Bearing Damage Detection of BLDC Motors Based on Current Envelope Analysis

Chun-Yao Lee; Yu-Hua Hsieh

doi:10.2478/v10048-012-0040-7

Abstract

This paper proposes current envelope analysis (CEA) to analyze bearing fault signals in brushless direct current (BLDC) motors, and back propagation neural networks (BPNN) to automatically identify bearing faults. We made sample motors which contained different types of fault, recorded the current signals, and extracted the current features using CEA and Hilbert Huang transform (HHT) for BPNN fault identification. The results indicate that this approach can efficiently identify bearing faults in BLDC motors.

References

[1] Altug, S., Chow, M.Y., Trussell, H.J. (1999). Fuzzy inference systems implemented on neural architectures for motor fault detection and diagnosis. IEEETransactions on Industrial Electronics, 46 (6), 1069-1079.10.1109/41.807988
Search in Google Scholar
[2] Manoharan, S.C., Veezhinathan, M., Ramakrishnan, S. (2008). Comparison of two ANN methods for classification of spirometer data. Measurement ScienceReview, 8 (3), 53-57.10.2478/v10048-008-0014-y
Search in Google Scholar
[3] Hasan, M.A., Reaz, M.B.I. (2012). Hardware prototyping of neural network based fetal electrocardiogram extraction. Measurement ScienceReview, 12 (2), 52-55.10.2478/v10048-012-0007-8
Search in Google Scholar
[4] Naik, G.R., Kumar, D.K., Arjunan, S.P. (2010). Pattern classification of Myo-Electrical signal during different Maximum Voluntary Contractions: A study using BSS techniques. Measurement Science Review, 10 (1), 1-6.10.2478/v10048-010-0001-y
Search in Google Scholar
[5] Hussain, M.S., Mamun, M. (2012). Effectiveness of the wavelet transform on the surface EMG to understand the muscle fatigue during. MeasurementScience Review, 12 (1), 28-33.10.2478/v10048-012-0005-x
Search in Google Scholar
[6] Phinyomark, A., Limsakul, C., Phukpattaranont, P. (2011). Application of wavelet analysis in EMG feature extraction for pattern classification. Measurement Science Review, 11 (2), 45-52.10.2478/v10048-011-0009-y
Search in Google Scholar
[7] Kijewski-Correa, T., Kareem, A. (2006). Efficacy of Hilbert and wavelet transforms for time-frequency analysis. Journal of Engineering Mechanics, 132 (10), 1037-1049.10.1061/(ASCE)0733-9399(2006)132:10(1037)
Search in Google Scholar
[8] Phinyomark, A., Limsakul, C., Phukpattaranont, P. (2011). On Hilbert-Huang transform approach for structural health monitoring. Journal of IntelligentMaterial Systems and Structures, 17 (8), 721-728.
Search in Google Scholar
[9] Phinyomark, A., Limsakul, C., Phukpattaranont, P. (2006). A new envelope algorithm of Hilbert-Huang transform. Mechanical Systems and Signal Processing, 20 (8), 1941-1952.
Search in Google Scholar
[10] da Silva, A.M., Povinelli, R., Demerdash, N.A.O. (2008). Induction machine broken bar and stator short circuit fault diagnostics based on three-phase stator. IEEE Transactions on Industrial Electronics, 55 (3), 1310-1318.10.1109/TIE.2007.909060
Search in Google Scholar
[11] Rivas, E., Burgos, J.C., Garcia-Prada, J.C. (2009). Condition assessment of power OLTC by vibration analysis using wavelet transform. IEEE Transactionson Power Delivery, 24 (2), 687-694.10.1109/TPWRD.2009.2014268
Search in Google Scholar
[12] Chow, M.-Y., Sharpe, R.N., Hung, J.C. (1983). On the application and design of artificial neural networks for motor fault. IEEE Transactions on IndustrialElectronics, 40 (2), 189-196.
Search in Google Scholar
[13] Tamura, S., Tateishi, M. (1997). Capabilities of a fourlayered feedforward neural network: Four layers versus three. IEEE Transactions on Neural Networks, 8 (2), 189-196.
Search in Google Scholar
[14] Huang, G.-B., Chen, L., Siew, C.-K. (2012). Universal approximation of extreme learning machine with adaptive growth of hidden nodes. IEEE Transactionson Neural Networks Learning System, 23 (2), 365-371.
Search in Google Scholar
[15] Tripathy, M., Maheshwari, R.P., Verma, H.K. (2012). Power transformer differential protection based on optimal probabilistic neural network. IEEETransactions on Power Delivery, 25 (1), 102-112.
Search in Google Scholar
[16] Perera, N., Rajapakse, A. (2012). Recognition of fault transients using a probabilistic neural-network classifier. In IEEE Power and Energy Society GeneralMeeting, 24-29 July 2011.
Search in Google Scholar
[17] Wei, W., Feng, G., Li, Z., Xu, Y. (2005). Deterministic convergence of an online gradient method for BP neural networks. IEEE Transactions onNeural Networks, 16 (3), 533-540.
Search in Google Scholar
[18] Cheng, J.S., Yu, D.J., Tang, J.S. (2008). Deterministic convergence of an online gradient method for BP neural networks. Mechanism and Machine Theory, 43 (6), 712-723.10.1016/j.mechmachtheory.2007.05.007
Search in Google Scholar
[19] Yang, R.Q., Gao, X. (2006). Hilbert-Huang transformbased vibration signal analysis for machine health monitoring. IEEE Transactions on Instrumentationand Measurement, 55 (6), 2320-2329.
Search in Google Scholar
[20] Shukla, S., Mishra, S., Singh, B. (2009). Empiricalmode decomposition with Hilbert transform for power-quality assessment. IEEE Transactions onPower Delivery, 21 (4), 2159-2165.10.1109/TPWRD.2009.2028792
Search in Google Scholar
[21] Burgsteiner, H. (2006). Training networks of biological realistic spiking neurons for real-time robot control. IEEE Transactions on Power Delivery, 19 (7), 741-752.
Search in Google Scholar
[22] Selaimia, Y., Moussaoui, A., Abbassi, H.A. (2006). Multi neural networks based approach for fault detection and diagnosis of a DC-Motor. NeuralNetwork World, 16, 369-379.
Search in Google Scholar

Bearing Damage Detection of BLDC Motors Based on Current Envelope Analysis

Abstract

Paradigm

My account