Ball Bearing Fault Diagnosis Using Continuous Wavelet Transforms with Modern Algebraic Function
Ball bearing plays a very crucial part of any rotating machineries, and the fault diagnosis in rotating system can be detected at early states when the fault is still small. In this paper, a ball bearing fault is detected by using continuous wavelet transform (CWT) with modern algebraic function. The reflected vibration signals from ball bearing having single point defect on its inner race, outer race, ball fault, and combination of these faults have been considered for analysis. The features extracted from a non-stationary multi-component ball bearing signal are very difficult. In this paper, a CWT with selected stretching parameters is used to analyze a signal in time–frequency domain and extract the features from non-stationary multi-component signals. The algebraic function norms are calculated from the matrix which can be generated with the help of wavelet transforms. The norms lookup table is used as a reference for fault diagnosis. The experimental results show that this method is simple and robust.
KeywordsBearing faults Norms CWT
- 1.Chiang, L.H., Kotanchek, M.E., Kordon, A.K.: Fault diagnosis based on Fisher discriminate analysis and support vector machines. 28, 1389–1401 (2004)Google Scholar
- 9.Galli, A.W., Heyd, G.T.: Comments on power quality assessment using wavelets. The 27 Annual NAPS. Bozeman, MT, U.S.AGoogle Scholar
- 10.Yuan, F.S., Chu, F.L.: Fault diagnosis based on particle swarm optimization and support vector machines. Mech. Syst. Sign. Process. 20, 1787–1798 (2007)Google Scholar
- 15.Watrous, J.: Theory of Quantum Information, 2.4 Norms of operators, lecture notes, University of Waterloo (2008)Google Scholar
- 16.Meyer, C.D.: Matrix Analysis and Applied Linear Algebra. SIAM (2000)Google Scholar