Journal of the Korea Society for Simulation (한국시뮬레이션학회논문지)

The Korea Society for Simulation (한국시뮬레이션학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on Machine Learning of the Drivetrain Simulation Model for Development of Wind Turbine Digital Twin

풍력발전기 디지털트윈 개발을 위한 드라이브트레인 시뮬레이션 모델의 기계학습 연구

  • Received : 2023.07.20
  • Accepted : 2023.08.23
  • Published : 2023.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

As carbon-free has been getting interest, renewable energy sources have been increasing. However, renewable energy is intermittent and variable so it is difficult to predict the produced electrical energy from a renewable energy source. In this study, digital-twin concept is applied to solve difficulties in predicting electrical energy from a renewable energy source. Considering that rotation of wind turbine has high correlation with produced electrical energy, a model which simulates rotation in the drivetrain of a wind turbine is developed. The base of a drivetrain simulation model is set with well-known state equation in mechanical engineering, which simulates the rotating system. Simulation based machine learning is conducted to get unknown parameters which are not provided by manufacturer. The simulation is repeated and parameters in simulation model are corrected after each simulation by optimization algorithm. The trained simulation model is validated with 27 real wind turbine operation data set. The simulation model shows 4.41% error in average compared to real wind turbine operation data set. Finally, it is assessed that the drivetrain simulation model represents the real wind turbine drivetrain system well. It is expected that wind-energy-prediction accuracy would be improved as wind turbine digital twin including the developed drivetrain simulation model is applied.

최근 전 세계가 탄소중립에 관심이 높아지면서 재생에너지 발전량이 증가하고 있다. 하지만 재생에너지는 간헐성과 변동성이 심해 발전량 예측이 어렵고, 정확하지 않은 발전량 예측은 전력 계통에 부정적인 영향을 끼칠 수 있다. 이에 본 연구에서는 풍력발전기 발전량 예측 문제를 해결할 방법으로 디지털트윈 개념을 적용하였다. 풍력발전기의 회전이 발전량과 높은 상관관계를 갖는 부분을 반영하여 풍력발전기 드라이브트레인 회전 거동을 주로 모의하는 기계학습된 모델을 개발하였다. 회전 거동을 모의하는 드라이브트레인 시뮬레이션 모델의 기반은 잘 알려진 회전 시스템을 모의하는 시스템 상태방정식으로 설정되었다. 또한 제조사로부터 제공되지 않은 파라미터들에 대하여 시뮬레이션 기반 기계학습을 수행하였다. 기계학습된 드라이 브트레인 모델은 27개의 실제 풍력발전기 운영데이터 세트를 활용하여 검증되었다. 검증 결과, 드라이브트레인 모델은 실제 풍력발전기 운영데이터 세트와 비교하여 평균 4.41%의 오차를 보였다. 결과적으로 기계학습된 드라이브트레인 모델은 실제 풍력발전기 드라이브트레인 시스템을 잘 모사한다고 평가하였다.

Keywords

Acknowledgement

이 논문은 2023년 정부의 재원으로 과학기술정보통신부와 정보통신산업진흥원의 지원을 받아 수행된 연구임(SW고성장클럽 사업)

References

  1. Ahmed, W. K. (2013), "Mechanical Modeling of Wind Turbine Comparative Study", International Journal of Renewable Energy Research, 3, 1.
  2. Alkesaiberi, A., Harrou, F. and Sun (2022), Y., "Efficient Wind Power Prediction Using Machine Learning Methods: A Comparative Study", Energies, 2022, 15, 2327.
  3. Buturache, A. N. and Stancu, S. (2021), "Wind Energy Prediction Using Machine Learning", Low Carbon Economy, 12, 1-21. https://doi.org/10.4236/lce.2021.121001
  4. Castillo, O. C., Andrade, V. R., Rivas, J. J. R. and Gonzalez, R. O. (2023), "Comparison of Power Coefficients in Wind Turbines Considering the Tip Speed Ratio and Blade Pitch Angle", Energies, 16, 2774. https://doi.org/10.3390/en16062774
  5. Choi, J. G. and Choi, H. S. (2021), "Prediction of Wind Power Generation using Deep Learnning", Journal of the KIECS, 16(2), pp. 329-338.
  6. Gambier, A. and Behera, A. (2018), "Modelling the aerodynamic coefficients of wind turbines by using neural networks for control design purposes", The Science of Making Torque From Wind, Milano, Italy, 032032.
  7. Jung, J. A., Lee, H. W., Jeon, W. B., Kim, D. H., Kim, H. G. and Kang, Y. H. (2015), "A Study on Effect of Improvement Plan for Wind Energy Forecasting", Journal of Korean Society for Atmospheric Environment, 31(1), 1-14. https://doi.org/10.5572/KOSAE.2015.31.1.001
  8. Kim, H. G., Lee, Y. S., Jang, M. S. and Kyong, N. H. (2006), "A Study on Development of a Forecasting Model of Wind Power Generation for Walryong Site", Journal of the Korean Solar Energy Society, 26(2).
  9. Li, N., Wang, Y., Ma, W., Xiao, Z. and An, Z. (2022), "A Wind Power Prediction Method Based on DE-BP Neural Network", Frontiers in Energy Research, 10, 844111.
  10. Lynn, P. A. (2011), Onshore and Offshore Wind Energy: An Introduction, WILEY.
  11. Tahiri, M., Djebli, A. and Mimet, A. (2017), "Drivetrain Flexibility Effect on Control Performance of a Horizontal Axis Wind Turbine", International Journal of Applied Engineering Research, 12, 5511-5519.
  12. Wi, Y. M. (2015), "Short-term Wind Farm Power Forecasting Using Multivariate Analysis to Improve Wind Power Efficiency", Jorunal of the Korean Institute of Illuminating and Electrical Installation Engineers, 29(7), 54-61. https://doi.org/10.5207/JIEIE.2015.29.7.054