Application of improved Hilbert-Huang and wavelet packet transforms in broken rotor bar fault detection

Abstract

one of the common techniques of rotary machinery fault diagnosis is the signal based fault diagnosis, in which the signal processing is one of its integral part. Signal processing converts the raw data into useful features to make the diagnostic operations. These features should be independent from the normal working conditions of the machine and the external noise. They should be sensitive only to faults in the machine. Therefore, providing more efficient processing techniques in order to achieve more useful features of the signal and faster and more accurate fault detection have been considered by researchers. This project applies the improved Hilbert-Huang Transform to decompose the signal into narrow frequency bands and extract instantaneous frequency and wavelet packet transform to remove the initial signal noise in vibration signal due to the broken rotor bars fault to achieve more useful features of vibration signals for the next stages of diagnosis. Comparison of Hilbert transform amplitude spectrum and detected instantaneous frequency by the Hilbert-Huang Transform and the improved Hilbert-Huang transform techniques and combining the improved Hilbert-Huang transform and wavelet packet transform indicate the superiority of the combined technique to detect frequencies of the fault.