3 October 2023 in Nuclear Science and Techniques
1 February 2026 in Journal of Instrumentation
Betatron tune measurement is essential for beam control in compact proton-therapy synchrotrons, yet conventional peak-detection techniques are not robust under the low signal-to-noise ratio (SNR) conditions typical of these machines. This work presents a lightweight convolutional neural network that performs real-time tune extraction from Schottky spectra with sub-millisecond inference latency and calibrated uncertainty estimates. The model uses attention-based pooling for reliable peak localization and a dual-branch architecture that jointly predicts the tune and its associated uncertainty. Trained with a Laplace negative log-likelihood loss, it produces uncertainty estimates whose magnitude tracks the instantaneous prediction error, which enables uncertainty-aware Kalman filtering for temporal smoothing. Experiments on a large synthetic dataset spanning SNR levels from 0 to -20 dB demonstrate substantial performance gains over traditional peak-detection baselines, while the Kalman filter further suppresses transient outliers in time-series operation. Preliminary validation on operational beam data confirms stable tune tracking without retraining. With only about 2.0 × 10 4 trainable parameters and real-time inference on commodity GPU hardware, the proposed diagnostic offers a practical solution for rapid and accurate betatron tune monitoring in compact medical synchrotrons and similar accelerators.
1 June 2025 in Journal of Instrumentation
This study introduces a novel real-time betatron tune measurement algorithm, utilizing Schottky signals and an FPGA-based backend architecture, specifically designed for rapidly ramping synchrotrons, with particular application to the Shanghai Advanced Proton Therapy (SAPT) facility. The developed algorithm demonstrates improved measurement accuracy under challenging operational conditions, especially in scenarios with limited sampling time and signal-to-noise ratios (SNR) as low as -20 dB. By applying Short-Time Fourier Transform (STFT) analysis, the algorithm effectively accommodates the rapid increase in revolution frequency from 4 MHz to 7.5 MHz over 0.35 seconds, along with tune shifts. A macro-particle simulation methodology is employed to generate Schottky signals, which are then combined with real noise collected from SAPT without beam to simulate practical conditions. The proposed betatron tune measurement algorithm integrates advanced spectral processing techniques and an enhanced peak detection algorithm specifically tailored for low SNR conditions. Simulation validation confirms the superior performance of the proposed algorithm over conventional approaches in terms of measurement accuracy, stability, and system robustness, while meeting the stringent operational requirements of proton therapy applications. This innovative approach effectively addresses critical limitations associated with Schottky diagnostics for betatron tune measurement in rapidly ramping synchrotrons operating under low SNR conditions, laying a robust foundation and providing a viable solution for advanced applications in proton therapy and related accelerator physics fields.
25 February 2022 in Physica Medica