Uncertainty aware anomaly detection to predict errant beam pulses in the SNS accelerator

TL;DR

This paper presents an uncertainty-aware Siamese neural network approach for predicting errant beam pulses in the SNS accelerator, aiming to prevent damage by early failure detection using single-device data.

Contribution

It introduces a novel application of Siamese neural networks with uncertainty estimation for real-time anomaly prediction in particle accelerators.

Findings

The method accurately predicts upcoming beam failures.

It enables preemptive shutdowns to prevent damage.

The approach improves operational safety and efficiency.

Abstract

High-power particle accelerators are complex machines with thousands of pieces of equipmentthat are frequently running at the cutting edge of technology. In order to improve the day-to-dayoperations and maximize the delivery of the science, new analytical techniques are being exploredfor anomaly detection, classification, and prognostications. As such, we describe the applicationof an uncertainty aware Machine Learning method, the Siamese neural network model, to predictupcoming errant beam pulses using the data from a single monitoring device. By predicting theupcoming failure, we can stop the accelerator before damage occurs. We describe the acceleratoroperation, related Machine Learning research, the prediction performance required to abort beamwhile maintaining operations, the monitoring device and its data, and the Siamese method andits results. These results show that the researched method can be applied to improve acceleratoroperations.