Speaker
Description
This study investigates the application of machine learning techniques for the phase space reconstruction of heavy ion linac beams at the Rare isotope Accelerator complex for ON-line experiments (RAON) facility in Korea. Phase space analysis is a critical component in understanding and optimizing beam dynamics, enabling precise control of beam quality for advanced nuclear physics experiments. Leveraging modern machine learning methods, including neural networks and differentiable simulations, the proposed approach seeks to reconstruct the multidimensional phase space distribution from limited and noisy measurement data. These methods utilize their ability to model nonlinear relationships and infer missing information, overcoming traditional challenges associated with high-dimensional data processing in heavy ion accelerators. The framework incorporates beam diagnostics data, such as beam profiles and time-of-flight measurements, as input to train predictive models capable of reconstructing spatial, angular, and energy distributions with high fidelity. Preliminary results suggest significant improvements in reconstruction accuracy compared to conventional techniques, along with potential for real-time implementation. This work highlights the feasibility and effectiveness of machine learning for beam diagnostics and optimization in state-of-the-art heavy ion linacs, paving the way for enhanced performance and operational efficiency at facilities like RAON.
