XGBoost-KDE-based main bearing temperature prediction and fault warning method for wind turbines

WAN Anping; GONG Zhipeng; ZHANG Yinlong; JI Yunsong; MA Shidong; LIU Hainan; ZHANG Yunning; AO Lizheng; CHEN Xi; PENG Chen

doi:10.19666/j.rlfd.202207179

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

XGBoost-KDE-based main bearing temperature prediction and fault warning method for wind turbines

更新时间：2025-09-28

- XGBoost-KDE-based main bearing temperature prediction and fault warning method for wind turbines
- Thermal Power Generation Vol. 51, Issue 12, Pages: 164-171(2022)
- 作者机构：
  
  1. 浙大城市学院
  2. 浙江工业大学机械工程学院
  3. 华电电力科学研究院
  4. 广东华电福新阳江海上风电有限公司
- 作者简介：
- 基金信息：
- DOI：10.19666/j.rlfd.202207179
  CLC： TM315;TP181
- Published：2022
- 稿件说明：
移动端阅览
WAN Anping, GONG Zhipeng, ZHANG Yinlong, et al. XGBoost-KDE-based main bearing temperature prediction and fault warning method for wind turbines[J]. Thermal power generation, 2022, 51(12): 164-171.
DOI：

WAN Anping, GONG Zhipeng, ZHANG Yinlong, et al. XGBoost-KDE-based main bearing temperature prediction and fault warning method for wind turbines[J]. Thermal power generation, 2022, 51(12): 164-171. DOI： 10.19666/j.rlfd.202207179.

摘要

风力发电机主轴承的故障诊断是提高其可靠性和可用性的关键。为及时发现风机主轴承故障，提出一种基于XGBoost-KDE的风机主轴承温度预测与故障预警方法。选用数据采集与监视控制（SCADA）系统中相关的特征参数作为输入变量，对风机正常工况下的主轴承温度进行预测，得到预测值和正常工作时运行数据的残差；之后运用非参数核密度估计（KDE）法确定残差预警阈值，结合滑动窗口分析法实现风机主轴承故障预警。以某2 MW等级风电机组为研究对象，采用SCADA系统中的运行数据做验证，实验结果表明，该方法可以对风机正常工况下的主轴承温度实现97.6%的精准预测，并对主轴承故障时产生的温度曲线波动做出反应，提前近1个月对风机主轴承故障进行有效预警。

Abstract

Effective early warning of main bearing failures in wind turbines is a key issue to improve their reliability and availability. In order to find out wind turbine main bearing faults in time and avoid greater loss

an XGBoostKDE-based wind turbine main shaft bearing temperature prediction and fault warning method is proposed. The relevant characteristic parameters in supervisory control and data acquisition(SCADA) system are selected as input variables to predict the main bearing temperature under normal operating conditions of the wind turbine

and the residuals between the predicted value and the operating data during normal operation are obtained. Afterward

the non-parametric kernel density estimation(KDE) method is applied to determine the residual warning threshold

and the sliding window analysis method is combined to achieve the main bearing fault warning of the wind turbine.Moreover

a 2 MW-level wind turbine is used as the research object

and the operating data in the SCADA system is read for verification. The experimental results show that

this method can predict the main bearing temperature under normal operating conditions with accuracy of 97.6%

respond to the fluctuation of the temperature curve when the main bearing fails

and give an effective warning signal to the main bearing failure of the wind turbine nearly one month in advance.

关键词

Keywords

references

Views

261

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Forecasting of photovoltaic power generation probability density based on similar day and quantile regression forests

Early warning of steam-driven induced draft fan based on data-driven and MSET

Research on development and engineering application of gas turbine performance monitoring and fault early warning system

Monitoring and fault warning of main shaft assembly runout of wind turbine

Coal mill fault warning based on multi-state estimation-analytic hierarchy process

Related Author

DING Haihua

ZHANG Jianhua

ZHANG Yijun

HE Feng

ZHANG Yanan

SUN Boyang

ZHAO Lihui

SUN Jianping

Related Institution

State Grid Zhejiang Anji County Power Supply Co., Ltd

School of Control and Computer Engineering, North China Electric Power University

Shanghai Power Generation Equipment Complete Design and Research Institute Co., Ltd

Shanghai Caojing Thermal Power Co., Ltd

Xi'an Thermal Power Research Institute Co., Ltd

AI问答

⁰