Abstract
The vibration signal of rotating machinery compound faults acquired in actual fields has the characteristics of complex noise sources, the strong background noise, and the nonlinearity, causing the traditional blind source separation algorithm not be suitable for the blind separation of rotating machinery coupling fault. According to these problems, an extraction method of multisource fault signals based on wavelet packet analysis (WPA) and fast independent component analysis (FastICA) was proposed. Firstly, according to the characteristic of the vibration signal of rotating machinery, an effective denoising method of wavelet packet based on average threshold is presented and described to reduce the vibration signal noise. In the method, the thresholds of every node of the best wavelet packet basis are acquired and averaged, and then the average value is used as a global threshold to quantize the decomposition coefficient of every node. Secondly, the mixed signals were separated by using the improved FastICA algorithm. Finally, the results of simulations and real rotating machinery vibration signals analysis show that the method can extract the rotating machinery fault characteristics, verifying the effectiveness of the proposed algorithm.
Highlights
Rotating machinery plays an increasingly important role in modern industry and intelligent manufacturing
From the analysis of frequency domain characteristics, only slight unbalance fault can be identified. It can be seen from the time-domain waveform in Figure 10 that under strong noise interference, the classical fast independent component analysis (FastICA) is used to directly separate the sampling signal, and the fault type of the rotor system cannot be identified from the time-domain waveform
A blind source separation algorithm based on wavelet packet analysis (WPA)-FastICA is proposed to solve the problem of fast feature extraction for weak fault of rotating machinery
Summary
Rotating machinery plays an increasingly important role in modern industry and intelligent manufacturing. Xin et al [24] proposed a fault feature extraction and diagnosis method for vibration signal based on iterative empirical wavelet transform (EWT) and sparse filter. If the noise is ignored and the blind source separation algorithm is directly used to separate the mixed vibration signals, it may produce large errors or draw wrong conclusions. Aiming at the problem of weak fault feature signal extraction of rotating machinery under the influence of noise, a fault separation method based on wavelet packet analysis (WPA) filter and improved fast independent component analysis (FastICA) algorithm is proposed. Wavelet packet filter is used to denoise the mixed signal under noise interference, and the improved FastICA algorithm is used to separate the denoised signal, and the weak fault signal is effectively extracted.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
