Motor Fault Prediction Based on Fault Feature Extraction and Signal Distribution Optimization

被引:0
|
作者
Qu, Yinpeng [1 ]
Wang, Xiwei [2 ]
Zhang, Xiaofei [1 ]
Qin, Guojun [1 ]
机构
[1] Hunan Univ, Coll Elect & Informat Engn, Changsha 410082, Peoples R China
[2] Co State Grid Zhejiang Elect Power Co Ltd, Shaoxing Power Supply, Shaoxing 310013, Peoples R China
关键词
Circuit faults; Feature extraction; Predictive models; Time series analysis; Mathematical models; Degradation; Time-frequency analysis; Fault prediction; feature extraction; gated recurrent unit (GRU); signal distribution optimization; time-frequency characteristics; USEFUL LIFE PREDICTION; HIDDEN MARKOV MODEL; MACHINE; NETWORK;
D O I
10.1109/TIM.2023.3318708
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
The fault prediction of motors can effectively reduce the occurrence of accidents and change the post diagnosis to prevention. However, the systematic errors caused by the complex signal components, such as different kinds of randomly distributed noise, make the false report or misreport inevitable, no matter what prediction model is selected. To tackle this issue, a motor fault prediction method based on fault feature extraction and signal distribution optimization is proposed in this article. A time-frequency parameter and resolution adaptive algorithm (TF-PRAA) is proposed to optimize the raw signal while reserving the fault characteristics. An extended model is developed to decompose and reconstruct the processed signals. Then, the optimized time series is transformed into the signal distribution. Fault prediction is carried out by combining the signal distributions as the inputs of the gated recurrent unit (GRU). Two datasets collected from experiments and National Aeronautics and Space Administration (NASA) are used to validate the effectiveness of the proposed methods. The test results indicate that the proposed methods provide better performance than other state-of-the-art models since the unrelated components of the signal are accurately reduced and the concentration of the signal is improved. From the predictive theory point of view, achieving accurate prediction of such signals is much easier. The method can accurately fulfill both long- and short-term fault prediction tasks.
引用
收藏
页数:14
相关论文
共 50 条
  • [41] Research of Fault Feature Extraction and Analysis Method Based on Aeroengine Fault Data
    Yu, Yahan
    Wang, Yun
    Zhang, Guigang
    Wang, Jian
    2020 CHINESE AUTOMATION CONGRESS (CAC 2020), 2020, : 2960 - 2965
  • [42] Nonlinear feature extraction in modeling of quality prediction and fault diagnosis
    Zhao, Jian-Zhe
    Wang, Da-Ke
    Li, Kai
    Zhu, Zhi-Liang
    Dongbei Daxue Xuebao/Journal of Northeastern University, 2012, 33 (06): : 793 - 796
  • [43] Weibull Distribution Parameters for Fault Feature Extraction of Rolling Bearing
    Peng Tao
    Jiang Haiyan
    Xie Yong
    2011 CHINESE CONTROL AND DECISION CONFERENCE, VOLS 1-6, 2011, : 69 - +
  • [44] Statistical Feature Extraction for Fault Locations in Nonintrusive Fault Detection of Low Voltage Distribution Systems
    Chang, Hsueh-Hsien
    Linh, Nguyen Viet
    ENERGIES, 2017, 10 (05):
  • [45] Probabilistic Diagnosis of Short Circuit Fault in Stator Winding of Motor Based on Feature Distribution
    Fukui, Hiroyuki
    Mizuno, Yukio
    Nakamura, Hisahide
    CONFERENCE RECORD OF THE 2010 IEEE INTERNATIONAL SYMPOSIUM ON ELECTRICAL INSULATION (ISEI), 2010,
  • [46] Comparative Study of Induction Motor Fault Analysis Using Feature Extraction
    Thakur, Arunava Kabiraj
    Kundu, Palash Kumar
    Das, Arabinda
    2017 IEEE CALCUTTA CONFERENCE (CALCON), 2017, : 150 - 154
  • [47] Development of Feature Extraction and Classification for Bearing Fault Analysis of Induction Motor
    Patel, Raj Kumar
    Giri, V. K.
    2018 5TH IEEE UTTAR PRADESH SECTION INTERNATIONAL CONFERENCE ON ELECTRICAL, ELECTRONICS AND COMPUTER ENGINEERING (UPCON), 2018, : 928 - 934
  • [48] Kurtosis filter in feature extraction for incipient motor bearing fault diagnosis
    Liang, Y.-C., 1600, Editorial Department of Electric Machines and Control (18):
  • [49] A Fault Feature Extraction Method of Motor Bearing Using Improved LCD
    Ding, Feng
    Zhang, Xinrui
    Wu, Wenfeng
    Wang, Yihua
    IEEE ACCESS, 2020, 8 : 220973 - 220979
  • [50] Application of hybrid interpolated ESMD in motor bearing fault feature extraction
    Su W.
    Zhang S.
    Liu T.
    Jing C.
    Zhendong yu Chongji/Journal of Vibration and Shock, 2020, 39 (04): : 266 - 272