|
|
|
| Research of Wind Turbine Main Bearing Condition Monitoring Based on Correlation PCA and ELM |
| HE Qun,WANG Hong,JIANG Guo-qian,XIE Ping,LI Ji-meng,WANG Teng-chao |
| Key Lab of Measurement Technology and Instrumentation of Hebei Province, Institute of Electrical Engineering,Yanshan University, Qinhuangdao, Hebei 066004, China |
|
|
|
|
Abstract A condition monitoring method of main bearing based on correlation coefficient method, principal component analysis and extreme learning machine are proposed. First, correlation coefficient method is used to select the initial input variables which is related to the main bearing temperature in the supervisory control and data acquistion system. Further, to eliminate the correlation and the redundancy between the selected variables, principal component analysis is applied to reduce the dimension. Again, the extreme learning machine is used to construct the normal behavior model of the main bearing temperature and predict the temperature. Last, a moving window and kernel density estimation method is used to analyze the residual, and based on the measured data to simulate main bearing fault conditions. The experimental results demonstrate that the proposed method can effectively achieve the potential failure prediction and avoid serious fault of the main bearing.
|
|
Received: 28 January 2016
Published: 29 December 2017
|
|
|
|
Corresponding Authors:
XIE Ping
E-mail: pingx@ysu.edu.cn
|
|
|
|
［1］赵文爽. 风机异常状态监测与关键参数预测方法研究［D］. 秦皇岛:燕山大学, 2015.
［2］Zaher A, McArthur S D J, Infield D G, et al. Online wind turbine fault detection through automated SCADA data analysis［J］. Wind Energy, 2009, 12(6):574-593
［3］Kim K, Parthasarathy G, Uluyol O, et al. Use of SCADA data for failure detection in wind turbines［C］//Presented at the 2011 Energy Sustainability Conference and Fuel,Cell Conference.
Washington D C, USA, 2011.
［4］Guo P, Infield D, Yang X. Wind turbine generator condition-monitoring using temperature trend analysis［J］. IEEE Transactions on Sustainable Energy, 2012, 3(1): 124-133.
［5］郭鹏, David Infield, 杨锡运. 风电机组齿轮箱温度趋势状态监测及分析方法［J］. 中国电机工程学报, 2011, 31(32): 129-136.
［6］顾煜炯, 宋磊, 徐天金, 等. 变工况条件下的风电机组齿轮箱故障预警方法［J］. 中国机械工程, 2014, 25(10) :1346-1351.
［7］董玉亮, 李亚琼, 曹海斌, 等. 基于运行工况辨识的风电机组健康状态实时评价方法［J］. 中国电机工程学报, 2013, 33(11): 123-127.
［8］郭鹏, 徐明, 白楠, 等. 基于SCADA运行数据的风电机组塔架振动建模与监测［J］. 中国电机工程学报, 2013, 33(5): 128-135.
［9］龙泉, 刘永前, 杨勇平. 基于粒子群优化BP神经网络的风电机组齿轮箱故障诊断方法［J］. 太阳能学报, 2012, 33(1):120-125.
［10］Huang G B, Zhu Q Y, Siew C K. Extreme learning machine : theory and applications［J］. Neurocomputing,2006, 70(1-3): 489-501.
［11］潘孝礼, 肖冬,常玉清,等. 基于极限学习机的软测量建模方法研究［J］. 计量学报,2009, 30(4) : 324-327.
［12］毛志忠, 唐奡, 肖冬. 基于 ELM 的非线性 PLS 软测量方法研究［J］. 计量学报, 2010, 31(4): 374-378.
［13］谢平,王一凡,江国乾,等. 基于样本熵的风力发电机早期故障检测［J］. 计量学报, 2017,38(5): 626-630.
［14］成天乐, 周胜瑜, 李斯, 等. 基于极限学习机方法的短期负荷预测［J］. 电力科学与工程, 2013, 29(4): 24-29.
［15］周松林, 茆美琴, 苏建徽. 基于主成分分析与人工神经网络的风电功率预测［J］. 电网技术, 2011, 35( 9) : 128-132. |
|
|
|
2018, Vol. 39 
