Saved in:
Bibliographic Details
Main Authors: Sulc, Antonin, Hellert, Thorsten, Hunt, Steven
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.13621
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915497992257536
author Sulc, Antonin
Hellert, Thorsten
Hunt, Steven
author_facet Sulc, Antonin
Hellert, Thorsten
Hunt, Steven
contents This paper introduces an automated fault analysis framework for the Advanced Light Source (ALS) that processes real-time event logs from its EPICS control system. By treating log entries as natural language, we transform them into contextual vector representations using semantic embedding techniques. A sequence-aware neural network, trained on normal operational data, assigns a real-time anomaly score to each event. This method flags deviations from baseline behavior, enabling operators to rapidly identify the critical event sequences that precede complex system failures.
format Preprint
id arxiv_https___arxiv_org_abs_2509_13621
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unsupervised Anomaly Detection in ALS EPICS Event Logs
Sulc, Antonin
Hellert, Thorsten
Hunt, Steven
Machine Learning
This paper introduces an automated fault analysis framework for the Advanced Light Source (ALS) that processes real-time event logs from its EPICS control system. By treating log entries as natural language, we transform them into contextual vector representations using semantic embedding techniques. A sequence-aware neural network, trained on normal operational data, assigns a real-time anomaly score to each event. This method flags deviations from baseline behavior, enabling operators to rapidly identify the critical event sequences that precede complex system failures.
title Unsupervised Anomaly Detection in ALS EPICS Event Logs
topic Machine Learning
url https://arxiv.org/abs/2509.13621