|About this Abstract
||NUMISHEET 2022: The 12th International Conference on Numerical Simulation of 3D Sheet Metal Forming Processes
||Studying the Micromechanical Behaviors of a Polycrystalline Metal by Artificial Neural Networks
||Huamiao H. Wang, Wei Dai, Dayong Li, Yinghong Peng
|On-Site Speaker (Planned)
||Huamiao H. Wang
Machine learning techniques were applied to study the micromechanical behaviors of OFHC copper under different loadings. Firstly, results from the visco-plastic self-consistent (VPSC) plasticity simulations were verified with experimental data for OFHC copper under tension and compression. Then, in order to enable the model to predict more initial textures, 912 sets of initial textures were generated and used for VPSC calculations under different loadings. Stress-strain curve, load conditions, and texture evolution results from VPSC simulations were used to train, validate and test the artificial neural network (ANN) model. The trained ANN model was applied to predict the stress-strain curves and texture evolution of OFHC copper with randomly generated initial texture and several typical textures under different loading conditions. Good predictive capabilities were obtained by the proposed ANN model for both the stress-strain curves and texture evolution responses, even beyond the strain limit of the original trained dataset.
||Definite: At-meeting proceedings