Design and development of a FOC algorithm based on machine learning for the HEPS

YiLin Li; Gao Guodong; Dai Quan Zhou; Shu Jun Wei; Jian She Cao; Xiyang Huang; Hong Zhang; JunHui Yue; Yan Feng Sui; Ying Zhao; Jun He; Dechong Zhu

doi:10.18429/jacow-ibic2025-tupco34

January 20, 2026JACOWOpen Access

Design and development of a FOC algorithm based on machine learning for the HEPS

View Full Paper

Ask AI

Bookmark

Share

Key Points

This work aims to develop a machine learning-based algorithm for the Fast Orbit Feedback system to enhance beam orbit stability at HEPS.
Developed a neural network algorithm to replace traditional PID control.
Trained the model using operational data from HEPS with hyperparameter optimization.
Set up a laboratory test environment utilizing BPM data for real-time feedback.
The neural network maintained a control error of approximately 1 mA during tests.
Demonstrated feasibility of neural networks as an alternative to PID control in FOFB systems.

Implication

Laboratory tests demonstrate a neural network algorithm effectively stabilizes beam orbit in synchrotron systems, suggesting a viable alternative to PID control.

Abstract

No abstract yet. The journal hasn't published one we can show.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Li et al. (2026) studied this question.

synapsesocial.com/papers/6971bd4c642b1836717e203b https://doi.org/10.18429/jacow-ibic2025-tupco34

View Full Paper

Ask AI

Bookmark

Share

Design and development of a FOC algorithm based on machine learning for the HEPS

Key Points

Implication

Abstract

Discussion

Cite This Study

Design and development of a FOC algorithm based on machine learning for the HEPS

Key Points

Implication

Abstract

Discussion

Cite This Study

Keep reading

Keep reading