DOI QR코드

DOI QR Code

Modeling of Heliostat Sun Tracking Error Using Multilayered Neural Network Trained by the Extended Kalman Filter

확장칼만필터에 의하여 학습된 다층뉴럴네트워크를 이용한 헬리오스타트 태양추적오차의 모델링

  • 이상은 (서울산업대학교 제어계측공학과) ;
  • 박영칠 (서울산업대학교 제어계측공학과)
  • Received : 2010.04.13
  • Accepted : 2010.05.20
  • Published : 2010.07.01

Abstract

Heliostat, as a concentrator reflecting the incident solar energy to the receiver located at the tower, is the most important system in the tower-type solar thermal power plant, since it determines the efficiency and performance of solar thermal plower plant. Thus, a good sun tracking ability as well as its good optical property are required. In this paper, we propose a method to compensate the heliostat sun tracking error. We first model the sun tracking error, which could be measured using BCS (Beam Characterization System), by multilayered neural network. Then the extended Kalman filter was employed to train the neural network. Finally the model is used to compensate the sun tracking errors. Simulated result shows that the method proposed in this paper improve the heliostat sun tracking performance dramatically. It also shows that the training of neural network by the extended Kalman filter provides faster convergence property, more accurate estimation and higher measurement noise rejection ability compared with the other training methods like gradient descent method.

Keywords

References

  1. PIER: California Energy Commission, Renewable Energy : Solar Two Central Receiver, Oct. 1999.
  2. Y. C. Park, "Heliostat control system," Journal of the Korean Solar Energy Society, vol. 29, no. 1, 2009.
  3. K. W. Stone and S. A. Hones, "Analysis of solar two heliostat tracking error sources," SAND99-0239C, 1999.
  4. Y. C. Park, "Analysis of sun tracking error caused by the heliostat driving axis geometrical error utilizing the solar ray tracing technique," Journal of the Korean Solar Energy Society, vol. 29, no. 2, pp. 39-46, 2009.
  5. Y. C. Park, "Analysis of sun tracking error due to the mirror installation and drive mechanism induced errors," Journal of the Korean Solar Energy Society, vol. 29, no. 3, pp. 1-1, 2009.
  6. Y. C. Park, "Compensation of sun tracking error caused by the heliostat geometrical error through the canting of heliostat mirror facets," Journal of the Korean Solar Energy Society, vol. 29, no. 6, pp. 22-31, 2009.
  7. A. Kribus, I. Vishnevetsky, A. Yogev, and T. Rubinov, "Closed loop control of heliostat," Energy 29, pp. 905-913, 2004. https://doi.org/10.1016/S0360-5442(03)00195-6
  8. John W. Strachan, "Revisiting the BCS, a Measurement System for Characterizing the Optics of Solar Collectors," Solar Thermal Test Division, Sandia National Laboratories, 1993.
  9. S. Haykin, Neural Networks: A Comprehensive Foundation, 2nd Ed., Prentice Hall, 1999.
  10. R. G. Brown and P. Hwang, Introduction to Random Signals and Applied Kalman Filtering, John Wiley & Sons, 1997
  11. Y. Iiguni, H. Sakai, and H. Tokumaru, "A real-time learning algorithm for a multilayered neural network based on the extended Kalman filter," IEEE Trans. Signal Processing, vol. 40, no. 4, pp. 959-966, 1992. https://doi.org/10.1109/78.127966