Induction machine fault diagnostic analysis with wavelet technique

A wavelet transform based method was developed for diagnosing machine faults operating at different rotating speeds. This paper shows that machine fault diagnosis can be effectively performed when an appropriate narrow-band filter is used to extract the required spectra components. A wavelets-transform-based technique is used to design specified narrow filter banks. This enables effective machine fault diagnostic analysis to be performed in the frequency domain. Gaussian-enveloped oscillation-type wavelet is employed. By matching the wavelet basis functions with the associated faulty signals, the required narrow filter banks are obtained. As a result, the detection and diagnosis of machine faults operating at different rotating speeds are made possible. The proposed technique was thoroughly tested at different rotating speeds.