RESEARCH ON FAULT WARNING METHOD OF WIND TURBINE GEARBOX BASED ON IICEEMDAN-PCA-GRU

被引：0

作者：

Ma Y. ^{[1
]}

Feng Y. ^{[1
]}

机构：

[1] School of Control and Computer Engineering, North China Electric Power University, Baoding

来源：

Taiyangneng Xuebao/Acta Energiae Solaris Sinica | 2023年 / 44卷 / 04期

关键词：

fault warning; feature extraction; gearbox; GRU; sliding window; statistical method; wind turbines;

D O I：

10.19912/j.0254-0096.tynxb.2021-1465

中图分类号：

学科分类号：

摘要：

In order to fully mine the hidden information of SCADA data，reduce the redundancy among features，and improve the prediction and warning accuracy of the model，a fault warning method for wind turbine gearbox was proposed based on the combination of fully noise- assisted aggregation empirical mode decomposition（IICEEMDAN），principal component analysis（PCA）and gate recurrent unit（GRU）. Pearson correlation coefficient method was used for feature extraction，IICEEMDAN was used for feature decomposition to obtain the continuity signals of features in different time scales. PCA is used to extract the key factors of decomposition features as network training inputs. GRU network conducts modeling training on the input time series characteristics to predict the oil pool temperature of the gearbox. Statistical theory is used to analyze the error between the predicted value and the actual value of the oil pool temperature，and the early warning threshold is set according to the actual situation. Using sliding window theory to realize gearbox fault warning. A wind field in North China was used to verify the effectiveness of the proposed method for early fault warning of gearbox. © 2023 Science Press. All rights reserved.

引用

页码：67 / 73

页数：6

共 12 条

[1]

WANG C, LI D Z., Fault early warning of fan gearbox bearing based on LSTM network［J］, Electric power science and engineering, 36, 9, pp. 40-45, (2020)

[2]

HUANG R Z, TANG B P，, YANG Y N，, Et al., Condition monitoring of wind turbine gearbox based on LSTM neural network fusing SCADA data［J］, Acta energiae solaris sinica, 42, 1, pp. 235-239, (2021)

[3]

WEI S R，, ZHANG X, FU Y，, Et al., Early fault warning and diagnosis of offshore wind DFIG based on GRA-LSTM-Stacking model［J］, Proceedings of the CSEE, 41, 7, pp. 2373-2382, (2021)

[4]

LYU F X, BIE F F，, Et al., Application of ICEEMDAN and GS-SVM algorithm in the fault diagnosis of acoustic emission of rolling bearings［J］, Noise and vibration control, 42, 6, pp. 92-97, (2022)

[5]

CHEN D F., Research on short-term wind power prediction based on ICEEMDAN and SSA-ELM［D］, (2021)

[6]

BIE F F, DU T F，, PANG M J，, Et al., Research on fault diagnosis method of reciprocating pump based on ICEEMDAN-GRNN neural network［J］, Mechanical design and manufacturing, 3, pp. 127-131, (2021)

[7]

ZHANG Y Q, CHENG Q Z，, JIANG W J，, Et al., Photovoltaic power prediction model based on EMD- PCA LSTM［J］, Acta energiae solaris sinica, 42, 9, pp. 62-69, (2021)

[8]

LI J Q, CHEN Y T., Application of LSTM-CNN network in fault waring of inter-turn short circuit in field windings of synchronous generator［J］, Journal of North China Electric Power University（natural cience edition）, 47, 4, pp. 61-70, (2020)

[9]

ZHANG G Z, WANG Q L, YE T Z，, Et al., Intelligent detection method of high-temperature capacity reduction of wind turbine based on random forest and LSTM-autoencoder［J］, Journal of North China Electric Power University（natural science edition）, 48, 3, pp. 81-88, (2021)

[10]

QIAO F Y, MA L Y，, MA Y G., Wind turbine fault early warning method based on power curve analysis and neural network［J］, China measurement & testing, 46, 8, pp. 44-50, (2020)

← 1 2 →