
UTIA-B |
| full_dept (cz) |
Stochastická informatika |
| full_dept (eng) |
Department of Stochastic Informatics |
| department (cz) |
SI |
| department (eng) |
SI |
| country |
CZ |
| share |
40 |
| garant |
K |
| fullinstit |
Ústav teorie informace a automatizace AV ČR, v. v. i. |
|
| author
|
| ARLID |
cav_un_auth*0283918 |
| name1 |
Marek |
| name2 |
René |
| institution |
UT-L |
| full_dept (cz) |
D 4 - Rázy a vlny v tělesech |
| full_dept |
D 4 - Impact and Waves in Solids |
| country |
CZ |
| share |
30 |
| fullinstit |
Ústav termomechaniky AV ČR, v. v. i. |
|
| author
|
| ARLID |
cav_un_auth*0101212 |
| name1 |
Tichavský |
| name2 |
Petr |
| institution |
UTIA-B |
| full_dept (cz) |
Stochastická informatika |
| full_dept |
Department of Stochastic Informatics |
| department (cz) |
SI |
| department |
SI |
| full_dept |
Department of Stochastic Informatics |
| share |
30 |
| fullinstit |
Ústav teorie informace a automatizace AV ČR, v. v. i. |
|
| source |
|
| source |
|
| cas_special |
| project |
| project_id |
GA23-05338S |
| agency |
GA ČR |
| ARLID |
cav_un_auth*0452392 |
|
| project |
| project_id |
GA22-11101S |
| agency |
GA ČR |
| country |
CZ |
| ARLID |
cav_un_auth*0435406 |
|
| project |
| project_id |
EH23_020/0008501 |
| agency |
GA MŠk |
| country |
CZ |
| ARLID |
cav_un_auth*0477721 |
|
| abstract
(eng) |
The increasing complexity of modern constitutive models of cyclic metal plasticity requires more efficient ways to achieve their optimal calibration. Traditional approaches, such as random search combined with Nelder-Mead optimization, are computationally expensive. In addition, they struggle with highly non-convex functions that have numerous local minima and complex behavior, making these methods highly sensitive to initial conditions. While numerical refinement is key, a better prediction for its initial point directly saves costs. In this work, we focus only on the uniaxial cyclic loading, as it is the dominant part of a general calibration process for such a model and can also utilize a closed-form solution, further speeding up the procedure. We propose a neural network framework with a loss function that combines the loss on both the predicted parameters and the generated stress responses. This network is then used to predict an initial point for Nelder-Mead optimization. Our method was also compared to the non-gradient Tensor Train Optimization method on both synthetic data and measured experiments. |
| result_subspec |
WOS |
| RIV |
JL |
| FORD0 |
20000 |
| FORD1 |
20300 |
| FORD2 |
20301 |
| reportyear |
2026 |
| num_of_auth |
3 |
| inst_support |
RVO:67985556 |
| inst_support |
RVO:61388998 |
| permalink |
https://hdl.handle.net/11104/0367699 |
| mrcbC61 |
1 |
| confidential |
S |
| mrcbC91 |
A |
| mrcbT16-e |
MECHANICS |
| mrcbT16-f |
2.5 |
| mrcbT16-g |
0.9 |
| mrcbT16-h |
6.9 |
| mrcbT16-i |
0.00524 |
| mrcbT16-j |
0.442 |
| mrcbT16-k |
8999 |
| mrcbT16-q |
93 |
| mrcbT16-s |
0.598 |
| mrcbT16-y |
47.89 |
| mrcbT16-x |
3.04 |
| mrcbT16-3 |
2650 |
| mrcbT16-4 |
Q1 |
| mrcbT16-5 |
2.300 |
| mrcbT16-6 |
362 |
| mrcbT16-7 |
Q2 |
| mrcbT16-C |
64 |
| mrcbT16-M |
0.61 |
| mrcbT16-N |
Q2 |
| mrcbT16-P |
64 |
| arlyear |
2025 |
| mrcbU14 |
SCOPUS |
| mrcbU24 |
PUBMED |
| mrcbU34 |
WOS |
| mrcbU56 |
767 kB |
| mrcbU63 |
cav_un_epca*0256062 Acta Mechanica 2025 0001-5970 1619-6937 Springer |
|