Bearing Feature Extraction Method Based on the Time Subsequence

Wang Dexue; Nie Fei; Zheng Zhifei; Yu Yongsheng

doi:10.16578/j.issn.1004.2539.2023.11.022

您当前的位置：

首页 >

文章列表页 >

Bearing Feature Extraction Method Based on the Time Subsequence

Development·Application | 更新时间：2023-12-01

- Bearing Feature Extraction Method Based on the Time Subsequence
- Journal of Mechanical Transmission Vol. 47, Issue 11, Pages: 146-153(2023)
- 作者机构：
  
  1.江苏省无锡交通高等职业技术学校信息管理学院，江苏无锡 214151
  2.无锡城市职业技术学院工业互联网学院，江苏无锡 214153
- 作者简介：
- 基金信息：
- DOI：10.16578/j.issn.1004.2539.2023.11.022
  CLC：
- Published：15 November 2023，
  
  Received：27 August 2022，
  
  Revised：26 September 2022，
扫描看全文
王得雪,聂飞,郑智飞等.基于时间子序列的轴承特征提取方法[J].机械传动,2023,47(11):146-153.

Wang Dexue,Nie Fei,Zheng Zhifei,et al.Bearing Feature Extraction Method Based on the Time Subsequence[J].Journal of Mechanical Transmission,2023,47(11):146-153.
王得雪,聂飞,郑智飞等.基于时间子序列的轴承特征提取方法[J].机械传动,2023,47(11):146-153. DOI： 10.16578/j.issn.1004.2539.2023.11.022.

Wang Dexue,Nie Fei,Zheng Zhifei,et al.Bearing Feature Extraction Method Based on the Time Subsequence[J].Journal of Mechanical Transmission,2023,47(11):146-153. DOI： 10.16578/j.issn.1004.2539.2023.11.022.

摘要

尽管纯粹的时域等特征有着提取速度快和物理意义明确的优点，但诊断准确性却略逊于其他方法。针对这一问题，提出了一种将词包模型和时间子序列（Based On the Time Subsequence，BOTS）相结合的轴承特征提取方法。首先，用滑动窗口在振动信号中滑动，得到多段连续的、非平稳的时间序列，并将其看作一篇篇文档。针对每一个时间序列，随机截取多个固定长度的连续子序列，求取子序列的时域或者频域特征；然后，用随机森林算法统计每一个时间序列中所有子序列的类别票数情况，基于类别票数情况构建词典；最后，将词典作为新特征，输入随机森林分类器进行训练学习，并利用西门子中国研究院无锡创新中心SQI-MFS实验平台、东南大学以及机械故障预防技术学会提供的轴承数据进行了多种实验。实验表明，BOTS+小波包能量方法提取的特征具有更高的识别度。

Abstract

Although pure time-domain features have the advantages of fast extraction speed and clear physical meaning

the diagnostic accuracy is slightly inferior to other methods. To solve this problem

a new bearing feature extraction method based on the time subsequence (BOTS) is proposed

which combines word package model and time subsequence. First

the sliding window is used to slide in the vibration signal to obtain multiple continuous and non-stationary time series

which are regarded as a document. For each time series

multiple continuous subsequences of fixed length are randomly intercepted to obtain the time-domain or frequency-domain characteristics of subsequences. Then

the random forest algorithm is used to count the class votes of all subsequences in each time series

and a dictionary is constructed based on the class votes. Finally

the dictionary is used as a new feature and input into the random forest classifier for training and learning. A variety of experiments are carried out using the bearing data provided by the SQI-MFS experimental platform of Wuxi Innovation Center of SIEMENS China Research Institute

Southeast University and Institute of Mechanical Failure Prevention Technology. The experiments show that the features extracted by BOTS+ wavelet packet energy method have higher recognition.

关键词

滚动轴承故障诊断特征提取故障状态识别

Keywords

Rolling bearingFault diagnosisFeature extractionFault status identification

references

AN D，XU B，SHAO M，et al.CEEMDAN-MFE method for fault extraction of rolling bearing［J］.Journal of Physics：Conference Series，2019，1213（5）：052092.

SU Z，TANG B，LIU Z，et al.Multi-fault diagnosis for rotating machinery based on orthogonal supervised linear local tangent space alignment and least square support vector machine［J］.Neuro Computing，2015，157（1）：208-222.

潘宏侠，张翔.基于GAMP和EEMD的滚动轴承故障诊断研究［J］.振动与冲击，2016，35（20）：190-196.

PAN Hongxia，ZHANG Xiang.Research on reolling bearing fault diagnosis based on GAMP and EEMD［J］.Journal of Vibration and Shock，2016，35（20）：190-196.

