Speaker
Description
Crocker Nuclear Laboratory has been going through a modernization in its control system. One of the projects being made for the modernization is using machine learning to model the isochronous cyclotron environment & to use that model for autonomous control. The model uses convoluted neural networks, and uses 32 controlled parameters that all affect the beam current and stability. This model is then used in a reinforcement learning model that will be used for autonomous control, which serves as a piece on the new digital control system that is currently being implemented. The system will focus on controlling the trim coil magnets to maintain a stable beam. The goal is to unravel new/simple tunings for a continuous spectrum of energies of the machine.
| In which format do you inted to submit your paper? | LaTeX |
|---|