Abstract
Plastic model-based neural networks are emerging phenomenological models with excellent calibration accuracy and interpretability of parameters, and they do not significantly increase the finite element calculation time of neural network models with a simple structure optimized by the algorithm. Because aluminum and magnesium have low ductility at room temperature, complex components made from these alloys need to be forged at high temperatures. In comparison with traditional thermoforming, advanced current-assisted processing provides energy savings, efficiency and green production. Experimental and constitutive modeling are carried out in this study to investigate the coupling effects of electrical pulse, temperature, strain rate, and strain on flow behavior and ductile fracture. It has been shown that electric pulses induce Joule heating effects and electroplastic effects, which reduce deformation resistance and improve formability. Electrical pulses suppress negative strain rate effects caused by dynamic strain aging, which is the main reason for the non-monotonic relationship between temperature and strain rate. The behavior of plasticity and fracture initiation can be described by simulations based on a neural network-based evolving plasticity model that incorporates stress states, current density, temperature, and strain rates.
Sign-in/Register to access full text options 
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 callMore From: IOP Conference Series: Materials Science and Engineering
Disclaimer: 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.
