Abstract
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 MAT_187_SAMP-1 and the failure model GISSMO 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 MAT_187_SAMP-1.
Highlights
In recent years, the application of FE analyses has become an indispensable tool in the product development process, especially when it comes to the design and dimensioning of structural components with complex materials such as polymers or fiber-reinforced plastics [1,2,3]
A doubling of the dynamic time warping (DTW) does not necessarily result in twice as bad reproduction quality compared to the reference curve
The required labeled data were generated by a large number of numerical simulations and the feedforward artificial neural network (FFANN) was trained using these data
Summary
The application of FE analyses has become an indispensable tool in the product development process, especially when it comes to the design and dimensioning of structural components with complex materials such as polymers or fiber-reinforced plastics [1,2,3]. Due to the increasing computational capacity and the progress in the software development of FE programs, the level of detail in calculations has increased in recent years and the generated data have become more accurate [4]. The required computing resources, as well as application-dependent high computing time and necessary user expertise often represent a barrier to the use of CAE software in the development process. To perform high-quality FE analyses, material cards are required for FE solvers which are able to represent the respective material behavior of the evaluated model with sufficient quality. State-of-the-art FE solvers use a large number of various different and mostly phenomenological material models [6,7,8,9]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
