Abstract
To improve the coordinated deformability and working stability of pure iron/aluminum (Fe/Al) laminates, pack isothermal compression experiments were conducted at deformation temperatures and strain rates ranging from 623 to 823 K and 0.01 to 10 s−1, respectively. The back-propagation neural network (BP-ANN) model was developed to predict the flow behavior of these laminates. Three-dimensional (3D) processing maps were established to optimize processing parameters by considering the deformation temperature, strain, and strain rate variables. The results indicated that the BP-ANN model is quite accurate, with a correlation coefficient (R) of 0.9979 and a mean absolute error (MAE) of 1.4681%. A peak energy dissipation efficiency of 73% was obtained in the optimized parameter range of 723–823 K and 1-10 s−1. The excellent deformation coordination between iron and aluminum layers occurred at 723 K/10 s−1. A Fe/Al interdiffusion layer of about 1 μm was formed at the interface, and the iron and aluminum layers present fine recrystallized (DRX) grains along the interface. In the rolling experiment guided by the most suitable process conditions in the hot processing map, the Fe/Al bonding was good at 723 K, and the reduction rate was 55%.
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.
