基于BiLSTM的滚动轴承故障诊断研究

针对滚动轴承的故障诊断,设计并实现了一种基于双向长短期记忆网络(BiLSTM)的诊断模型.将原始振动信号直接作为模型输入,自动提取滚动轴承故障特征,可以对内圈、滚动体、外圈不同故障类型及不同损伤程度的滚动轴承进行故障识别.该模型通过BiLSTM神经网络自动提取轴承振动信号的深层信息,弥补了传统故障诊断方法需要人工提取特...

Rolling bearing fault diagnosis based on BiLSM network

Aiming at rolling bearing fault diagnosis,a diagnosis model based on the bidirectional long short term memory(BiLSTM)network was designed and implemented.The original vibration signal was directly used as the input of the model and rolling bearing fault features were extracted automatically to do fault recognition of rolling bearings with different fault types and damage degrees of inner race,rolling element and outer race.The deep information of bearing vibration signals was extracted with BiLSTM network to make up for the deficiency of traditional fault diagnosis methods needing to extract features manually,and thus realize the end-to-end intelligent fault diagnosis of rolling bearing.The test results of rolling bearing really measured vibration signals showed that the fault recognition correctness rate of the proposed method can reach 99.8%;the proposed method has a certain application value.