Open Access Open Access  Restricted Access Subscription or Fee Access

Implementation of Locally Weighted Projection Regression Network for Condition Monitoring of a Steam Turbine

K. Satyanarayana, Dr.M.M.M. Sarcar, Dr.S. Purushothaman

Abstract


Steam Turbine used in power station is a costly system. It is used to drive generators for producing electricity. Periodic monitoring and preventive maintenance is mandatory to minimize heavy loss in terms of time and money. The loss can be sudden breakage of small to large sized mechanical rotating parts due to improper maintenance. There are many methods of identifying the fault that prevails when the turbine is operating. However, monitoring of vibration of rotating parts is very important as the vibration slowly escalates to different mechanical parts leading to failure of components. Many statistical methods, artificial neural network algorithms, evolutionary algorithms have been proposed by earlier researchers especially for bearing fault identification, gas turbine condition monitoring. However, there are very limited publications that discusses about implementation of ANN in condition monitoring of steam turbine. This paper implements Locally weighted projection regression (LWPR) which experimentally recognizes turbine bearings faults. Wavelet coefficients are obtained from the vibration signal and used as feature. The statistical parameters of the wavelet coefficients are used to train the LWPR. The turbine working condition has been categorized as good, satisfactory and bad. RBF with 5 X 7 X 1 topology has been used to classify the conditions of turbine.

Keywords


Locally Weighted Projection Regression Neural Network, Turbine Data, Vibration

Full Text:

PDF

References


Alguindigue, I. E., Loskiewicz-Buczak, A. and Uhrig, R. E., 1993, Monitoring and diagnosis of rolling element bearings sing artificial neural networks, IEEE Transactions on Industrial Electronics, Vol.40, pp.209–216.

Atiya AF and Parlos AG, 2000, New results on recurrent network training: Unifying the algorithms and accelerating convergence, IEEE Trans. Neural Networks, Vol.11, Issue 3, pp.697-709.

Chebil, J., Noel, G., Mesbah, M., Deriche, M., 2009,Wavelet Decomposition for the Detection and Diagnosis of Faults in Rolling Element Bearings, Jordan Journal of Mechanical and Industrial Engineering, Vol.3, No.4, pp.260-267.

Chow, M., Mangum, P. M., and Yee, S. O., 1991, A neural network approach to real-time condition monitoring of induction motors, IEEE Transactions on Industrial Electronics, Vol.38, pp.448–453.

Dellomo, M.R., 1999. Helicopter gearbox fault detection: a neural network-based approach. Transactions of the ASME, Journal of Vibration and Acoustics, Vol.121, pp.265–272.

Gary, Y., Yen, Kuo-Chung Lin, 1999, Wavelet packet feature extraction for vibration monitoring, Proceedings of the IEEE International Conference on Control Applications, pp. 1573-1578.

Jaeger H., “The „echo-state‟ approach to analysing and training recurrent neural networks,” Fraunhofer Institute for Autonomous Intelligent Systems, GDM Report 148, December 2001.

James Li, C., Jun Ma, 1997, Wavelet decomposition of vibrations for detection of bearing-localized defects, Independent Nondestructive Testing and Evaluation (NDT&E) International, Vol.30, No.3, pp.143-149.

Kahaei, M. H., Torbatian, M., and Poshtan, J., 2006, Detection of bearing faults using Haar wavelets, IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, E89-A(3), pp.757-763.

Lada, E. K., Lu, J. C., and Wilson, J. R., 2002, A wavelet-based procedure for process fault detection, IEEE Transactions on Semiconductor Manufacturing, Vol.15, No.1, pp.79-90.

McCormick, A. C., and Nandi, A. K., 1997, Classification of the rotating machine condition using artificial neural networks, Proceedings of Institution of Mechanical Engineers, Part C 211, pp.439–450.

McCormick, A. C., and Nandi, A. K., 1997, Real-time classification of the rotating shaft loading conditions using artificial neural networks, IEEE Transactions on Neural Networks, Vol.8, pp.748–756.

McCormick, A. C., Nandi, A. K., and Jack, L. B., 1998, Application of periodic time-varying autoregressive models to the detection of bearing faults, Proceedings of Institution of Mechanical Engineers, Part C 212, pp.417–428.

McCormick, A.C., Nandi, A.K., 1997, Classification of the rotating machine condition using artificial neural networks. Proceedings of IMechE, Part C: Journal of Mechanical Engineering Science, Vol.211, pp.439–450.

Nandi, A.K., 2000. Advanced digital vibration signal processing for condition monitoring. Proceedings of COMADEM2000, Houston, TX, USA, pp. 129–143.

Paya, B. A., Esat, I. L., and Badi, M. N. M., 1997, Artificial neural network based fault diagnostics of rotating machinery using wavelet transforms as a preprocessor, Mechanical Systems and Signal Processing, Vol.11, pp.751–765.

Purushothaman S., Suganthi D., fmri segmentation using echo state neural network, International Journal of Image Processing, Vol.2, Issue 1, 2008, pp.1‐9.

Samanta, B., Al-Balushi, K.R., 2001. Use of time domain features for the neural network based fault diagnosis of a machine tool coolant system. Proceedings of IMechE, Part I: Journal of Systems and Control Engineering, Vol.215, pp.199–207.

Samanta, B., Al-Balushi, K.R., 2003, Artificial neural network based fault diagnostics of rolling element bearings using time domain features. Mechanical Systems and Signal Processing, Vol.17, No.2, pp.317–328.

Samanta, B., Al-Balushi, K.R., Al-Araimi, S.A., 2001. Use of genetic algorithm and artificial neural network for gear condition diagnostics. Proceedings of COMADEM 2001, University of Manchester, UK, pp.449–456.

Sethu Vijayakumar, Stefan Schaal, 2000, Locally Weighted Projection Regression : An O(n) Algorithm for Incremental Real Time Learning in High Dimensional Space, Proc. of Seventeenth International Conference on Machine Learning (ICML2000), pp.1079-1086.

Sethu Vijayakumar, Stefan Klanke, Stefan Schaal, 2008, A Library for Locally Weighted Projection Regression, Journal of Machine Learning Research, Vol. 9, pp. 623-626.


Refbacks

  • There are currently no refbacks.