摘要
滚动轴承故障识别是实现视情维修的基础。针对滚动轴承出现故障时振动信号表现出的非平稳性和非线性,提出了一种基于多尺度熵(Multi-scale Entropy,MSE)和自组织特征映射(Self-organizing Feature Maps,SOM)神经网络的滚动轴承故障识别方法。该方法通过提取滚动轴承振动信号中不同故障状态下的MSE作为SOM神经网络的输入,通过SOM神经网络进行识别,得出轴承的不同故障及故障程度。通过实验表明提出的方法能有效地实现滚动轴承故障类型以及故障程度的智能识别。
Fault diagnosis of rolling bearing is the basis for real-time maintenance.Aiming at the non-stationary and nonlinear behavior of the vibration signal when the rolling bearing fault,a fault diagnosis of rolling bearing mothod named multi-scale Entropy(MSE)and Self-organizing Feature Maps(SOM)neural network is proposed.The method extracts the MSE under different fault conditions in the vibration signal of the rolling bearing as the input of the SOM neural network,and identifies it through the SOM neural network,and obtains the different types and fault degrees of the bearing.Experiments show that the proposed method can effectively realize the intelligent identification of rolling bearing fault types and fault degrees.
作者
张龙
吴佳敏
吴荣真
宋成洋
易剑昱
ZHANG Long;WU Jiamin;WU Rongzhen;SONG Chengyang;YI Jianyu(School of Mechatronies Engineering,East China Jiaotong University,Nanchang 330013,China)
出处
《机械设计与研究》
CSCD
北大核心
2019年第6期105-110,共6页
Machine Design And Research
基金
国家自然科学基金(51665013,51865010)
江西省自然科学基金(20161BAB216134,20171BAB206028)资助项目。
