LIFE PREDICTION OF ROLLING BEARING BASED ON MULTI-RESOLUTION SINGULAR VALUE DECOMPOSITION AND ECNN-LSTM

XIONG Jun; CHEN Lin; WANG ShangQing

doi:10.16579/j.issn.1001.9669.2021.03.003

您当前的位置：

首页 >

文章列表页 >

LIFE PREDICTION OF ROLLING BEARING BASED ON MULTI-RESOLUTION SINGULAR VALUE DECOMPOSITION AND ECNN-LSTM

更新时间：2022-09-22

- LIFE PREDICTION OF ROLLING BEARING BASED ON MULTI-RESOLUTION SINGULAR VALUE DECOMPOSITION AND ECNN-LSTM
- Journal of Mechanical Strength Vol. 43, Issue 3, Pages: 523-530(2021)
- 作者机构：
  
  1. 泸州职业技术学院机械工程学院
  2. 西安电子科技大学通信工程学院
- 作者简介：
- 基金信息：
- DOI：10.16579/j.issn.1001.9669.2021.03.003
  CLC：
扫描看全文
XIONG Jun, CHEN Lin, WANG ShangQing. LIFE PREDICTION OF ROLLING BEARING BASED ON MULTI-RESOLUTION SINGULAR VALUE DECOMPOSITION AND ECNN-LSTM. [J]. 43(3):523-530(2021)
DOI：

XIONG Jun, CHEN Lin, WANG ShangQing. LIFE PREDICTION OF ROLLING BEARING BASED ON MULTI-RESOLUTION SINGULAR VALUE DECOMPOSITION AND ECNN-LSTM. [J]. 43(3):523-530(2021) DOI： 10.16579/j.issn.1001.9669.2021.03.003.

摘要

针对现有滚动轴承剩余寿命预测时寿命特征表征能力不足的问题,提出了多分辨奇异值分解和ECNN-LSTM的滚动轴承剩余寿命预测方法。首先,采用多分辨奇异值分解方法获取滚动轴承全寿命振动时域信号中具有不同分辨率的近似和细节信号,以多分辨展现信号不同层次的概貌和细节特征;其次,根据初时刻标准差划分健康阶段,划分出滚动轴承平稳运行阶段和能提供退化信息的快速退化阶段;然后,在两层一维卷积神经网络结构上加入高效通道注意力机制模块,在不降维的情况下自适应调整卷积核进行多通道交互,充分自提取轴承退化特征;最后,利用MSE损失函数统一评价尺度,在LSTM上完成剩余寿命预测。通过辛辛那提全寿命数据进行验证,证明了所提方法的可行性和有效性。

Abstract

In order to solve the problem of the lack of life characteristic characterization ability in the prediction of the remaining life of the rolling bearing,a method of the residual life prediction of the rolling bearing based on multi-resolution singular value decomposition and ECNN-LSTM is proposed. Firstly,the time-frequency information of vibration signals in onedimensional multi-space scale is extracted by using the multi-resolution singular value decomposition method,and the health stage is divided according to the standard deviation at the initial time. Secondly,a high-efficiency channel attention mechanism module was added to the two-layer one-dimensional convolutional neural network structure,and the convolution kernel was adaptively adjusted for multi-channel interaction without dimension reduction,so as to fully extract bearing degradation characteristics and establish effective life degradation indicators. Finally,MSE loss function is used to achieve the residual life prediction on LSTM.The feasibility and effectiveness of the proposed method are verified by Cincinnati whole life data.

关键词

滚动轴承剩余寿命预测高效通道注意力机制多分辨奇异值分解长短时记忆网络(LSTM)

Keywords

Rolling bearingRemaining life predictionEfficient channel attention mechanismMulti-resolution singular value decompositionLong and short term memory network（LSTM）

references

Views

331

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

WEAK FAULT FEATURE EXTRACTION OF ROLLING BEARING BASED ON PARAMETER OPTIMIZED MOMEDA AND CEEMDAN

CONSTRUCTION METHOD OF WAVELET BASE BASED ON GAUSSIAN FUNCTION AND ITS APPLICATION IN FAULT DIAGNOSIS OF ROLLING BEARING

LIFE PREDICTION OF ROLLING BEARING BASED ON BIDIRECTIONAL STACKING SIMPLE RECURRENT UNIT

ROLLING BEARING FAULT DIAGNOSIS BASED ON FUSION CNN AND PSO-SVM

ROLLING BEARING WEAK FAULT FEATURE EXTRACTION BASED ON MULTIPOINT OPTIMAL MINIMUM ENTROY DECONVOLUTION ADJUSTED AND ADAPTIVE STOCHASTIC RESONANCE WITH CUCKOO SEARCH

Related Author

No data

Related Institution

School of Photoelectric Information ＆ Computer Engineering,University of Shanghai for Science and Technology

College of Mechanical Engineering,North China University of Science and Technology

Beijing Key Laboratory of Performance Guarantee on Urban Rail Transit Vehicles,Beijing University of Civil Engineering Architecture

School of Machine-Electricity and Automobile Engineering,Beijing University of Civil Engineering Architecture

College of Engineering Science and Technology,Shanghai Ocean University

⁰