摘要
提出基于能量矩、EMD-SOM的智能诊断方法,首先将轴承部位原始信号EMD分解得到IMF分量,提取IMF分量的能量矩特征;将提取得到的特征作为SOM网络的输入参数进行模型训练;采用CWRU轴承振动数据进行验证,其准确率可达98%,说明了该方法可以有效地识别轴承故障,可为设备的状态监测和故障诊断提供理论依据。
For that rotor system faults often occur in the bearing,an intelligent diagnosis method based on energy moment and EMD-SOM is proposed in this paper.The original signal EMD of the bearing was decomposed to obtain the IMF component,and the energy moment characteristics of the IMF component were extracted;The feature was used as the input parameter of SOM network for fault diagnosis;CWRU bearing vibration data was used for experimental verification.The results show that its accuracy can reach 98%,which shows that the energy moment feature can extract fault information and effectively identify bearing faults,which provides a theoretical basis for equipment condition monitoring and fault diagnosis.
作者
夏孟阳
邢芷恺
陈浩
应银生
XIA Mengyang;XING Zhikai;CHEN Hao;YING Yinsheng(The No.92429 th Troop of PLA,Qingdao 266000,China;College of Power Engineering,Naval University of Engineering,Wuhan 430033,China;Jiangnan Shipbuilding Group Co.,Ltd.,Shanghai 200000,China)
出处
《兵器装备工程学报》
CSCD
北大核心
2022年第S01期342-346,共5页
Journal of Ordnance Equipment Engineering
基金
国家科技重大专项(J2019-IV-0021-0089)
湖北省自然科学基金项目(2020CFB536)。
