Automating Anomaly Detection for Target Systems at Spallation Neutron Source

The Spallation Neutron Source (SNS) at Oak Ridge National Laboratory produces the world's most intense pulse neutron beams. At SNS, an accelerated proton beam is directed into a mercury target to generate neutrons via spallation. The target system accounted for over 40% of the facility's overall downtime in 2022. Early detection of target system anomalies can enable taking corrective actions to avoid failures and reduce downtime. Fault prognostics and anomaly detection analyses of accelerators at SNS and at other facilities has largely focused on the beam side. This paper presents one of the first studies that explores leveraging machine learning to automate anomaly detection in the target system. The target system consists of over 30 different interconnected subsystems; the present work focuses on the mercury process system as a use case. Analyzing data from 28 process variables obtained in 2022 and 2023, tree-based and reconstruction-based algorithms were employed to detect anomalies in archived data. The algorithms detected previously unreported anomalies, several of which were deemed alert-worthy by human experts, particularly those found by reconstruction-based algorithms. Using data from each production run in the accelerator increased the generalizability of the models in time. Efforts are now underway to implement a workflow to incorporate human feedback to update the models and to evaluate performance on unseen data. The models will eventually be integrated into the existing System Tracking and Reliability system with a web interface for automated anomaly detection and reporting, along with a pathway for incorporating human feedback for model updates.