In recent years there has been a rapid growth in machine learning (ML) and artificial intelligence (AI) applications in accelerators. As the scale of complexity and sophistication of modern accelerators grows, the difficulties in modeling the machine increase greatly in order to include all the interacting subsystems and to consider the limitation of various diagnostics to benchmark against measurements. Tools based on ML can help substantially in revealing correlations of machine condition and beam parameters that are not easily discovered using traditional physics model-based simulations, reducing machine tuning up time etc among the many possible applications. While at APS we have many excellent tools for the optimization, diagnostics, and controls of the accelerators, we do not yet have ML-based tools established. It is our desire to test ML in our machine operation, optimization, and controls. In this paper, we introduce the application of neural networks to the APS linac bunch charge transmission efficiency.
Proceedings of the 12th International Particle Accelerator Conference, IPAC2021, Campinas, SP, Brazil