EEMD与LSTM在轴承剩余寿命预测中的应用
Application of EEMD and LSTM in Residual Life Prediction of Bearings
张丹 1袁林 2隋文涛 2金亚军2
作者信息
- 1. 山东理工大学电气与电子工程学院,山东 淄博 255000
- 2. 山东理工大学机械工程学院,山东 淄博 255000
- 折叠
摘要
剩余使用寿命(RUL)预测是实现装备健康管理与预测性维护的最主要技术手段之一,为了准确预测轴承的剩余使用寿命,提出了一种基于集合经验模态分解(EEMD)和长短时记忆网络(LSTM)的轴承剩余寿命预测方法.首先,对采集到的振动信号做时域、频域及时频分析,同时记录相应特征;进而,筛选特征,通过EEMD对振动信号予以分解并重构;最后,通过LSTM结合经过处理的信号构建健康特征指标.通过实验证明了该方法能有效的预测出轴承的剩余寿命,且有较高的预测精度.
Abstract
Residual useful life(RUL)prediction is one of the most important technical means to realize equipment health man-agement and predictive maintenance.In order to accurately predict the remaining service life of bearings,a bearing remaining life prediction method based on ensemble empirical mode decomposition(EEMD)and long short time memory network(LSTM)was proposed.First,the vibration signal is time domain,frequency domain and time frequency analysis and record correspond-ing features;second,screen selection,decomposition and reconstruction via EEMD;Finally,a health feature index is construct-ed by LSTM binding.Experiments prove that the method can effectively predict the remaining life of the bearing.
关键词
集合经验模态分解/长短时记忆网络/特征提取/寿命预测Key words
Ensemble Empirical Mode Decomposition/Long Short Term Memory Network/Feature Extraction/Li-fe Prediction引用本文复制引用
基金项目
山东省自然科学基金(ZR2016EEM20)
出版年
2024
NETL
NSTL
万方数据