基于联合指标的滚动轴承振动信号重构及故障诊断
Rolling bearing vibration signal reconstruction based on joint indicators and fault diagnosis
高铭悦 1蒋丽英 1张群晨 1张瀛予 1李贺1
作者信息
- 1. 沈阳航空航天大学 自动化学院,沈阳 110136
- 折叠
摘要
为了提高滚动轴承特征提取的有效性和故障识别的准确性,提出了一种基于联合指标的信号重构及基于CWT-2DCNN的故障诊断方法.首先,根据峭度和互相关系数构建出联合指标对通过集成经验模态分解(ensemble empirical mode decomposition,EEMD)得到的本征模态函数(intrinsic mode fuction,IMF)分量进行筛选与重构;其次,运用连续小波变换(con-tinue wavelet transform,CWT)变换对重构信号进行时频域特征提取;最后,以时频特征图作为输入,构建基于卷积神经网络(convolutional neural network,CNN)的故障识别模型,从而实现滚动轴承故障的智能诊断.实验结果表明,提出的信号重构及故障诊断方法故障诊断正确率达到了99.48%,且在强噪声下仍具有较高的正确识别率,说明其具有较强的泛化能力.
Abstract
In order to improve the effectiveness of feature extraction and accuracy of fault identifica-tion of rolling bearing,a signal reconstruction method based on joint indicators and a fault diagnosis method based on CWT-2DCNN were proposed.First,a joint indicator was constructed according to kurtosis and cross-correlation number to screen and reconstruct the intrinsic mode fuction(IMF)com-ponents obtained by ensemble empirical mode decomposition(EEMD).Secondly,continue wavelet transform(CWT)was used to extract the features of the reconstructed signal in time-frequency domain.Finally,a fault recognition model based on convolutional neural network(CNN)was constructed with time-frequency feature diagram as input,so as to realize the intelligent fault diagnosis of rolling bear-ing.The experimental results show that the fault diagnosis accuracy of the proposed signal reconstruc-tion and fault diagnosis method is 99.48%,and it still has a high correct recognition rate under strong noise,indicating that it has a strong generalization ability.
关键词
峭度/互相关系数/卷积神经网络/时频特征/故障诊断/信号重构/滚动轴承/联合指标Key words
kurtosis/cross-correlation number/convolutional neural network/time-frequency char-acteristics/fault diagnosis/signal reconstruction/rolling bearing/joint indicators引用本文复制引用
出版年
2024
国家科技期刊平台
NSTL
万方数据