Wavelet energy-based visualization and classification of high-dimensional signal for bearing fault detection

被引:1
|
作者
Uk Jung
Bong-Hwan Koh
机构
[1] Dongguk University,
来源
关键词
Wavelet energy; Scalogram; Silhouette statistic ; Visualization; Vibration; Classification;
D O I
暂无
中图分类号
学科分类号
摘要
This study investigates a methodology for interpretable visualizing and classifying high-dimensional data such as vibration signals in machine fault detection application. Although principal component analysis is one of the most widely used dimension reduction methods, it does not clearly explain the source of signal variations (i.e., statistical characteristics such as mean and variance), but just locate signals on low-dimensional space which maximizing data dispersion. This deficiency restricts its interpretability to specific problems of process control and thus limits their broader usefulness. To overcome this deficiency, this study exploits the multiscale energy analysis of discrete wavelet transformation, so-called wavelet scalogram, in unsupervised manner. Wavelet scalogram allows us to first obtain a very low-dimensional feature subset of our data, which is strongly correlated with the characteristics of the data without considering the classification method used, although each of these features is uncorrelated with each other. In supervised learning scheme, it can be eventually combined with silhouette statistics for the purpose of more effective visualization of the main sources of different classes and classifying signals into different classes. Finally, nonparametric multi-class classifiers such as classification and regression tree and k-nearest neighbors quantitatively evaluate the performance of our approach for machine fault classification problem in terms of the 10-fold misclassification error rate.
引用
收藏
页码:197 / 215
页数:18
相关论文
共 50 条
  • [1] Wavelet energy-based visualization and classification of high-dimensional signal for bearing fault detection
    Jung, Uk
    Koh, Bong-Hwan
    [J]. KNOWLEDGE AND INFORMATION SYSTEMS, 2015, 44 (01) : 197 - 215
  • [2] Average Wavelet Energy-Based Method for Fault Classification in Transmission Lines
    Ju, Wenyun
    Wang, Yajun
    Del Rosso, Alberto
    [J]. 2019 IEEE POWER & ENERGY SOCIETY INNOVATIVE SMART GRID TECHNOLOGIES CONFERENCE (ISGT), 2019,
  • [3] The Study of Fault Signal Detection Based on Wavelet Energy Entropy
    Zhou, Tian-pei
    Huang, Wen-fang
    [J]. PROCEEDINGS OF 2010 INTERNATIONAL SYMPOSIUM ON IMAGE ANALYSIS AND SIGNAL PROCESSING, 2010, : 170 - 173
  • [4] Bearing Fault Classification Using Wavelet Energy and Autoencoder
    Udmale, Sandeep S.
    Singh, Sanjay Kumar
    [J]. DISTRIBUTED COMPUTING AND INTERNET TECHNOLOGY (ICDCIT 2020), 2020, 11969 : 227 - 238
  • [5] The High-Dimensional Signal Classification of Electrogastrogram for Detection of Gastric Motility Disorders
    Wang, Bin
    Wen, Tingxi
    Hou, Jigong
    Lin, Luxin
    Fang, Yan
    Du, Yu
    Pan, Ting
    [J]. JOURNAL OF MEDICAL IMAGING AND HEALTH INFORMATICS, 2020, 10 (06) : 1281 - 1287
  • [6] AutoEncoder based High-Dimensional Data Fault Detection System
    Fan, Jicong
    Wang, Wei
    Zhang, Haijun
    [J]. 2017 IEEE 15TH INTERNATIONAL CONFERENCE ON INDUSTRIAL INFORMATICS (INDIN), 2017, : 1001 - 1006
  • [7] Wavelet transform-based fault detection method for hydrogen energy-based distributed generators
    Bayrak, Gokay
    [J]. INTERNATIONAL JOURNAL OF HYDROGEN ENERGY, 2018, 43 (44) : 20293 - 20308
  • [8] A wavelet decomposition analysis of vibration signal for bearing fault detection
    Nizwan, C. K. E.
    Ong, S. A.
    Yusof, M. F. M.
    Baharom, M. Z.
    [J]. 2ND INTERNATIONAL CONFERENCE ON MECHANICAL ENGINEERING RESEARCH (ICMER 2013), 2013, 50
  • [9] Energy-based Fault Detection for an Autothermal Reformer
    Marais, Henri-Jean
    van Schoor, George
    Uren, Kenneth R.
    [J]. IFAC PAPERSONLINE, 2016, 49 (07): : 353 - 358
  • [10] Visualization Study of High-dimensional Data Classification Based on PCA-SVM
    Zhao Zhongwen
    Guo Huanghuang
    [J]. 2017 IEEE SECOND INTERNATIONAL CONFERENCE ON DATA SCIENCE IN CYBERSPACE (DSC), 2017, : 346 - 349