摘要
为了准确识别卧式离心泵地脚螺栓松动故障,搭建了卧式离心泵机组诊断平台,采用电涡流传感器对离心泵转子位移进行监测.将采集的转子位移信号经过经验模态分解法(empirical mode decomposition,EMD)分解为多个固有模态函数(intrinsic mode function,IMF),对各层IMF频谱特征、相关系数及能量占比进行分析得到故障敏感分量.最后,通过径向基(radial basis function,RBF)神经网络对离心泵松动故障进行识别预测.结果表明:采用EMD方法可以有效提取出离心泵松动故障特征,IMF5—IMF8层可作为故障特征分量.通过将IMF5—IMF8层的相关系数和能量占比作为故障特征输入到RBF神经网络中进行识别,准确率可达95%.
In order to accurately identify the loosening fault of the anchor bolt of horizontal centrifugal pump,a diagnostic platform of horizontal centrifugal pump unit was built,and eddy current sensor was used to monitor the rotor displacement of centrifugal pump.The acquired rotor displacement signals were decomposed into multiple intrinsic mode functions(IMF)by empirical mode decomposition(EMD),and the fault sensitive component was obtained by analyzing the IMF spectrum characteris-tics,correlation coefficient and energy ratio of each layer.Finally,the radial basis function(RBF)neural network was used to identify and predict the loosening fault of the centrifugal pump.The results show that the EMD method can effectively extract the centrifugal pump loosening fault features,and the IMF5-IMF8 layer can be used as the fault feature components.An accuracy of 95%can be reached by inputting the correlation coefficient and energy ratio of IMF5-IMF8 layers into the RBF neural network as fault features for recognition.
作者
宋礼威
张翊勋
陈泽宇
张宇航
范传翰
肖幸鑫
董亮
SONG Liwei;ZHANG Yixun;CHEN Zeyu;ZHANG Yuhang;FAN Chuanhan;XIAO Xingxin;DONG Liang(State Key Laboratory of Nuclear Power Safety Monitoring Technology and Equipment of CGN Engineering Co.,Ltd.,Shenzhen,Guangdong 518124,China;National Research Center of Pumps,Jiangsu University,Zhenjiang,Jiangsu 212013,China)
出处
《排灌机械工程学报》
CSCD
北大核心
2022年第10期993-998,共6页
Journal of Drainage and Irrigation Machinery Engineering
基金
国家自然科学基金资助项目(51879122,51779108,51779106)
镇江市重点研发计划项目(GY2017001,GY2018025)
西华大学流体及动力机械教育部重点实验室开放课题项目(szjj2015-017,szjj2017-094,szjj2016-068)
过程装备与控制工程四川省高校重点实验室开放基金资助项目(GK201614,GK201816)
江苏高校优势学科建设工程项目
江苏省“六大人才高峰”高层次人才项目(GBZB-017)。
关键词
卧式离心泵
经验模态分解
地脚螺栓
径向基神经网络
horizontal centrifugal pump
empirical mode decomposition
anchor bolt
radial basis neural network
作者简介
第一作者:宋礼威(1983-),男,河南商丘人,工程师(songliwei@cgnpc.com.cn),主要从事核电泵系统装置研究;通信作者:董亮(1981-),男,黑龙江齐齐哈尔人,研究员(dongliang@ujs.edu.cn),主要从事旋转机械优化设计研究.
