Journal of information and communication convergence engineering

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지

Performance Comparison between Neural Network and Genetic Programming Using Gas Furnace Data

  • Bae, Hyeon (School of Electrical Engineering, Pusan National University) ;
  • Jeon, Tae-Ryong (School of Electrical Engineering, Pusan National University) ;
  • Kim, Sung-Shin (School of Electrical Engineering, Pusan National University)
  • Published : 2008.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

This study describes design and development techniques of estimation models for process modeling. One case study is undertaken to design a model using standard gas furnace data. Neural networks (NN) and genetic programming (GP) are each employed to model the crucial relationships between input factors and output responses. In the case study, two models were generated by using 70% training data and evaluated by using 30% testing data for genetic programming and neural network modeling. The model performance was compared by using RMSE values, which were calculated based on the model outputs. The average RMSE for training and testing were 0.8925 (training) and 0.9951 (testing) for the NN model, and 0.707227 (training) and 0.673150 (testing) for the GP model, respectively. As concern the results, the NN model has a strong advantage in model training (using the all data for training), and the GP model appears to have an advantage in model testing (using the separated data for training and testing). The performance reproducibility of the GP model is good, so this approach appears suitable for modeling physical fabrication processes.

Keywords

References

  1. S. Mottet, "Solar cell modeling for computer-aided generator design and irradiation degradation computations," In ESA Photovoltaic Generators in Space, pp. 177-186, June 1980
  2. G. Agostinellia, D. L. Batznerb, and M. Burgelmanc, "A theoretical model for the front region of cadmium telluride solar cells," Thin Solid Films, vol. 431-432, no. 1, pp. 407-413, May 2003 https://doi.org/10.1016/S0040-6090(03)00263-3
  3. S. Michael, A. D. Bates, and M. S. Green, "Silvaco ATLAS as a solar cell modeling tool," Conference Record of the Thirty-first IEEE Photovoltaic Specialists Conference, no. 3-7, pp. 719-721, Jan. 2005
  4. J. Appelbaum, A. Chait, and D. Thompson, "Parameterization of Solar Cells," NASA STI/Recon Technical Report N, Oct. 1992
  5. D. C. Marvin, "Solar cell modeling and simulation," NASA STI/Recon Technical Report N, Feb. 1988
  6. Joseph A Jervase, Hadj Bourdoucen and Ali Al-Lawati, "Solar cell parameter extraction using genetic algorithms," Measurement Science and Technology, vol. 12, pp. 1922-1925, 2001 https://doi.org/10.1088/0957-0233/12/11/322
  7. M. AbdulHadi, A. M. Al-Ibrahim, and G. S. Virk, "Neuro-fuzzy-based solar cell model," IEEE Transaction on Energy Conversion, vol. 19, no. 3, pp. 619-624, Sept. 2004 https://doi.org/10.1109/TEC.2004.827033
  8. www.genetic-programming.org
  9. G. E. P. Box and G. M. Jenkins, Time Series Analysis: Forecasting and Control. San Francisco, Holden-Day, 1976
  10. Simon Haykin, Neural Networks. NJ: Prentice Hall, pp. 6-67, 1999
  11. Lefteri H. Tsoukalas and Robert E. Uhrig, Fuzzy and Neural Approaches in Engineering. New York: John Wiley & Sons, Inc., pp. 238-246, 1997
  12. John R. Koza, Genetic Programming: On the Programming of Computers by Means of Natural Selection. MA: The MIT Press, December 11, 1992
  13. John R. Koza, Genetic Programming II: Automatic Discovery of Reusable Programs. MA: The MIT Press, May 17, 1994
  14. John R. Koza, Forrest H. Bennett III, David Andre, and Martin A. Keane, Genetic Programming III: Darwinian Invention and Problem Solving. CA: Morgan Kaufmann, May 15, 1999
  15. D. Hammerslrom, "Working with neural networks," IEEE Spectrum, pp. 46-53, July 1993 https://doi.org/10.1109/6.222230
  16. B. Kim and G. May, "An Optimal Neural Network Process Model for Plasma Etching," IEEE Transaction on Semiconductor Manufacturing, vol. 7, pp. 12-21, Feb. 1994 https://doi.org/10.1109/66.286829
  17. Cleon Davis, Sang Jeen Hong, Ronald Setia, Rana Pratap, Terence Brown, Benjamin Ku, Greg Triplett, and Gary S. May, "An Object-Oriented Neural Network Simulator for Semiconductor Manufacturing Applications," IIIS 8th Ann. Multi-Conf. Systemics, Cybernetics Informatics 5, pp. 356-370, 2004
  18. Matthew Walker, "Introduction to Genetic Programming," Technical report, Oct. 7, 2001
  19. David E. Goldberg, Genetic Algorithms in Search, Optimization and Machine Learning, Kluwer Academic Publishers, Boston, MA, 1989
  20. Wael Farag and Ahmed Tawfik, "On Fuzzy Model Identification and the Gas Furnace Data," Proceedings of the IASTED International Conference Intelligent Systems and Control 2000, August 14-16, 2000