Development of a dynamic maintenance system for electric motor’s failure prognosis
During the last years there have become a lot of studies concerning the preventive maintenance of mechanical equipment and fault diagnosis, each one of them having a different approach. The predictive maintenance allows to be continuously known the kind of maintenance and care that a system needs, and mainly what kind of equipment replacement is foreseen in the future. This paper presents the development of a smart – dynamic maintenance system for electric motor’s failure prognosis. The method is based on the analysis of the motor into his subsystems by using neural networks and by recording their relations and interactions. In this model are also embodied the possible damages of every subsystem and its symptoms, respectively. The objective goal of this analysis is to develop an algorithm for the calculation of the probability of showing the damage in a motor’s part according to its dynamic operational status. The creation of a data basis reflects the techniques experience concerning the causes and the possible preventive actions that are necessary. The suggested method is general and can be applied in every part or system of the mechanical equipment. Finally, the paper presents a simple study case for the rotor and practical conclusions are drawn which can lead to a better focus on preventive maintenance.
KeywordsElectric Motor Fault Diagnosis Preventive Maintenance Spare Part Mechanical Equipment
Unable to display preview. Download preview PDF.
- 1.J. D. Patton, “Preventive Maintenance”: Instrument Soc. Of America, 1983.Google Scholar
- 2.S.S. Rao, “Reliability-Based Design”: McGraw-Hill, 1992.Google Scholar
- 10.J. Jang, C. Sun, and E. Mizutani, Neuro-Fuzzy and Soft Computing. Englewood Cliffs, NJ: Prentice-Hall, 1997.Google Scholar
- 12.An Intelligent System for Machinery Condition Monitoring IEEE Trans. Fuzzy Syst 10.1109/TFUZZ.2007.896237 January 17, 2006.Google Scholar
- 13.R. Patton, P. Frank, and R. Clark, Issues of Fault Diagnosis for DynamicSystems. New York: Springer-Verlag, 2000.Google Scholar
- 15.M. Pourahmadi, Foundation of Time Series Analysis and Prediction Theory. New York: Wiley, 2001.Google Scholar
- 16.J. Korbicz, Fault Diagnosis: Models, Artificial Intelligence, Applications. New York: Springer-Verlag, 2004.Milan J & Munt CE. (1992)Google Scholar
- 22.H. Ishibuchi and T. Nakashima, “Effect of rule weights in fuzzy rulebased classification systems,” IEEE Trans. Fuzzy Syst., vol. 9, no. 4, pp. 506–515, Aug. 2001.  M. Kowal and J. Korbicz, “Robust fault detection using neuro-fuzzy networks,” in Proc. 16th IFAC World Congr., 2004, Prague Czech Republic, CD-ROM.Google Scholar
- 31.V. Giurgiutiu, “Current issues in vibration-based fault diagnostics and prognostics,” in Proc. SPIE 9th Int. Symp. Smart Structures Materials, San Diego, CA, 2002, pp. 17–21.Google Scholar
- 32.D. McFadden, “Detecting fatigue cracks in gears by amplitude and phase demodulation of the meshing vibration,” J. Vib., Acoust., Stress, Reliab. Design, vol. 108, pp. 165–170, 1986.Google Scholar
- 33.N. Nikolaou and I. Antoniadis, “Rolling element bearing fault diagnosis using wavelet packets,” Nondestructive Test. Eval. Int., vol. 35, pp. 197–205, 2002.Google Scholar
- 37.Statistical analysis. SKF, Gerard Schram, May 2003.Google Scholar