DOI QR코드

DOI QR Code

Comparison of the effectiveness of various neural network models applied to wind turbine condition diagnosis

풍력터빈 상태진단에 적용된 다양한 신경망 모델의 유효성 비교

  • Manh-Tuan Ngo (Dept. of Electrical Engineering, Changwon National University) ;
  • Changhyun Kim (Institute of Mechatronics, Changwon National University) ;
  • Minh-Chau Dinh (Institute of Mechatronics, Changwon National University) ;
  • Minwon Park (Dept. of Electrical Engineering, Changwon National University)
  • Received : 2023.07.30
  • Accepted : 2023.10.10
  • Published : 2023.10.30

Abstract

Wind turbines playing a critical role in renewable energy generation, accurately assessing their operational status is crucial for maximizing energy production and minimizing downtime. This study conducts a comparative analysis of different neural network models for wind turbine condition diagnosis, evaluating their effectiveness using a dataset containing sensor measurements and historical turbine data. The study utilized supervisory control and data acquisition data, collected from 2 MW doubly-fed induction generator-based wind turbine system (Model HQ2000), for the analysis. Various neural network models such as artificial neural network, long short-term memory, and recurrent neural network were built, considering factors like activation function and hidden layers. Symmetric mean absolute percentage error were used to evaluate the performance of the models. Based on the evaluation, conclusions were drawn regarding the relative effectiveness of the neural network models for wind turbine condition diagnosis. The research results guide model selection for wind turbine condition diagnosis, contributing to improved reliability and efficiency through advanced neural network-based techniques and identifying future research directions for further advancements.

재생 에너지 생성에서 중요한 역할을 하는 풍력 터빈은 작동 상태를 정확하게 평가하는 것이 에너지 생산을 극대화하고 가동 중지 시간을 최소화하는 데 매우 중요하다. 이 연구는 풍력 터빈 상태 진단을 위한 다양한 신경망 모델의 비교 분석을 수행하고 센서 측정 및 과거 터빈 데이터가 포함된 데이터 세트를 사용하여 효율성을 평가하였다. 분석을 위해 2MW 이중 여자 유도 발전기 기반 풍력 터빈 시스템(모델 HQ2000)에서 수집된 감시 제어 및 데이터 수집 데이터를 활용했다. 활성화함수, 은닉층 등을 고려하여 인공신경망, 장단기기억, 순환신경망 등 다양한 신경망 모델을 구축하였다. 대칭 평균 절대 백분율 오류는 모델의 성능을 평가하는 데 사용되었다. 평가를 바탕으로 풍력 터빈 상태 진단을 위한 신경망 모델의 상대적 효율성에 관한 결론이 도출되었다. 본 연구결과는 풍력발전기의 상태진단을 위한 모델선정의 길잡이가 되며, 고도의 신경망 기반 기법을 통한 신뢰성 및 효율성 향상에 기여하고, 향후 관련연구의 방향을 제시하는데 기여한다.

Keywords

Acknowledgement

This research was supported by Changwon National University in 2023~2024

References

  1. A. G. Olabi, Khaled Obaideen, Mohammad Ali Abdelkareem, Maryam Nooman AlMallahi, Nabila Shehata, Abdul Hai Alami, Ayman Mdallal, Asma Ali Murah Hassan, and Enas Taha Sayed. Wind Energy Contribution to the Sustainable Development Goals: Case Study on London Array, Sustainability, 2023, 15(5), 4641 https://doi.org/10.3390/su15054641.
  2. Alberto Diez-Olivan, Javier Del Ser, Diego Galar, Basilio Sierra, "Data fusion and machine learning for industrial prognosis: Trends and perspectives towards Industry 4.0," in Information Fusion, Volume 50, October 2019, Pages 92-111. https://doi.org/10.1016/j.inffus.2018.10.005
  3. Alberto Pliego Marugan, Fausto Pedro Garcia Marquez, Jesus Maria Pinar Perez, Diego Ruiz-Hernandez, "A survey of artificial neural network in wind energy systems," in Applied Energy, Volume 228, 15 October 2018, Pages 1822-1836. https://doi.org/10.1016/j.apenergy.2018.07.084
  4. Fausto Pedro Garcia Marquez, Andrew Mark Tobias, Jesus Maria Pinar Perez, Mayorkinos Papaelias, "Condition monitoring of wind turbines: Techniques and methods," in Renewable Energy, Volume 46, October 2012, Pages 169-178. https://doi.org/10.1016/j.renene.2012.03.003
  5. Johan Ribrant, Reliability performance and maintenance - A survey of failures in wind power systems, Master Thesis, Graduate KTH School of Electrical Engineering, Stockholm, Sweden, 2006.
  6. John J. Hopfield, "Artificial Neural Networks," in IEEE Circuits and Devices Magazine, Volume: 4, Issue: 5, September 1988.
  7. Lu Wei, Zheng Qian, Hamidreza Zareipour, "Wind Turbine Pitch System Condition Monitoring and Fault Detection Based on Optimized Relevance Vector Machine Regression," in IEEE Transactions on Sustainable Energy, Volume: 11, Issue: 4, October 2020.
  8. M. Fast, T. Palme, "Application of artificial neural networks to the condition monitoring and diagnosis of a combined heat and power plant," in Energy, Volume 35, Issue 2, February 2010, Pages 1114-1120. https://doi.org/10.1016/j.energy.2009.06.005
  9. Roeland De Geest, Tinne Tuytelaars, "Modeling Temporal Structure with LSTM for Online Action Detection," in 2018 IEEE Winter Conference on Applications of Computer Vision (WACV).
  10. Zhengru Ren, Amrit Shankar Verma, Ye Li, Julie J.E. Teuwen, Zhiyu Jiang, "Offshore wind turbine operations and maintenance: A state-of-the-art review," in Renewable and Sustainable Energy Reviews, Volume 144, July 2021, 110886.