JACoW logo

Joint Accelerator Conferences Website

The Joint Accelerator Conferences Website (JACoW) is an international collaboration that publishes the proceedings of accelerator conferences held around the world.


https://doi.org/10.18429/JACoW-ICALEPCS2017-TUCPA04
Title Model Learning Algorithms for Anomaly Detection in CERN Control Systems
Authors
  • F.M. Tilaro, B. Bradu, M. Gonzalez-Berges, F. Varela
    CERN, Geneva, Switzerland
  • M. Roshchin
    Siemens AG, Corporate Technology, München, Germany
Abstract At CERN there are over 600 different industrial control systems with millions of deployed sensors and actuators and their monitoring represents a challenging and complex task. This paper describes three different mathematical approaches that have been designed and developed to detect anomalies in CERN control systems. Specifically, one of these algorithms is purely based on expert knowledge while the other two mine historical data to create a simple model of the system, which is then used to detect anomalies. The methods presented can be categorized as dynamic unsupervised anomaly detection; "dynamic" since the behaviour of the system is changing in time, "unsupervised" because they predict faults without reference to prior events. Consistent deviations from the historical evolution can be seen as warning signs of a possible future anomaly that system experts or operators need to check. The paper also presents some results, obtained from the analysis of the LHC Cryogenic system. Finally the paper briefly describes the deployment of Spark and Hadoop into the CERN environment to deal with huge datasets and to spread the computational load of the analysis across multiple nodes.
Paper download TUCPA04.PDF [0.964 MB / 7 pages]
Slides download TUCPA04_TALK.PDF [1.965 MB]
Export download ※ BibTeX LaTeXText/WordRISEndNote
Conference ICALEPCS2017, Barcelona, Spain
Series International Conference on Accelerator and Large Experimental Control Systems (16th)
Proceedings Link to full ICALEPCS2017 Proccedings
Session Data Analytics
Date 10-Oct-17   14:00–15:30
Main Classification Data Analytics
Keywords ion, controls, cryogenics, operation, monitoring
Publisher JACoW, Geneva, Switzerland
Editors Volker RW Schaa (GSI, Darmstadt, Germany); Isidre Costa (ALBA-CELLS, Cerdanyola del Vallès, Spain); David Fernández (ALBA-CELLS, Cerdanyola del Vallès, Spain); Óscar Matilla (ALBA-CELLS, Cerdanyola del Vallès, Spain)
ISBN 978-3-95450-193-9
Published January 2018
Copyright
Copyright © 2018 by JACoW, Geneva, Switzerland     CC-BY Creative Commons License
cc Creative Commons Attribution 3.0