Advertisement

A Possibilistic Approach for Transient Identification with “Don’t Know” Response Capability Optimized by Genetic Algorithm

  • José Carlos S. de Almeida
  • Roberto Schirru
  • Cláudio M. N. A. Pereira
Chapter
Part of the Power Systems book series (POWSYS)

Abstract

This work describes a possibilistic approach for transient identification based on the minimum centroids set method, proposed in previous work, optimized by genetic algorithm. The idea behind this method is to split the complex classification problem into small and simple ones, so that the performance in the classification can be increased. In order to accomplish that, a genetic algorithm is used to learn, from realistic simulated data, the optimized time partitions, which the robustness and correctness in the classification are maximized. The use of a possibilistic classification approach propitiates natural and consistent classification rules, leading naturally to a good heuristic to handle the “don’t know” response, in case of unrecognized transient, which is fairly desirable in transient classification systems where safety is critical. Application of the proposed approach to a nuclear transient identification problem reveals good capability of the genetic algorithm in learning optimized possibilistic classification rules for efficient diagnosis including “don’t know” response. Obtained results are shown and commented.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Bartal Y, Lin J, Uhrig RE (1995) Nuclear Power Plant Transient Diagnostics Using Artificial Neural Networks that Allow “Don’t Know” Classifications, Nuclear Technology, Vol. 110, (June), pp. 346–449.Google Scholar
  2. Bartlett EB, Uhrig RE. (1992) Nuclear Power Plant Status Diagnostics Using an Artificial Neural Network, Nuclear Technology, Vol. 97, pp. 272–281.Google Scholar
  3. Goldberg DE (1989) Genetic Algorithms in Search Optimization and Machine Learning,Addison Wesley.Google Scholar
  4. Holland JH (1975) Adaptation in Natural and Artificial Systems, An Arbor,University of Michigan.Google Scholar
  5. Krishnapuram R, Keller JM (1993) A Possiilistic Approach to Clustering, IEEE Transactions on Fuzzy Systems, Vol. 1, No. 2.Google Scholar
  6. Pereira CMNA, Schirru R (2000) Designing Optimized Pattern Recognition Systems by Learning Voronoi Vectors Using Genetic Algorithms. In: Ebecken, N. F. F (ed), Data Mining II, Computational Mechanics Publications, WIT Press, England.Google Scholar
  7. Pereira CMNA, Schirm R, Martinez AS (1998) Learning an Optimized Classification System from a Data Base of Time Series Patterns Using Genetic Algorithms, In: Ebecken, N. F. F (ed), Data Mining, Computational Mechanics Publications, WIT Press, England, pp. 20–34.Google Scholar
  8. Schirm R, Pereira CMNA, Martinez AS (1999a) Genetic Algorithms Applied to Nuclear Power Plant Operation, In: Da Ruan (ed), Fuzzy Systems and Soft Computing in Nuclear Engineering, Springer-Verlag, pp. 335–350.Google Scholar
  9. Schirru R, Martinez AS, Pereira CMNA., Domingos,RP, Machado MD, Machado L (1999b) Intelligent Soft Computing in Nuclear Engineering in Brazil, Progress in Nuclear Energy, 35 (3–4), pp. 367–391.CrossRefGoogle Scholar
  10. Zadeh, LA (1978) Fuzzy Sets as a Basis for Theory of Possibility. Fuzzy Sets and Systems, Vol. 1, pp. 3–28.MathSciNetzbMATHCrossRefGoogle Scholar
  11. Zimmermann HJ, Zysno P (1985) Quantifying Vagueness in Decusion Models. European Journal of Operational Research, Vol. 22, pp. 148–158.MathSciNetzbMATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • José Carlos S. de Almeida
    • 1
  • Roberto Schirru
    • 2
  • Cláudio M. N. A. Pereira
    • 1
    • 2
  1. 1.Comissão Nacional de Energia NuclearIENRio de JaneiroBrasil
  2. 2.Universidade Federal do Rio de JaneiroPEN/COPPERio de JaneiroBrasil

Personalised recommendations