Detection of Gearbox lubrication Using PSO-Based WKNN

Lee, Chun-Yao; Kuo, Cheng-Chien; Liu, Ryan; Tseng, I-Hsiang; Chang, Lu-Chen

doi:10.2478/msr-2013-0019

Abstract

This paper proposes an optimization classification model, which combines particle swarm optimization (PSO) with weighted knearest neighbors (WKNN), namely PWKNN. The model optimizes the weight and k parameter of WKNN to improve the detection accuracy of gearbox lubrication levels. In the experiment, the current signals of the generator are measured, and the relative frequency spectrum of the measured signals is illustrated by using fast Fourier transform (FFT). The features from the spectrum are extracted, and then the optimal weight and k parameter of WKNN are obtained by using PSO. The average detection accuracy of gearbox lubrication levels is 96% by using PWKNN, which the result shows that the proposed PWKNN can efficiently detect the lubrication level of gearboxes. The experiment also shows that the performance of the proposed PWKNN by using the current signals of the generator is superior to that by using typical vibration signals of a gearbox. In addition, the accuracy can reach 95.4% even in environments with 20 dB noise interference.

References

[1] Randall, R.B. (2011). Vibration-based ConditionMonitoring: Industrial, Aerospace and AutomotiveApplications. Wiley.
Search in Google Scholar
[2] He, P., Li, Q., Kong, F. (2010). A new method of feature extraction for gearbox vibration signals. In Image and Signal Processing (CISP) : 3rdInternational Congress, 16-18 October 2010. IEEE, Vol. 8, 3980-3984.
Search in Google Scholar
[3] Yang, Z., Hoi, W.I., Zhong, J. (2011). Gearbox fault diagnosis based on artificial neural network and genetic algorithms. In International Conference onSystem Science and Engineering (ICSSE), 8-10 June 2011. IEEE, 37-42.10.1109/ICSSE.2011.5961870
Search in Google Scholar
[4] Yang, S., Li, W., Wang, C. (2008). The intelligent fault diagnosis of wind turbine gearbox based on artificial neural network. In International Conferenceon Condition Monitoring and Diagnosis (CMD 2008), 21-24 April 2008. IEEE, 1327-1330.10.1109/CMD.2008.4580221
Search in Google Scholar
[5] Mohanty, R., Kar, C., (2006). Fault detection in a multistage gearbox by demodulation of motor current waveform. IEEE Transactions on IndustrialElectronics, 53 (4), 1285-1297.10.1109/TIE.2006.878303
Search in Google Scholar
[6] Rajagopalan, S., Habetler, T.G., Harley, R.G., Sebastian, T., Lequesne, B. (2007). Current/voltagebased detection of faults in gears coupled to electric motors. IEEE Transactions on Industry Applications, 42 (6), 1414-1420.
Search in Google Scholar
[7] Huang, X., Habetler, T.G., Harley, R.G. (2007). Detection of rotor eccentricity faults in closed-loop drive-connected induction motors using an artificial neural network. IEEE Transactions on PowerElectronics, 22 (4), 1552-1559.10.1109/TPEL.2007.900607
Search in Google Scholar
[8] Wan, S.T., Li, H.M., Li, Y.G, Meng, F.C. (2005). Analysis of stator winding parallel-connected branches circulating current and its application in generator fault diagnosis. In Conference Record of the IndustryApplications Conference : Fourthieth IAS AnnualMeeting, 2-6 October 2005. IEEE, Vol. 1, 42-45.
Search in Google Scholar
[9] Blodt, M., Chabert, M., Regnier, J., Faucher, J. (2006) Mechanical load fault detection in induction motors by stator current time-frequency analysis. IEEETransactions on Industry Applications, 42 (6), 1454-1463.10.1109/TIA.2006.882631
Search in Google Scholar
[10] Thomas, V.V., Vasudevan, K., Kumar, V.J. (2003). Online cage rotor fault detection using air-gap torque spectra. IEEE Transactions on Energy Conversion, 18 (2), 265-270.10.1109/TEC.2003.811718
Search in Google Scholar
[11] Gaouda, A.M., Salama, M.M.A., Sultan, M.R., Chikhani, A.Y. (1999). Power quality diction and classification using wavelet-multiresolution signal decomposition. IEEE Transactions on Power Delivery, 14 (4), 1469-1476.10.1109/61.796242
