Fermilab, Batavia, Illinois, USA
Northwestern University, Evanston, Illinois, USA
The Real-time Edge AI for Distributed Systems (READS) project’s goal is to create a Machine Learning (ML) system for real-time beam loss de-blending within the accelerator enclosure, which houses two accelerators: the Main Injector (MI) and the Recycler (RR). In periods of joint operation, when both machines contain high intensity beam, radiative beam losses from MI and RR overlap on the enclosure¿s beam loss monitoring (BLM) system, making it difficult to attribute those losses to a single machine. Incorrect diagnoses result in unnecessary downtime that incurs both financial and experimental cost. The ML system will automatically disentangle each machine¿s contributions to those measured losses, while not disrupting the existing operations-critical functions of the BLM system. Within this paper, the ML models, used for learning both local and global machine signatures and producing high quality inferences based on raw BLM loss measurements, will only be discussed at a high-level. This paper will focus on the evolution of the architecture, which provided the high-frequency, low-latency collection of synchronized data streams to make real-time inferences.
Performed at Northwestern with support from the Departments of Computer Science and Electrical and Computer Engineering
