A fuzzy-neural multiagent system for optimisation of a roll-mill application

3 Formal Tools Multi-Agent Systems
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1415)


This article presents an industrial application of hybrid system: the development of a fuzzy-neural prototype for optimising a rollmill. The prototype has been developed following an agent-oriented methodology called MAS-CommonKADS. This prototype has the original characteristic of being agent-oriented, i.e. each learning technique has been encapsulated into an agent. This multiagent architecture for hybridisation provides flexibility for testing different hybrid configurations. Moreover, the intelligence of the agents allows them to select the best possible hybrid configuration dynamically, for some applications whereas no best configuration for all the situations has been determined.


Hybrid System Fuzzy Rule Multiagent System Rolling Force Rule Extraction 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [Ale95]
    Frederic Alexandre. Report on definition and specification of industrial applications: Steel rollmill application. Technical Report MIX/WP3/INRIA/1.0, INRIA Lorraine, March 1995.Google Scholar
  2. [ALLM96]
    F. Alexandre, A. Labbi, Y. Lallement, and M. Malek. Evaluation report on the case-based reasoning / neural networks hybrid architecture. Technical Report Deliverable D8, IMAG-INRIA, 1996.Google Scholar
  3. [GG89]
    I. Gath and A. B. Geva. Unsupervised optimal fuzzy clustering. Trans. on Pattern Analisys and Machine Intelligence, PAMI-11(7):773–781, July 1989.CrossRefGoogle Scholar
  4. [GVI95]
    José C. González, Juan R. Velasco, and Carlos A. Iglesias. A distributed platform for symbolic-connectionist interoperation. In Ron Sun and Frederic Alexandre, editors, Proceedings of the IJCAI'95 Workshop on Connectionist-Symbolic Integration: From Unified to Hybrid Approaches, pages 94–99, Montreal, Canada, August 1995. International Joint Conference on Artificial Intelligence. (An extended version of this paper has appeared in Connectionist Symbolic Integration, Lawrence Erlbaum Associates, 1996.).Google Scholar
  5. [Hil95]
    Melanie Hilario. KADS: A framework for neurosymbolic integration? Technical Report UNIGE-AI-95-04, Computer Science Department. University of Geneva, 1995.Google Scholar
  6. [HLA95]
    M. Hilario, Y. Lallement, and F. Alexandre. Neurosymbolic Integration: Unified versus Hybrid Approaches. In M. Verleysen, editor, Proceedings European Symposium on Artificial Neural Networks, Brussels (Belgium), 1995.Google Scholar
  7. [Hun93]
    C. Hung. Building a neuro-fuzzy learning control system. AI Expert, 8(11):40–49, 1993.Google Scholar
  8. [IGGV97]
    Carlos A. Iglesias, Mercedes'Garijo, José C. González, and Juan R. Velasco. Analysis and design of multiagent systems using MAS-CommonKADS. In AAAI'97 Workshop on Agent Theories, Architectures and Languages, Providence, RI, July 1997. ATAL. (An extended version of this paper will be published in INTELLIGENT AGENTS IV: Agent Theories, Architectures, and Languages, Springer Verlag, 1998,.Google Scholar
  9. [IGV96]
    Carlos A. Iglesias, José C. González, and Juan R. Velasco. Prototype of a fuzzy-neural hybrid model. evaluation report. Technical Report MIX/WP2/UPM/3.0, Dep. Ingeniería de Sistemas Telemáticos, E.T.S.I. Telecomunicación, Universidad Politécnica de Madrid, January 1996.Google Scholar
  10. [IGVE96]
    Carlos A. Iglesias, José C. González, Juan R. Velasco, and Klaus Eder. Prototype of a fuzzy-neural hybrid model. Implementation report. Technical Report MIX/WP2/UPM/2.0, Dep. Ingeniería de Sistemas Telemáticos, E.T.S.I. Telecomunicación, Universidad Politécnica de Madrid, January 1996.Google Scholar
  11. [Kos92]
    Bart Kosko. Neural Networks and Fuzzy Systems. A Dynamical Systems Approach to Machine Intelligence. Prentice-Hall, Englewood Cliffs, 1992.zbMATHGoogle Scholar
  12. [NK95]
    Detlef Nauck and Rudolf Kruse. NEFCLASS — a neuro fuzzy approach for the classification of data. In Symposium on Applied Computing during 1995 ACM Computing Week, Nashville, March 1995.Google Scholar
  13. [PA96]
    Nicolas Pican and Frédéric Alexandre. Artificial neural networks for the presetting of a steel temper mill. IEEE Expert, pages 22–27, February 1996.Google Scholar
  14. [SWV94]
    A. Th. Schreiber, B. J. Wielinga, and J. M. Akkermans W. Van de Velde. CommonKADS: A comprehensive methodology for KBS development. Deliverable DM1.2a KADS-II/M1/RR/UvA/70/1.1, University of Amsterdam, Netherlands Energy Research Foundation ECN and Free University of Brussels, 1994.Google Scholar
  15. [VdVA92]
    Walter Van de Velde and Agar Aamodt. Machine learning issues in CommonKADS. Technical report ESPRIT Project 5248 KADS-II/TII.4.3/TR/VUBS/002/3.0, Free University Brussels, January 1992.Google Scholar
  16. [VV94]
    Juan R. Velasco and F. Enrique Ventero. Some applications of fuzzy clustering to fuzzy control systems. In Proceedings of the Joint Conference on Information Sciences, pages 363–366, Pinehurst, NC, USA, November 1994.Google Scholar

Copyright information

© Springer-Verlag 1998

Authors and Affiliations

  1. 1.Dep. de TSC e Ing. Telemática, E.T.S.I. TelecomunicaciónUniversidad de ValladolidValladolidSpain
  2. 2.Dep. de Ingeniería de Sistemas Telemáticos, E.T.S.I. TelecomunicaciónUniversidad Politécnica de MadridMadridSpain

Personalised recommendations