Bearing Fault Detection by One-Dimensional Convolutional Neural Networks

被引:169
作者
Eren, Levent [1 ]
机构
[1] Izmir Univ Econ, Dept Elect & Elect Engn, Sakarya Cad 156, TR-35330 Izmir, Turkey
关键词
DAMAGE DETECTION; DIAGNOSIS; DECOMPOSITION; SENSORLESS; MACHINE;
D O I
10.1155/2017/8617315
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Bearing faults are the biggest single source of motor failures. Artificial Neural Networks (ANNs) and other decision support systems are widely used for early detection of bearing faults. The typical decision support systems require feature extraction and classification as two distinct phases. Extracting fixed features each time may require a significant computational cost preventing their use in real-time applications. Furthermore, the selected features for the classification phase may not represent the most optimal choice. In this paper, the use of 1D Convolutional Neural Networks (CNNs) is proposed for a fast and accurate bearing fault detection system. The feature extraction and classification phases of the bearing fault detection are combined into a single learning body with the implementation of 1D CNN. The raw vibration data (signal) is fed into the proposed system as input eliminating the need for running a separate feature extraction algorithm each time vibration data is analyzed for classification. Implementation of 1D CNNs results in more efficient systems in terms of computational complexity. The classification performance of the proposed system with real bearing data demonstrates that the reduced computational complexity is achieved without a compromise in fault detection accuracy.
引用
收藏
页数:9
相关论文
共 38 条
[1]  
[Anonymous], 2012, STI FIELD APPL NOT R
[2]  
[Anonymous], 2011, IND AEROSPACE AUTOMO
[3]   Induction machine condition monitoring with higher order spectra [J].
Arthur, N ;
Penman, J .
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2000, 47 (05) :1031-1041
[4]   Adaptive neural fuzzy inference system for the detection of inter-turn insulation and bearing wear faults in induction motor [J].
Ballal, Makarand S. ;
Khan, Zafar J. ;
Suryawanshi, Hiralal M. ;
Sonolikar, Ram L. .
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2007, 54 (01) :250-258
[5]   Wavelet based Neuro-Detector for low frequencies of vibration signals in electric motors [J].
Bayram Kara, Duygu ;
Seker, Serhat .
APPLIED SOFT COMPUTING, 2013, 13 (05) :2683-2691
[6]   Induction motors' faults detection and localization using stator current advanced signal processing techniques [J].
Benbouzid, MEH ;
Vieira, M ;
Theys, C .
IEEE TRANSACTIONS ON POWER ELECTRONICS, 1999, 14 (01) :14-22
[7]   Early fault diagnosis of rotating machinery based on wavelet packets-Empirical mode decomposition feature extraction and neural network [J].
Bin, G. F. ;
Gao, J. J. ;
Li, X. J. ;
Dhillon, B. S. .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2012, 27 :696-711
[8]  
Chen WY, 2012, 2012 XXTH INTERNATIONAL CONFERENCE ON ELECTRICAL MACHINES (ICEM), P2390, DOI 10.1109/ICElMach.2012.6350218
[9]  
Di Stefano R., 1994, ISIE '94. 1994 IEEE International Symposium on Industrial Electronics. Symposium Proceedings (Cat. No.94TH0670-0), P220, DOI 10.1109/ISIE.1994.333115
[10]   Bearing damage detection via wavelet packet decomposition of the stator current [J].
Eren, L ;
Devaney, MJ .
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2004, 53 (02) :431-436