Prediction of Coast Down Time for Mechanical Faults in Rotating Machinery Using Artificial Neural Networks

Authors: G. R. Rameshkumar, B. V. A Rao, K. P. Ramachandran

Abstract:

Misalignment and unbalance are the major concerns in rotating machinery. When the power supply to any rotating system is cutoff, the system begins to lose the momentum gained during sustained operation and finally comes to rest. The exact time period from when the power is cutoff until the rotor comes to rest is called Coast Down Time. The CDTs for different shaft cutoff speeds were recorded at various misalignment and unbalance conditions. The CDT reduction percentages were calculated for each fault and there is a specific correlation between the CDT reduction percentage and the severity of the fault. In this paper, radial basis network, a new generation of artificial neural networks, has been successfully incorporated for the prediction of CDT for misalignment and unbalance conditions. Radial basis network has been found to be successful in the prediction of CDT for mechanical faults in rotating machinery.

Keywords: Coast Down Time, Misalignment, Unbalance, Artificial Neural Networks, Radial Basis Network.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1072100

References:

[1] Piotrowski John, "Shaft alignment handbook," 3rd ed. New York: CRC Press, Taylor & Francis Group LLC, 2007, pp. 341-351.
[2] Victor Wowk, "Machinery vibration measurement and analysis," McGraw-Hill, Inc, 1991, pp. 127-130.
[3] T. L. Daugherty, and R. J. Craig, "Coast down time as a mechanical condition indicator for vertical axis motors with grease-lubricated ball bearings," American Society of Lubrication Engineers Transactions, vol. 22, pp. 349-357, 1977.
[4] B. S. Prabhu, "An experimental investigation on the misalignment effects in journal bearings," Tribology Transactions, vol. 40, 2, pp. 235-242, 1997.
[5] P. Arumugam, S. Swarnamani, and B. S. Prabhu, "Effects of journal misalignment on the performance characteristics of three-lobe bearings," Wear 206. pp. 122-129, 1997.
[6] K. P. Ramachandran, M. Z. K. Malik, and A. Abdul Harees, "CDT analysis as a tool for evaluating bearing lubrication and mechanical conditions," Caledonian Journal of Engineering, pp. 19-24, Dec. 2004.
[7] R. Edwin Browne, K. P. Ramachandran, A. K. M. De Silva, and D. K Harrison, "An experimental investigation to analyze the effect of unbalance in a horizontal rotor system using coast down factor," International Journal of COMADEM, 10(3), pp. 11-18, July 2007.
[8] G. R. Rameshkumar, B. V. A. Rao, and K. P. Ramachandran, "Evaluation of unbalance and misalignment effect on forward curved centrifugal blower using coast down time analysis," International Journal of COMADEM, submitted for publication.
[9] K. Mehrotra, C.K. Mohan and S. Ranka, "Elements of artificial neural networks," Mumbai, Penram International, 1997.
[10] A. K. Nandi, "Advanced digital vibration signal processing for condition monitoring," Proc. 13th International congress and exhibition on condition monitoring and diagnostic engineering management (COMADEM2000), Houston, Tex, USA, pp. 129-143, December 2000.
[11] R. B. Randall, Ed, "Special issue on gear and bearing diagnostics," Mechanical Systems and Signal Processing, vol. 15(5), pp. 827-1029, 2001.
[12] B. A. Paya, I. L. Esat, and M. N. M. Badi, "Artificial neural network based fault diagnosis of rotating machinery using wavelet transforms as a preprocessor," Mechanical Systems and Signal Processing, vol. 11(5), pp. 751-765, 1997.
[13] Al-Raheem Khalid F, A. Roy, K. P. Ramachandran, D. K. Harrison, and S. Grainger, "Application of Laplace wavelet combined with artificial neural networks for rolling element bearing fault diagnosis," ASME J. of vibration and Acoustics, vol.130 (5), pp. 1-9, 2008.
[14] B. Samanth, and K. R. Al Balushi, "Artificial neural network based fault diagnostics of rolling element nearing using time-domain features," Mechanical Systems and Signal Processing, vol. 17(5), pp. 317-328, 2003.
[15] B. Li, M. Y. Chow, Y. Tipsuwan, and J. C. Hung, "Neural network based motor rolling bearing fault diagnosis," Transactions on Industrial Electronics, vol. 47(5), pp. 1070-1078, 2000.
[16] B. Sreejith, A. K. Varma and A. Srividya, "Fault diagnosis of rolling element bearing using time-domain features and neural networks," Proceedings of the IEEE International Conference on Industrial and Information systems (ICIIS2000) Kharagpur, India, pp. 1-6, 2008.
[17] A. C. McCormick, and A. K. Nandi, "Classification of the rotating machine condition using artificial neural networks," Proceedings of Institution of Mechanical Engineers, Part C, vol. 211, pp. 439-450, 1997.
[18] L. B. Jack, and A. K. Nandi, "Feature selection for ANNs using Genetic Algorithms in Condition Monitoring," European Symposium on Artificial Neural Networks, Bruges (Belgium), pp. 313-318, April 1999.
[19] A. Baraldi, and N. A. Borghese, "Learning from data: general issues and special applications of radial basis function networks," Tech. Rep. TR- 98-028, International Computer Science Institute, Berkeley, California, USA, 1998.
[20] J. Park, and I. W. Sandberg, "Universal approximation using radial basis function networks," Neural Computation, vol. 5, no.2, pp. 305-316, 1993.
[21] L. B. Jack, A. K. Nandi, and A. C. McCormick, "Diagnosis of rolling element bearing faults using radial basis functions," EUEASIP Journal on Applied Signal Processing, vol. 6, pp. 25-32, 1999.
[22] L. Govindarajan, and P. L. Sabarathinam, "Prediction of vapor-liquid equilibrium data by using radial basis neural networks," Chem. Biochem. Eng. Q. 20 (3), pp. 319-323, 2006.
[23] G. R. Rameshkumar, B. V. A. Rao, and K. P. Ramachandran, "An experimental investigation to study the effect of misalignment using CDT as a condition monitoring parameter for rotating machinery," 22nd International Congress, COMADEM 2009, San Sebastian, Spain, pp. 531-539, June 2009.
[24] Joseph S Shighley, and Charies R Mischke, "Mechanical engineering design," 5th ed. McGraw-Hill, 1989, pp. 503.
[25] F. Li. Min, "Neural networks in computer intelligence," 1st ed. Singapore: McGraw-Hill, 1994.
[26] L. Govindarajan, "Optimal design of reactors," PhD Thesis, Annamalai University, India, 2005.
[27] Neural Networks Toolbox User-s guide, 1st ed. The Math Work Inc, Mass, 1994.