DOE OSTI · 2008057
Modeling a Thermionic Electron Source Using a Physics-Informed Neural Network
Abstract
We explore the application of Physics-Informed Neural Networks (PINNs) for simulation of thermionic electron sources. This is motivated by the need for quick surrogate models used to simulate such sources within a digital twin of a complete particle accelerator. Here, a PINN was developed on a simplified model of the thermionic source: the planar diode. This model very accurately simulated the system, and performed significantly better than a traditional neural network while also using less training data. We hope to apply this proof-of-concept in motivating the development of a PINN model for a full thermionic electron source at the University of Chicago.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Ellis, Kai, Banerjee, Nilanjan, Pierce, Christopher. 2023-08-11. Modeling a Thermionic Electron Source Using a Physics-Informed Neural Network. https://doi.org/10.2172/2008057. https://engineeringpapers.com/record/osti%3A2008057/modeling-a-thermionic-electron-source-using-a-physics-informed-neural-network
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Engineering Papers by Indiciae: BibTeX · RIS.