Implementation of a Neural Network into a User-Material Subroutine for Finite Element Simulation of Material Viscoplasticity
Source abstract
Abstract
Abstract In this study, a neural network is trained to predict the response of a viscoplastic solder alloy based on a reduced data set. The model is shown to accurately describe the behavior of the material for the temperature range from 298 °K to 398 °K and the strain rate range from 2 × 10−5 s−1 to 2 × 10−2 s−1. The model is then implemented in the form of a user subroutine in the finite element code Abaqus to be used for simulations of the material behavior. The implementation requires that the weights and biases of the network are extracted and that its gradients (derivatives of the output with respect to the inputs) are calculated to be passed on to the user subroutine. Finite element (FE) simulations based on the implemented neural network are compared with those based on the physical viscoplastic model of Anand, showing an overall good agreement between both approaches. However, some limitations concerning the neural network ability to predict the transient effects during a strain rate jump or a temperature change are identified and discussed.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Electronic Packaging and Soldering Technologies · High-Velocity Impact and Material Behavior · Metallurgy and Material Forming
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
LISV, Université de Versailles, Saint-Quentin-en-Yvelines, Paris Saclay, 78140 Vélizy, France
References (30)
Show source-provided references
1. Solders in Electronics10.1007/BF00687275 ↗
2. Lead-Free Solders in Microelectronics10.1016/S0927-796X(00)00010-3 ↗
3. Hwang · 2004
4. Microstructural Influences on Thermomechanical Fatigue Behaviour of Third Generation High Ag Content Pb-Free Solder Alloys10.1016/j.jallcom.2016.07.191 ↗
5. Modeling of Intergranular Thermal Fatigue Cracking of a Lead-Free Solder Joint in a Power Electronic Module10.1016/j.ijsolstr.2016.12.003 ↗
6. Microstructural Effects of Isothermal Aging on a Doped SAC Solder Alloy10.3139/146.111578 ↗
7. Constitutive Equations for Hot-Working of Metals10.1016/0749-6419(85)90004-X ↗
8. Semiatin · 1984
9. Hot Workability10.1179/095066072790137765 ↗
10. Thermo-mechanical Models of Steel Solidification Based on Two Elastic Visco-plastic Constitutive Law10.1016/j.jmatprotec.2007.06.060 ↗
11. A Neural Network Tool for Identifying the Material Parameters of a Finite Deformation Viscoplasticity Model With Static Recovery10.1016/S0045-7825(01)00278-X ↗
12. A Neural Networks Approach to Characterize Material Properties Using the Spherical Indentation Test10.1016/j.proeng.2011.04.507 ↗
13. The Use of ANN to Predict the Hot Deformation Behavior of AA7075 at Low Strain Rates10.1007/s11665-012-0332-y ↗
14. The Use of Genetic Algorithm and Neural Network to Predict Rate-Dependent Tensile Flow Behaviour of AA5182-O Sheets10.1016/j.matdes.2016.01.038 ↗
15. Numerical Implementation of a Neural Network Based Material Model in Finite Element Analysis10.1002/nme.905 ↗
16. Artificial Neural Networks and Intelligent Finite Elements in Non-linear Structural Mechanics10.1016/j.tws.2018.06.035 ↗
17. Neural Network Based Constitutive Modeling of Nonlinear Viscoplastic Structural Response10.1016/j.mechrescom.2019.01.004 ↗
18. An Efficient Monte Carlo Strategy for Elasto-plastic Structures Based on Recurrent Neural Networks10.1007/s00707-019-02436-5 ↗
19. Deep Convolutional Neural Networks in Structural Dynamics Under Consideration of Viscoplastic Material Behaviour10.1016/j.mechrescom.2020.103565 ↗
20. An Intelligent Nonlinear Meta Element for Elastoplastic Continua: Deep Learning Using a New Time-Distributed Residual U-Net Architecture10.1016/j.cma.2020.113088 ↗
21. Neural Network Constitutive Model for Rate-Dependent Materials10.1016/j.compstruc.2006.02.015 ↗
22. Constitutive Modeling of Plastic Deformation Behavior of Open-Cell Foam Structures Using Neural Networks10.1016/j.mechmat.2019.01.015 ↗
23. Artificial Neural Networks in Structural Dynamics: A New Modular Radial Basis Function Approach vs. Convolutional and Feedforward Topologies10.1016/j.cma.2020.112989 ↗
24. Viscoplastic Characterization and Post-rupture Microanalysis of a Novel Lead-Free Solder With Small Additions of Bi, Sb and Ni10.1016/j.jallcom.2016.10.025 ↗
25. Use of Artificial Neural Networks to Predict the Deformation Behavior of Zr-2.5Nb-0.5Cu10.1016/j.jmatprotec.2005.03.022 ↗
26. Application of Neural Networks to Predict the Elevated Temperature Flow Behavior of a Low Alloy Steel10.1016/j.commatsci.2008.01.039 ↗
27. Du · 2006
28. Matlab · 2018
29. Deep Learning Predicts Path-Dependent Plasticity10.1073/pnas.1911815116 ↗
30. Deep Learning for Plasticity and Thermo-viscoplasticity10.1016/j.ijplas.2020.102852 ↗