首页 | 本学科首页   官方微博 | 高级检索  
     

基于深度信念网络的风机主轴承状态监测方法
引用本文:王洪斌,王红,何群,王跃灵,周振. 基于深度信念网络的风机主轴承状态监测方法[J]. 中国机械工程, 2018, 29(8): 948
作者姓名:王洪斌  王红  何群  王跃灵  周振
作者单位:1.燕山大学工业计算机控制工程河北省重点实验室,秦皇岛,0660042.燕山大学河北省测试计量技术及仪器重点实验室,秦皇岛,066004
基金项目:国家自然科学基金资助项目(61473248);河北省自然科学基金资助项目(F2016203496)National Natural Science Foundation of China(No. 61473248)Hebei Provincial Natural Science Foundation of China(No. F2016203496)
摘    要:提出了一种基于深度信念网络(DBN)的风电机组主轴承状态监测方法。为了降低建模难度并减少训练时间,首先利用相关系数法选取建模变量,进而建立主轴承正常行为的DBN温度模型并用于主轴承温度预测。该模型克服了传统神经网络随机初始化网络权重、易陷入局部最小值等缺点,能有效提高主轴承温度的预测精度。然后采用指数加权移动平均法(EWMA)对主轴承温度残差序列进行分析,并利用核密度估计方法确定故障阈值。最后基于实测的数据采集与监视控制(SCADA)系统数据对主轴承故障进行模拟。结果表明,与传统预测方法相比,该方法能有效地实现主轴承的异常状态监测。

关 键 词:数据采集与监视控制  深度信念网络  温度建模  状态监测  

Condition Monitoring Method for Wind Turbine Main Bearings Based on DBN
WANG Hongbin,WANG Hong,HE Qun,WANG Yueling,ZHOU Zhen. Condition Monitoring Method for Wind Turbine Main Bearings Based on DBN[J]. China Mechanical Engineering, 2018, 29(8): 948
Authors:WANG Hongbin  WANG Hong  HE Qun  WANG Yueling  ZHOU Zhen
Affiliation:1.Key Lab of Industrial Computer Control Engineering of Hebei Province,Yanshan University,Qinhuangdao,Hebei,0660042.Key Lab of Measurement Technology and Instrumentation of Hebei Province,Yanshan University,Qinhuangdao,Hebei,066004
Abstract:A condition monitoring method of wind turbine main bearings was proposed based on DBN. To reduce the modeling difficulties and decrease the training time, a correlation coefficient method was firstly applied to select the modeling variables. Further, a DBN temperature model of the normal behaviors of the main bearings was established and the main bearing temperature was predicted. This model overcomes the shortcomings of traditional neural network that randomly initializes the network weights and easily to fall into the local minimum thus may effectively improve the prediction accuracy of main bearing temperature. Then exponentially weighted moving average was used to analyze the residual errors of main bearing temperature and the failure threshold was determined by kernel density estimation method. Lastly, the main bearing failure was simulated based on the measured SCADA data. The experimental results show that the proposed method may effectively realize the abnormal condition monitoring of the main bearings than that of the traditional prediction methods.
Keywords:supervisory control and data acquisition(SCADA)  deep belief network(DBN);temperature modeling  condition monitoring  
本文献已被 CNKI 等数据库收录!
点击此处可从《中国机械工程》浏览原始摘要信息
点击此处可从《中国机械工程》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号