Artificial Intelligence for Industrial Process Supervision

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4031)


This paper presents some difficulties of complex industrial process supervision and explains why artificial intelligence may help to solve some problems. Qualitative or semi-qualitative trend extraction is mentioned first. Then fault detection and fault supervision are evoked. The necessity for intelligent interfaces is explained next and distributed supervision is finally mentioned.


Supervision Model-based Diagnosis Prognosis Trend extraction Causal Reasoning Multi-agents systems Decision Support Fuzzy Logic 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Iserman, R.: Fault Diagnosis Systems. Springer, Heidelberg (2006)Google Scholar
  2. 2.
    Gentil, S., Montmain, J.: Hierarchical representation of complex systems for supporting human decision making. Advanced Engineering Informatics 18(3), 143–159 (2004)CrossRefGoogle Scholar
  3. 3.
    de Kleer, J., Kurien, J.: Fundamentals of Model-based Diagnosis. In: IFAC Symposium Safeprocess, Washington (USA) (2003)Google Scholar
  4. 4.
    Venkatasubramanian, V.: Process Fault Detection and Diagnosis: Past, Present and Future. In: 4th Workshop On-Line Fault Detection and Supervision in the Chemical Process Industries, Seoul (Korea) (2001)Google Scholar
  5. 5.
    Charbonnier, S., Garcia-Beltran, C., Cadet, C., Gentil, S.: Trends extraction and analysis for complex system monitoring and decision support. Engineering Applications of Artificial Intelligence 18(1), 21–36 (2004)CrossRefGoogle Scholar
  6. 6.
    Evsukoff, A., Gentil, S., Montmain, J.: Fuzzy Reasoning in Co-operative Supervision Systems. Control Engineering Practice 8, 389–407 (2000)CrossRefGoogle Scholar
  7. 7.
    Montmain, J., Gentil, S.: Causal modelling for supervision. In: 14th IEEE International Symposium On Intelligent Control/Intelligent Systems and Semiotics, ISIC 1999, Cambridge (USA) (1999)Google Scholar
  8. 8.
    Montmain, J., Gentil, S.: Dynamic causal model diagnostic reasoning for on-line technical process supervision. Automatica 36, 1137–1152 (2000)CrossRefzbMATHMathSciNetGoogle Scholar
  9. 9.
    Gentil, S., Montmain, J., Combastel, C.: Combining FDI and AI Approaches within Causal-Model-based Diagnosis. IEEE Transactions SMC-Part B 34(5), 2207–2221 (2004)Google Scholar
  10. 10.
    Cordier, M.-O., Dague, P., Lévy, F., Montmain, J., Staroswiecki, M., Travé-Massuyès, L.: Conflicts versus Analytical Redundancy Relations: A comparative analysis of the model-based diagnostic approach from the artificial intelligence and automatic control perspectives. IEEE Transactions on Systems, Man and Cybernetics - Part B 34(5), 1992–2206 (2004)CrossRefGoogle Scholar
  11. 11.
    Heim, S., Gentil, S., Cauvin, L., Trave-Massuyes, B.: Braunschweig, Fault diagnosis of a chemical process using causal uncertain model. In: Workshop PAIS Prestigious Applications of Intelligent Systems, 15th European Conference on Artificial Intelligence ECAI 2002, Lyon (FR) (2002)Google Scholar
  12. 12.
    Köppen-Seliger, B., Marcu, T., Capobianco, M., Gentil, S., Albert, M., Latzel, S.: Magic: an integrated approach for diagnostic data management and operator support. In: IFAC Symposium Safeprocess 2003, Washington (USA) (2003)Google Scholar
  13. 13.
    Lesecq, S., Gentil, S., Exel, M., Garcia-Beltran, C.: Diagnostic Tools for a Multi-agent Monitoring System IMACS. In: IEEE Multi-Conference CESA 2003, Lille (Fr.) (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  1. 1.Laboratoire d’Automatique de Grenoble, UMR 5528 CNRS-INPG-UJFSaint Martin d’Hères

Personalised recommendations