Physics-regularized neural networks for predictive modeling of silicon carbide swelling with limited experimental data

HIGHLIGHTS

• What: As the author13 pointed out, the model shows agreement with previously published swelling data for CVD SiC and CVI SiC/SiC at temperatures up to 1073 K. In contrast, above 1200 K, the models show a dose-dependent swelling trend, characteristic of the void swelling regime, where higher doses lead to greater volume expansion. This model characterizes the swelling behavior over the entire temperature spectrum, encompassing all irradiation doses.
• Who: Kazuma Kobayashi et al. from the Nuclear, and, University of have published the paper: Physics-regularized neural networks for predictive modeling of silicon carbide . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

  If you don't have an account, you can create one here.