A Multi-agent Model with Dynamic Leadership for Fault Diagnosis in Chemical Plants

Conference paper
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 91)


Timely fault detection and diagnosis are critical matters for modern chemical plants and refineries. Traditional approaches to fault detection and diagnosis of those complex systems produce centralized models that are very difficult to maintain. In this article, we introduce a biologically inspired multi-agent model which exploits the concept of leadership; that is, when a fault is detected one agent emerges as leader and coordinates the fault classification process. The proposed model is flexible, modular, decentralized, and portable. Our experimental results show that even using simple detection and diagnosis methods, the model can achieve comparable results to those from sophisticated centralized approaches.


Multi-agent systems modeling distributed data fusion fault diagnosis collective consensus 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Chiang, L.H., Russell, E.L., Braatz, R.D.: Fault Detection and Diagnosis in Industrial Systems. Springer, London (2001)zbMATHGoogle Scholar
  2. 2.
    Crowder, J.A.: Multiple information agents for real-time ISHM: Architectures for real-time warfighter support. In: Proc. of Int. Conf. on Artificial Intelligence (2010)Google Scholar
  3. 3.
    Downs, J.J., Vogel, E.F.: A plant-wide industrial process control problem. Computers and Chemical Engineering 17(3), 245–255 (1993)CrossRefGoogle Scholar
  4. 4.
    King, A., Cowlishaw, G.: Leaders, followers and group decision-making. Communicative & Integrative Biology 2(2), 147–150 (2009)Google Scholar
  5. 5.
    Mangina, E.E., McArthur, S.D.J., McDonald, J.R.: COMMAS (COndition Monitoring Multi-Agent System). Autonomous Agents and Multi-Agent Systems 4(3), 279–282 (2001)CrossRefGoogle Scholar
  6. 6.
    Mendoza, B., Xu, P., Song, L.: A multi-agent model for fault diagnosis in petrochemical plants. In: Proc. of 2011 IEEE Sensors Applications Symposium (2011)Google Scholar
  7. 7.
    Perk, S., Teymour, F., Cinar, A.: Statistical monitoring of complex chemical processes using agent-based systems. Industrial & Engineering Chemistry Research 49(11), 5080–5093 (2010)CrossRefGoogle Scholar
  8. 8.
    Raich, A., Cinar, A.: Multivariate statistical methods for monitoring continuous processes: Assessment of discrimination power of disturbance models and diagnosis of multiple disturbances. Chemometrics and Intelligent Laboratory Systems 30, 37–48 (1995)CrossRefGoogle Scholar
  9. 9.
    Seng, N.Y., Srinivasana, R.: Multi-agent based collaborative fault detection and identification in chemical processes. Eng. Applications of Artificial Intelligence 23(6), 934–949 (2010)CrossRefGoogle Scholar
  10. 10.
    Yu, C.H., Werfel, J., Nagpal, R.: Collective decision-making in multi-agent systems by implicit leadership. In: Proc. of 9th Int. Conf. on Autonomous Agents and Multiagent Systems (2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  1. 1.ExxonMobil Research and Engineering CompanyAnnandaleUSA

Personalised recommendations