condition monitoring method of wind turbine gear box based on SCADA data

被引：0
|
作者：
Yin S. [1 ,2 ]
Hou G. [1 ]
Yu X. [1 ]
Wang Q. [2 ]
Gong L. [1 ]
机构：
[1] College of Control and Computer Engineering, North China Electric Power University, Beijing
[2] Zhong Neng Power-Tech Development Co., Ltd., Beijing
来源：
Taiyangneng Xuebao/Acta Energiae Solaris Sinica | 2021年 / 42卷 / 01期
关键词：
Condition monitoring; Gear box; Long short-term memory(LSTM)neural network; Principal component analysis(PCA); Random forest (RF); Wind turbine;
D O I：
10.19912/j.0254-0096.tynxb.2019-1198
中图分类号：
学科分类号：
摘要：
In order to solve the influence of long time series of fault deterioration gradual process on gear box condition monitoring model and improve its decision-making accuracy, a combined modeling method based on SCADA data is proposed in this paper. Firstly, the input observation vectors which are closely related temperature of the gear box are selected by using principal component analysis (PCA), and the temperature model of gear box under normal and abnormal conditions are established by long short-term memory(LSTM) neural network respectively. Secondly, the residual distribution eigenvectors are extracted by combining the model output with SCADA data, and the random forest residual distribution model is implemented to monitor the operation status of the gear box. Finally, the model is carried out and simulated in a large wind farm. The strong practicability and high accuracy of the LSTM neural network combined with random forest algorithm in monitoring the wind turbine gear box are demonstrated through the results, which provides a new method and idea for subsequent health evaluation of gear box. © 2021, Solar Energy Periodical Office Co., Ltd. All right reserved.
引用
收藏
页码：324 / 332
页数：8
相关论文
共 20 条
  • [1] HU Y G., Study of health condition monitoring and assessment for critical components of large wind turbine generator systems, (2017)
  • [2] LONG X F, YANG P, GUO H X, Et al., Review of fault diagnosis methods for large wind turbines, Power system technology, 41, 11, pp. 3480-3491, (2017)
  • [3] DING X, XU J, TENG W, Et al., Research status and development trend of wind turbine condition detection technology, Renewable energy resources, 35, 10, pp. 1551-1557, (2017)
  • [4] LIU S, LIU C L, ZHEN C G, Et al., Fault warning strategy of wind turbines gearbox based on group multi-dimensional similarity, Chinese journal of scientific instrument, 39, 1, pp. 180-189, (2018)
  • [5] LI T, TANG M Z, TAN X X., Fault diagnosis of wind turbine gearbox based on cost-sensitive least squares support vector machine, Renewable energy resources, 33, 2, pp. 232-237, (2015)
  • [6] INFIELD D, GUO P, INFIELD D, YANG X Y., Wind turbine gearbox condition monitoring using temperature trend analysis, Proceedings of the CSEE, 31, 32, pp. 129-136, (2011)
  • [7] CHENG J T, AI L, DUAN Z M, Et al., Application of CQPSO-BP algorithm in fault diagnosis of wind turbine gearbox, Acta energiae solaris sinica, 38, 8, pp. 2112-2116, (2017)
  • [8] WANG J H, JIA R, TAN B., Fault diagnosis of wind turbine's gearbox based on EEMD and fuzzy C-means flustering, Acta energiae solaris sinica, 36, 2, pp. 319-324, (2015)
  • [9] LECUN Y, BENGIO Y, HINTON G., Deep learning, Nature, 521, 7553, pp. 436-444, (2015)
  • [10] GRAVES A., Long short-term memory, pp. 1735-1780, (2012)
12