Methodology for Neural Network-Based Material Card Calibration Using LS-DYNA <i>MAT_187_SAMP-1</i> Considering Failure with GISSMO
A neural network (NN)-based method is presented in this paper which allows the identification of parameters for material cards used in Finite Element simulations. Contrary to the conventionally used computationally intensive material parameter identification (MPI) by numerical optimization with inte...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Materials |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1944/15/2/643 |
| _version_ | 1797492342208331776 |
|---|---|
| author | Paul Meißner Jens Winter Thomas Vietor |
| author_facet | Paul Meißner Jens Winter Thomas Vietor |
| author_sort | Paul Meißner |
| collection | DOAJ |
| description | A neural network (NN)-based method is presented in this paper which allows the identification of parameters for material cards used in Finite Element simulations. Contrary to the conventionally used computationally intensive material parameter identification (MPI) by numerical optimization with internal or commercial software, a machine learning (ML)-based method is time saving when used repeatedly. Within this article, a self-developed ML-based Python framework is presented, which offers advantages, especially in the development of structural components in early development phases. In this procedure, different machine learning methods are used and adapted to the specific MPI problem considered herein. Using the developed NN-based and the common optimization-based method with LS-OPT, the material parameters of the LS-DYNA material card <i>MAT_187_SAMP-1</i> and the failure model <i>GISSMO</i> were exemplarily calibrated for a virtually generated test dataset. Parameters for the description of elasticity, plasticity, tension–compression asymmetry, variable plastic Poisson’s ratio (VPPR), strain rate dependency and failure were taken into account. The focus of this paper is on performing a comparative study of the two different MPI methods with varying settings (algorithms, hyperparameters, etc.). Furthermore, the applicability of the NN-based procedure for the specific usage of both material cards was investigated. The studies reveal the general applicability for the calibration of a complex material card by the example of the used <i>MAT_187_SAMP-1</i>. |
| first_indexed | 2024-03-10T01:02:17Z |
| format | Article |
| id | doaj.art-2280746c9d124d9d84e48fe83b3dd942 |
| institution | Directory Open Access Journal |
| issn | 1996-1944 |
| language | English |
| last_indexed | 2024-03-10T01:02:17Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Materials |
| spelling | doaj.art-2280746c9d124d9d84e48fe83b3dd9422023-11-23T14:32:33ZengMDPI AGMaterials1996-19442022-01-0115264310.3390/ma15020643Methodology for Neural Network-Based Material Card Calibration Using LS-DYNA <i>MAT_187_SAMP-1</i> Considering Failure with GISSMOPaul Meißner0Jens Winter1Thomas Vietor2Institute for Engineering Design, Technische Universität Braunschweig, Hermann-Blenk-Strasse 42, 38108 Brunswick, GermanyInstitute for Engineering Design, Technische Universität Braunschweig, Hermann-Blenk-Strasse 42, 38108 Brunswick, GermanyInstitute for Engineering Design, Technische Universität Braunschweig, Hermann-Blenk-Strasse 42, 38108 Brunswick, GermanyA neural network (NN)-based method is presented in this paper which allows the identification of parameters for material cards used in Finite Element simulations. Contrary to the conventionally used computationally intensive material parameter identification (MPI) by numerical optimization with internal or commercial software, a machine learning (ML)-based method is time saving when used repeatedly. Within this article, a self-developed ML-based Python framework is presented, which offers advantages, especially in the development of structural components in early development phases. In this procedure, different machine learning methods are used and adapted to the specific MPI problem considered herein. Using the developed NN-based and the common optimization-based method with LS-OPT, the material parameters of the LS-DYNA material card <i>MAT_187_SAMP-1</i> and the failure model <i>GISSMO</i> were exemplarily calibrated for a virtually generated test dataset. Parameters for the description of elasticity, plasticity, tension–compression asymmetry, variable plastic Poisson’s ratio (VPPR), strain rate dependency and failure were taken into account. The focus of this paper is on performing a comparative study of the two different MPI methods with varying settings (algorithms, hyperparameters, etc.). Furthermore, the applicability of the NN-based procedure for the specific usage of both material cards was investigated. The studies reveal the general applicability for the calibration of a complex material card by the example of the used <i>MAT_187_SAMP-1</i>.https://www.mdpi.com/1996-1944/15/2/643parameter identificationmachine learninghyperparameter optimizationLS-DYNA<i>MAT_187_SAMP-1</i>GISSMO failure model |
| spellingShingle | Paul Meißner Jens Winter Thomas Vietor Methodology for Neural Network-Based Material Card Calibration Using LS-DYNA <i>MAT_187_SAMP-1</i> Considering Failure with GISSMO Materials parameter identification machine learning hyperparameter optimization LS-DYNA <i>MAT_187_SAMP-1</i> GISSMO failure model |
| title | Methodology for Neural Network-Based Material Card Calibration Using LS-DYNA <i>MAT_187_SAMP-1</i> Considering Failure with GISSMO |
| title_full | Methodology for Neural Network-Based Material Card Calibration Using LS-DYNA <i>MAT_187_SAMP-1</i> Considering Failure with GISSMO |
| title_fullStr | Methodology for Neural Network-Based Material Card Calibration Using LS-DYNA <i>MAT_187_SAMP-1</i> Considering Failure with GISSMO |
| title_full_unstemmed | Methodology for Neural Network-Based Material Card Calibration Using LS-DYNA <i>MAT_187_SAMP-1</i> Considering Failure with GISSMO |
| title_short | Methodology for Neural Network-Based Material Card Calibration Using LS-DYNA <i>MAT_187_SAMP-1</i> Considering Failure with GISSMO |
| title_sort | methodology for neural network based material card calibration using ls dyna i mat 187 samp 1 i considering failure with gissmo |
| topic | parameter identification machine learning hyperparameter optimization LS-DYNA <i>MAT_187_SAMP-1</i> GISSMO failure model |
| url | https://www.mdpi.com/1996-1944/15/2/643 |
| work_keys_str_mv | AT paulmeißner methodologyforneuralnetworkbasedmaterialcardcalibrationusinglsdynaimat187samp1iconsideringfailurewithgissmo AT jenswinter methodologyforneuralnetworkbasedmaterialcardcalibrationusinglsdynaimat187samp1iconsideringfailurewithgissmo AT thomasvietor methodologyforneuralnetworkbasedmaterialcardcalibrationusinglsdynaimat187samp1iconsideringfailurewithgissmo |