Data-Driven Bearing Fault Diagnosis of Microgrid Network Power Device Based on a Stacked Denoising Autoencoder in Deep Learning and Clustering by Fast Search without Data Labels

被引:4
作者
Xu, Fan [1 ,2 ]
Shu, Xin [3 ,4 ]
Li, Xin [5 ]
Zhang, Xiaodi [6 ]
机构
[1] China Univ Geosci, Sch Automat, Wuhan 730072, Peoples R China
[2] City Univ Hong Kong, Sch Data Sci, Kowloon, Tat Chee Ave, Hong Kong 990777, Peoples R China
[3] China Railway Major Bridge Engn Grp Co Ltd, Wuhan 730072, Peoples R China
[4] State Key Lab Hlth & Safety Bridge Struct, Wuhan 730072, Peoples R China
[5] Wuhan Univ Technol, Sch Energy & Power Engn, Wuhan 730072, Peoples R China
[6] State Grid Beijing Elect Power Co, Beijing 100080, Peoples R China
基金
中国国家自然科学基金;
关键词
EMPIRICAL MODE DECOMPOSITION; PERFORMANCE DEGRADATION ASSESSMENT; HYBRID ENERGY SYSTEM; APPROXIMATE ENTROPY; ALGORITHM; MACHINERY; OPERATION; TOOL;
D O I
10.1155/2020/5013871
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
The traditional health indicator (HI) construction method of electric equipment devices in microgrid networks, such as bearings that require different time-frequency domain indicators, needs several models to combine. Therefore, it is necessary to manually select appropriate and sensitive models, such as time-frequency domain indicators and multimodel fusion, to build HIs in multiple steps, which is more complicated because sensitivity characteristics and suitable models are more representatives of bearing degradation trends. In this paper, we use the stacked denoising autoencoder (SDAE) model in deep learning to construct HI directly from the microgrid power equipment of raw signals in bearings. With this model, the HI can be constructed without multiple model combinations or the need for manual experience in selecting the sensitive indicators. The SDAE can extract the representative degradation information adaptively from the original data through several nonlinear hidden layers automatically and approximate complicated nonlinear functions with a small reconstruction error. After the SDAE extracts the preliminary HI, a model is needed to divide the wear state of the HI constructed by the SDAE. A cluster model is commonly used for this, and unlike most clustering methods such as k-means, k-medoids, and fuzzy c-means (FCM), in which the clustering center point must be preset, cluster by fast search (CFS) can automatically find available cluster center points automatically according to the distance and local density between each point and its clustering center point. Thus, the selected cluster center points are used to divide the wear state of the bearing. The root mean square (RMS), kurtosis, Shannon entropy (SHE), approximate entropy (AE), permutation entropy (PE), and principal component analysis (PCA) are also used to construct the HI. Finally, the results show that the performance of the method (SDAE-CFS) presented is superior to other combination HI models, such as EEMD-SVD-FCM/k-means/k-medoids, stacked autoencoder-CFS (SAE-CFS), RMS, kurtosis, SHE, AE, PE, and PCA.
引用
收藏
页数:29
相关论文
共 53 条
  • [1] Permutation entropy: A natural complexity measure for time series
    Bandt, C
    Pompe, B
    [J]. PHYSICAL REVIEW LETTERS, 2002, 88 (17) : 4
  • [2] Stacking denoising auto-encoders in a deep network to segment the brainstem on MRI in brain cancer patients: A clinical study
    Dolz, Jose
    Betrouni, Nacim
    Quidet, Mathilde
    Kharroubi, Dris
    Leroy, Henri A.
    Reyns, Nicolas
    Massoptier, Laurent
    Vermandel, Maximilien
    [J]. COMPUTERIZED MEDICAL IMAGING AND GRAPHICS, 2016, 52 : 8 - 18
  • [3] Improving the robustness of spatial networks by link addition: more and dispersed links perform better
    Dong, Zhengcheng
    Tian, Meng
    Tang, Ruoli
    Li, Xin
    Lai, Jingang
    [J]. NONLINEAR DYNAMICS, 2020, 100 (03) : 2287 - 2298
  • [4] Impact of core-periphery structure on cascading failures in interdependent scale-free networks
    Dong, Zhengcheng
    Tian, Meng
    Lu, Yuxin
    Lai, Jingang
    Tang, Ruoli
    Li, Xin
    [J]. PHYSICS LETTERS A, 2019, 383 (07) : 607 - 616
  • [5] A summary of fault modelling and predictive health monitoring of rolling element bearings
    El-Thalji, Idriss
    Jantunen, Erkki
    [J]. MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2015, 60-61 : 252 - 272
  • [6] Intelligent condition-based prediction of machinery reliability
    Heng, Aiwina
    Tan, Andy C. C.
    Mathew, Joseph
    Montgomery, Neil
    Banjevic, Dragan
    Jardine, Andrew K. S.
    [J]. MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2009, 23 (05) : 1600 - 1614
  • [7] The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis
    Huang, NE
    Shen, Z
    Long, SR
    Wu, MLC
    Shih, HH
    Zheng, QN
    Yen, NC
    Tung, CC
    Liu, HH
    [J]. PROCEEDINGS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES, 1998, 454 (1971): : 903 - 995
  • [8] Rolling bearing fault diagnosis and performance degradation assessment under variable operation conditions based on nuisance attribute projection
    Huang, Wenyi
    Cheng, Junsheng
    Yang, Yu
    [J]. MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2019, 114 : 165 - 188
  • [9] Enabling Health Monitoring Approach Based on Vibration Data for Accurate Prognostics
    Javed, Kamran
    Gouriveau, Rafael
    Zerhouni, Noureddine
    Nectoux, Patrick
    [J]. IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2015, 62 (01) : 647 - 656
  • [10] Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data
    Jia, Feng
    Lei, Yaguo
    Lin, Jing
    Zhou, Xin
    Lu, Na
    [J]. MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2016, 72-73 : 303 - 315