Online condition monitoring for wind turbines based on SCADA data analysis and sparse auto-encoder neural network

被引：0
|
作者：
Jin X. [1 ,2 ,3 ]
Xu Z. [2 ]
Sun Y. [1 ,3 ,4 ]
Shan J. [1 ,2 ]
机构：
[1] Key Laboratory of Special Purpose Equipment and Advanced Processing Technology, Ministry of Education and Zhejiang Province, Zhejiang University of Technology, Hangzhou
[2] College of Mechanical Engineering, Zhejiang University of Technology, Hangzhou
[3] Ninghai ZJUT Academy of Science and Technology, Ninghai
[4] Institute of Ocean Research, Zhejiang University of Technology, Hangzhou
来源：
Taiyangneng Xuebao/Acta Energiae Solaris Sinica | 2021年 / 42卷 / 06期
关键词：
Condition monitoring; Deep neural network; Sparse auto-encoder; Supervisory control and data acquisition system; Wind turbine;
D O I：
10.19912/j.0254-0096.tynxb.2019-0219
中图分类号：
学科分类号：
摘要：
An integrated approach, which is based on SCADA data analysis, sparse self-encoder and deep neural network algorithms, is proposed for wind turbines online condition monitoring. Firstly, the complex intrinsic features of SCADA high-dimensional data are learned by sparse auto-encoder, and the reduced dimension data is obtained. Secondly, deep neural network is used to predict the output power of wind turbine based on the reduced dimension data, wind turbine's condition is judged by analyzing the residuals between the predicted active power and the actual active power. Finally, SCADA data of a wind turbine for nearly one and a half years are used to verify the proposed method. Results show that the proposed approach can detect anomalies of wind turbine generator 5 days before it is shut down for maintenance which can avoid the shutdown caused by catastrophic failures, reduce the maintenance cost, and improve the competitiveness of the wind energy. © 2021, Solar Energy Periodical Office Co., Ltd. All right reserved.
引用
收藏
页码：321 / 328
页数：7
相关论文
共 22 条
  • [1] Global wind report 2017: annual market update, (2018)
  • [2] JIN X H, SUN Y, SHAN J H, Et al., Fault diagnosis and prognosis for wind turbine: an overview, Chinese journal of scientific instrument, 5, pp. 1042-1053, (2017)
  • [3] JIN X H, QIAO W, PENG Y Y, Et al., Quantitative evaluation of wind turbine faults under variable operational conditions, IEEE transactions on industry applications, 52, 3, pp. 2061-2069, (2016)
  • [4] LI D, QIU Y N, FENG Y H., Alarm fault diagnosis of wind turbine system, Acta energiae solaris sinica, 38, 11, pp. 3183-3143, (2017)
  • [5] LIANG Y, FANG R M., An online wind turbine condition assessment method based on SCADA and support vector regression, Automation of electric power systems, 37, 14, pp. 7-12, (2013)
  • [6] CHEN T, SUN W, ZHANG X., Reliablity analysis of gearbox transmission for wind turbine based on fault tree model, Acta energiae solaris sinica, 33, 10, pp. 1655-1660, (2012)
  • [7] CHEN N Y, YU R R, CHEN Y, Et al., Hierarchical method for wind turbine prognosis using SCADA data, IET renewable power generation, 4, 11, pp. 403-410, (2017)
  • [8] LECUN Y, BENGIO Y, HINTON G., Deep learning, Nature, 521, 7553, pp. 436-444, (2015)
  • [9] WANG Y, MENG W J, XIANG D, Et al., Experimental and numerical analysis of the elasto-plastic oblique contact-impact dynamics using digital Image processing method, Journal of mechanical engineering, 1, pp. 81-90, (2019)
  • [10] WANG H C, YANG Q L, YANG Y., Background segmentation and parameter detection of jatropha seeds images, Journal of drainage and irrigation machinery engineering, 36, 8, pp. 713-718, (2018)
123