Search in Google Scholar
[12] Jena, D.P., Kumar, R. (2011). Implementation of wavelet denoising and image morphology on welding image for estimating HAZ and welding defect. Measurement Science Review, 11 (4), 108-111.10.2478/v10048-011-0020-3
Search in Google Scholar
[13] Wei, L., Wang, H., Li, F. (2009). Fault diagnosis of turbine generator vibration based on wavelet packet and data-driven. In ISECS International Colloquiumon Computing, Communication, Control, andManagement (CCCM 2009), 8-9 August 2009. IEEE, Vol. 2, 29-32.
Search in Google Scholar
[14] Fan, X., Zuo, M.J. (2006). Gearbox fault detection using Hilbert and wavelet packet transform. Mechanical Systems and Signal Processing, 20 (4), 966-982.10.1016/j.ymssp.2005.08.032
Search in Google Scholar
[15] Stockwell, R.G., Mansinha, L., Lowe, R.P. (1996). Localization of the complex spectrum: The Stransform. IEEE Transactions on Signal Processing, 44 (4), 998-1001.10.1109/78.492555
Search in Google Scholar
[16] Yuping, Z. (2006). Hilbert-Huang transform and marginal spectrum for detection of bearing localized defects. In The 6th World Congress on IntelligentControl and Automation (WCICA 2006). IEEE, Vol. 2, 5457-5461.
Search in Google Scholar
[17] Cheng, J.S., Yu, D.J., Yang, Y. (2007). Application of support vector regression machines to the processing of end effects of Hilbert-Huang transform. Mechanical Systems and Signal Processing, 21 (3), 1197-1211.10.1016/j.ymssp.2005.09.005
Search in Google Scholar
[18] Chaovalitwongse, W.A., Fan, Y., Sachdeo, R.C. (2007). On the time series K-nearest neighbor classification of abnormal brain activity. IEEETransactions on System, Man and Cybernetics, Part A:System and Humans, 37 (6), 1005-1016.10.1109/TSMCA.2007.897589
Search in Google Scholar
[19] Manoharan, S.C., Veezhinathan, M., Ramakrishnan, S. (2008). Comparison of two ANN methods for classification of spirometer Data. MeasurementScience Review, 8 (3), 53-57.10.2478/v10048-008-0014-y
Search in Google Scholar
[20] Rumelhart, D.E., Hinton, G.E., Willia, R.J. (1986). Learning representations by back-propagation errors. Nature, 323, 533-536.10.1038/323533a0
Search in Google Scholar
[21] Song, T., Jamshidi, M.M., Lee, R.R., Huang, M. (2007). A modified probabilistic neural network for partial volume segmentation in brain MR image. IEEETransactions on Neural Network, 18 (5), 1424-1432.10.1109/TNN.2007.89163518220190
Search in Google Scholar
[22] Chen, B., Liu, H., Chia, J., Bao, Z. (2009). Large margin feature weighting method via linear programming. IEEE Transactions on Knowledge andData Engineering, 21 (10), 1475-1488.10.1109/TKDE.2008.238
Search in Google Scholar
[23] Middlemiss, M.J., Dick, G. (2003). Weighted feature extraction using genetic algorithms for intrusion detection. In The 2003 Congress on EvolutionaryComputation (CEC ‘03), 8-12 December 2003. IEEE, Vol. 3, 1669-1675.
Search in Google Scholar
[24] Kennedy, J., Eberhart, R. (1995). Particle swarm optimization. In IEEE International Conference onNeural Networks. IEEE, Vol. 4, 1942-1948.
Search in Google Scholar
[25] Biswal, B., Dash, P.K., Panigrahi, B.K. (2009). Power quality disturbance classification using fuzzy C-means algorithm and adaptive particle swarm optimization. IEEE Transactions on Industrial Electronics, 56 (1), 212-220.10.1109/TIE.2008.928111
Search in Google Scholar
[26] Parsopoulos, K.E., Vrahatis, M.N. (2002). Particle swarm optimization method for constrained optimization problems. In Intelligent Technologies -Theory and Application: New Trends in IntelligentTechnologies. IOS Press, Vol. 76, 214-220.
Search in Google Scholar
[27] Valle, Y.D., Venayagamoorthy, G.K., Mohagheghi, S., Hernandez, J., Harley, R.G. (2008). Particle warm optimization: Basic concepts, variants and applications in power systems. IEEE Transactions on EvolutionComputation, 12 (2), 171-195.
Search in Google Scholar

Detection of Gearbox lubrication Using PSO-Based WKNN

Abstract

Paradigm

My account