A novel method for condition monitoring of wind turbine gearbox in wind farm. Issue 6 (December 2022)

• Record Type: Journal Article
• Authors: Xin, Hongwei; Wen, Xiaoqiang; Xu, Ziang; Wang, Jianguo
• Is Part Of: Wind engineering. Volume 46:Issue 6(2022)
• Page Start: 1706
• Page End: 1720
• Publication Date: 2022-12
• Subjects: Wind turbine -- long short term memory networks -- maximal information coefficient -- exponentially weighted moving-average; Wind-pressure -- Periodicals; Winds -- Periodicals; Wind power -- Periodicals; Engineering meteorology -- Periodicals; Pression du vent; Vents; Énergie éolienne; Météorologie appliquée; Engineering meteorology; Wind power; Wind-pressure; Winds; Periodicals; 621.4505
• DOI: 10.1177/0309524X221102966
• Languages: English
• ISSNs: 0309-524X

Abstract

In this paper, the gearbox of wind turbine in a wind farm is taken as research object, and its operation condition monitoring model is established by using multivariable long-short term memory networks (LSTM). Firstly, parameters with high correlation are obtained by using maximum information coefficient (MIC) as the input vectors of monitoring model. Then, the oil temperature prediction model of gearbox is constructed based on LSTM network. The residual between actual value and predicted value of gearbox oil temperature is obtained. After that, a gearbox condition monitoring model is established by using residual sequence, exponential weighted moving average (EWMA), and kernel density estimation algorithm. The case analysis shows that the proposed method can carry out fault early warning about 15.7 hours in advance. Compared with univariate LSTM condition monitoring model and SVR condition monitoring model, it can find faults more timely and can be applied to fault early warning of wind turbines in wind farm.