Semi-supervised Case-based Reasoning Approach to Alarm Flood Analysis

  • Marta Fullen
  • Peter Schüller
  • Oliver Niggemann
Conference paper
Part of the Technologien für die intelligente Automation book series (TIA, volume 11)


Alarm floods are a major issue in complex industrial plants. Abundance of alarms annunciated in a short period of time can exceed the operators cognitive capabilities and lead to an increased downtime or a serious plant failure. We propose a data-driven approach to detecting and analysing the alarm floods with the goal of supporting the operator during an alarm flood. The approach is based on machine learning concepts of semi-supervised learning and case-based reasoning, and requires a small amount of expert annotations on a historical alarm flood case base. It is comprised of an offline learning stage and an online detection and root cause classification stage. The proposed approach is applied and validated on a real industrial alarm dataset.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.



This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 678867.


  1. 1. K. Ahmed, I. Izadi, T. Chen, D. Joe, and T. Burton. Similarity analysis of industrial alarm flood data. In IEEE Transactions on Automation Science and Engineering, Apr 2013.Google Scholar
  2. 2. M. Ester, H.-P. Kriegel, J. Sander, and X. Xu. A density-based algorithm for discovering clusters in large spatial databases with noise. pages 226–231. AAAI Press, 1996.Google Scholar
  3. 3. M. Fullen, P. Schüller, and O. Niggemann. Defining and validating similarity measures for industrial alarm flood analysis. In IEEE 15th International Conference on Industrial Informatics (INDIN), July 2017.Google Scholar
  4. 4. Health and S. E. (HSE). The Explosion and Fires at the Texaco Refinery, Milford Haven, 24 July 1994 (Incident Report). HSE Books, 1997.Google Scholar
  5. 5. Instrumentation, Systems, and Automation Society. ANSI/ISA-18.2-2009: Management of Alarm Systems for the Process Industries, 2009.Google Scholar
  6. 6. K. S. Jones. A statistical interpretation of term specificity and its application in retrieval. Journal of Documentation, 28:11–21, 1972.CrossRefGoogle Scholar
  7. 7. O. Niggemann and V. Lohweg. On the diagnosis of cyber-physical production systems: State-of-the-art and research agenda. In Proc. AAAI, pages 4119–4126. AAAI Press, 2015.Google Scholar
  8. 8. B. Vogel-Heuser, D. Schütz, and J. Folmer. Criteria-based alarm flood pattern recognition using historical data from automated production systems (aps). Mechatronics, 31:89 – 100, 2015.CrossRefGoogle Scholar
  9. 9. J. Wang, F. Yang, T. Chen, and S. L. Shah. An overview of industrial alarm systems: Main causes for alarm overloading, research status, and open problems. IEEE Transactions on Automation Science and Engineering, 13(2):1045–1061, April 2016.CrossRefGoogle Scholar
  10. 10. X. Zhu and Z. Ghahramani. Learning from labeled and unlabeled data with label propagation. Technical report, 2002.Google Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2020

Authors and Affiliations

  • Marta Fullen
    • 1
  • Peter Schüller
    • 2
  • Oliver Niggemann
    • 1
    • 3
  1. 1.Fraunhofer Application Center Industrial AutomationLemgoGermany
  2. 2.Marmara UniversityIstanbulTurkey
  3. 3.Institute Industrial ITLemgoGermany

Personalised recommendations