基于RSSD和CNNSE-BiLSTM的滚动轴承早期故障诊断  

Early Fault Diagnosis of Rolling Bearings Based on RSSD and CNNSE-BiLSTM

作　　者：孙梦 高丙朋[1] 程静[1] SUN Meng;GAO Bingpeng;CHENG Jing(School of Electrical Engineering,Xinjiang University,Urumqi Xinjiang 830017,China)

机构地区：[1]新疆大学电气工程学院,新疆乌鲁木齐830017

出　　处：《机床与液压》2024年第16期200-206,共7页Machine Tool & Hydraulics

基　　金：国家重点研发计划项目(2021YFB1506902)。

摘　　要：针对滚动轴承早期故障具有强噪声背景且信号弱强度导致诊断精度较低的问题,提出一种基于共振稀疏分解(RSSD)的改进一维卷积和双向长短期记忆的故障诊断方法。利用3σ原则确定轴承全寿命周期的早期退化起始点,对起始点时域信号进行RSSD降噪处理,从而提高早期微弱故障的分辨率;将数据预处理后的信号输入到添加SE注意力机制的卷积神经网络(CNNSE)中提取关键局部特征,其输出输入双向长短期记忆神经网络(BiLSTM)对当前及前后时间序列信息进行特征提取;最后,通过全连接层和Softmax层进行早期多故障分类。采用所提方法针对XJTU-SY轴承全寿命周期故障信号进行实验,结果表明:所提方法对早期微弱故障信号有更高的识别率,诊断准确率99.75%,优于其他诊断方法。The early fault of rolling bearing has a strong noise background and the signal strength is weak,which leads to low diagnostic accuracy.In order to solve the problem,a fault diagnosis method based on resonance sparse signal decomposition(RSSD)was proposed,which improved 1D convolution and bidirectional long short-term memory.The 3σprinciple was used to determine the early degradation starting point of the bearing throughout its entire life cycle,and RSSD denoising was applied to the time-domain signal of the starting point to improve the resolution of early weak faults.The preprocessed signal was input into the convolutional neural network adding SE attention mechanism to extract key local features,and the feature extraction of the current and before and after time series information was performed by its output and input bidirectional long short-term memory neural network(BiLSTM).Finally,the early multi fault classification was carried out through the fully connected layer and Softmax layer.The above method was used for the entire life cycle fault signal experiment of XJTU-SY bearing.The results show that the proposed method has a higher recognition rate for early weak fault signals,with a diagnostic accuracy of 99.75%,which is superior to other diagnostic methods.

关 键 词：共振稀疏分解 卷积神经网络 注意力机制 双向长短期神经网络 早期故障诊断 

分 类 号：TH133.33[机械工程—机械制造及自动化]