Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지

An Input Feature Selection Method Applied to Fuzzy Neural Networks for Signal Estimation

  • Published : 2001.10.01
Download PDF
⟨ Previous Next ⟩

Abstract

It is well known that the performance of a fuzzy neural network strongly depends on the input features selected for its training. In its applications to sensor signal estimation, there are a large number of input variables related with an output As the number of input variables increases, the training time of fuzzy neural networks required increases exponentially. Thus, it is essential to reduce the number of inputs to a fuzzy neural network and to select the optimum number of mutually independent inputs that are able to clearly define the input-output mapping. In this work, principal component analysis (PCA), genetic algorithms (CA) and probability theory are combined to select new important input features. A proposed feature selection method is applied to the signal estimation of the steam generator water level, the hot-leg flowrate, the pressurizer water level and the pressurizer pressure sensors in pressurized water reactors and compared with other input feature selection methods.

Keywords

References

  1. Tomas Eklov, Per Martensson, and Ingemar Lundstorm, 'Selection of variable for interpreting multivariate gas sensor data,' Analytica Chimica Acta, vol. 381, pp. 221-232, (1999) https://doi.org/10.1016/S0003-2670(98)00739-9
  2. B. K. Lavine, A. Moores, and L. K. Helfend, 'A genetic algorithm for pattern recognition analysis of pyrolysis gas chromatographic data,' J. Anal. Appl. Pyrolysis, vol. 50, pp. 47-62, (1999) https://doi.org/10.1016/S0165-2370(99)00002-9
  3. K. W. Bauer Jr., S. G. Alsing, and K. A. Greene, 'Feature screening using signal-to-noise ratios,' Neurcomputing, vol. 31, pp. 29-44, (2000) https://doi.org/10.1016/S0925-2312(99)00147-2
  4. P. van de Laar and T. Keskes, 'Input selection based on an ensemble,' Neurocomputing, vol. 34, pp. 227-238, (2000) https://doi.org/10.1016/S0925-2312(00)00294-0
  5. N. R. Pal, 'Soft computing for feature analysis,' Fuzzy Sets and Systems, vol. 103, pp. 201-221, (1999) https://doi.org/10.1016/S0165-0114(98)00222-X
  6. X. Z. Wang and R. F. Li, 'Combining conceptual clustering and principal component analysis for state space based process montoring,' Ind. Eng. Chem. Res., vol. 38, no. 11, pp. 4345-4358, (1999) https://doi.org/10.1021/ie990144q
  7. Junghui Chen and Jialin Liu, 'Mixture principal component analysis models for process monitoring,' Ind. Eng. Chem. Res., vol. 38, no. 4, pp. 1478-1488, (1999) https://doi.org/10.1021/ie980577d
  8. D. E. Goldbug, Genetic Algorithms in search, Optimization, and Machine Learning,Genetic Algorithms in search, Optimization, and Machine Learning, Addison Wesley, Reading, Massachusetts, (1989)
  9. M. Mitchell, An Introduction to Genetic Algorithms,An Introduction to Genetic Algorithms, The MIT Press, Cambridge, Massachusetts, (1996)
  10. T. Takagi and M. Sugeno, 'Fuzzy indentification of systems and its applications to modeling and control,' IEEE Trans. System, Man, Cybern., vol. 1, pp. 116-132, (1985)
  11. Man Gyun Na, Neuro-fuzzy control aplications in pressurized water reactors: in Da Ruan (ed) Fuzzy Systems and Soft Computing in Unclear Engineering, Springer-Verlag, Beriln Heidelberg New York, pp.172-207, (1999)
  12. Won-Jae Lee, Bub-Dong Chung, Jea-Jun Jeong, Kwi-Seok Ha, and Moon-Kyu Hwang, Improved Features of MARS 1.4 and Verification,Improved Features of MARS 1.4 and Verification, Korea Atomic Energy Research Institute, KAERI/TR-1386-99, (1999)
  13. Michel Misiti, Yves Misiti, Georges Oppenheim, and Jean-Michel Poggi, Wavelet Toolbox User's Guide, MathWorks, Natick, MA, (1996)