马啸，赵众，熊善海.基于Bootstrap-SVM在小样本条件下光谱定量分析研究（英文）［J］.光谱学与光谱分析，2016，36（5）：1571-1575.

MA Xiao，ZHAO Zhong，XIONG Shanhai.Spectrum quantitative analysis based on Bootstrap-SVM model with small sample set［J］.Spectroscopy and Spectral Analysis，2016，36（5）：1571-1575.

郑近德，陈敏均，程军圣，等.多尺度模糊熵及其在滚动轴承故障诊断中的应用［J］.振动工程学报，2014，27（1）：145-151.

ZHENG Jinde，CHEN Minjun，CHENG Junsheng，et al.Multiscale fuzzy entropy and its application in fault diagnosis of rolling bearing ［J］.Journal of Vibration Engineering，2014，27（1）：145-151.

郑近德，代俊习，朱小龙，等.基于改进多尺度模糊熵的滚动轴承故障诊断方法［J］.振动.测试与诊断，2018，38（5）：929-934.

ZHENG Jinde，DAI Junxi，ZHU Xiaolong，et al.Rolling bearing fault diagnosis method based on improved multi-scale fuzzy entropy［J］.Journal of Vibration，Measurement and Diagnosis，2018，38（5）：929-934.

陈俊杰，王晓峰，刘飞，等.针对滚动轴承故障诊断的新时频特征提取方法［J］.机械传动，2016，40（7）：126-131.

CHEN Junjie，WANG Xiaofeng，LIU Fei，et al.A new time-frequency feature extraction method for rolling bearing fault diagnosis［J］.Journal of Mechanical Transmission，2016，40（7）：126-131.

袁洪芳，姜宇萱，王华庆.基于词袋模型和极限学习机的轴承故障诊断［J］.测控技术，2017，36（2）：24-27.

YUAN Hongfang，JIANG Yuxuan，WANG Huaqing.Bearing fault diagnosis based on BOW and ELM［J］.Measurement and Control Technology，2017，36（2）：24-27.

卢晓勇，陈木生.基于随机森林和欠采样集成的垃圾网页检测［J］.计算机应用，2016，36（3）：731-734.

LU Xiaoyong，CHEN Musheng.Spam web page detection based on random forest and under sampling integration［J］.Journal of Computer Applications，2016，36（3）：731-734.

廖崴，郑立华，李民赞，等.基于随机森林算法的自然光照条件下绿色苹果识别［J］.农业机械学报，2017，48（S1）：86-91.

LIAO Wei，ZHENG Lihua，LI Minzan，et al.Green apple recognition under natural illumination based on random forest algorithm［J］.Transactions of the Chinese Society for Agricultural Machinery，2017，48（S1）：86-91.

BAYDOGAN M G，RUNGER G，TUV E.A bag-of-features framework to classify time series［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence，2013，35（11）：2796-2802.

张瑞强.基于离散余弦变换的时间序列分类问题研究［D］.杭州：浙江工业大学，2012：14-15.

ZHANG Ruiqiang.Research on time series classification based on discrete cosine transform［D］.Hangzhou：Zhejiang University of Technology，2012：14-15.

李世玲，李治，李合生.基于小波包能量特征的滚动轴承故障监测方法［J］.系统仿真学报，2003，15（1）：76-80.

LI Shiling，LI Zhi，LI Hesheng.Rolling bearing fault monitoring method based on wavelet packet energy characteristics［J］.Journal of System Simulation，2003，15（1）：76-80.

SHAO S，MCALEER S，YAN R，et al.Highly accurate machine fault diagnosis using deep transfer learning［J］.IEEE Transactions on Industrial Informatics，2019，15（4）：2446-2455.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Fault Feature Extraction Method of Rolling Bearings Based on Optimized VMD and UMAP

A VMD and CNN Combined Fault Diagnosis Method for Rolling Bearings

Feature Extraction of Weak Fault for Rolling Bearing based on Improved SSD Denoising

Gearbox Fault Diagnosis based on Time-frequency Combination Feature Extraction and Manifold Learning of MS-LTSA

Fault Diagnosis of Rolling Bearings based on SVD-LMD Joint De-noising and TEO

Related Author

Liu Junli

Miao Bingrong

Zhang Ying

Li Yongjian

Huang Zhong

Li Kui

Sui Xin

Liu Chunyang

Related Institution

State Key Laboratory of Traction Power, Southwest Jiaotong University

School of Rail Transportation, Wuyi University

School of Mechanical Engineering, Henan University of Science and Technology

Henan Key Laboratory for Machinery Design and Transmission System

School of Mechanical Engineering，North University of China

⁰