Feature Extraction Method for Condition Monitoring of Rolling Element Bearings Based on Dual-Tree Complex Wavelet Packet Transform and VMD

Abstract

The feature extraction of rolling element bearings vibration signals is one of the key issue for high-speed rotating machinery condition monitoring. A new scheme based on Dual-Tree Complex Wavelet Packet Transform (DTCWPT) and Variational Mode Decomposition (VMD) for extracting vibration condition monitoring feature is proposed. First, DTCWPT is used to reduce noise and pseudo frequency components from vibration signals by the energy ratio. Second, a set of Intrinsic Mode Function components (IMFs) can be got by VMD. Then, the energy ratio between the screening vibration signal and IMFs are calculated. And, the corresponding IMFs are selected according to the energy ratio threshold. Finally, applying the spectrum analysis technology, the condition monitoring feature can be extracted from the reconstructing signal. The experimental results of simulation signals and practical rolling element bearings vibration signals show that the scheme is feasible and effective for extracting the bearings operation state feature.