Abstract
To improve the fault identification accuracy of rolling bearing and effectively analyze the fault severity, a novel rolling bearing fault diagnosis and severity analysis method based on the fast sample entropy, the wavelet packet energy entropy, and a multiclass relevance vector machine is proposed in this paper. A fast sample entropy calculation method based on a kd tree is adopted to improve the real-time performance of fault detection in this paper. In view of the non-linearity and non-stationarity of the vibration signals, the vibration signal of the rolling bearing is decomposed into several sub-signals containing fault information by using a wavelet packet. Then, the energy entropy values of the sub-signals decomposed by the wavelet packet are calculated to generate the feature vectors for describing different fault types and severity levels of rolling bearings. The multiclass relevance vector machine modeled by the feature vectors of different fault types and severity levels is used to realize fault type identification and a fault severity analysis of the bearings. The proposed fault diagnosis and severity analysis method is fully evaluated by experiments. The experimental results demonstrate that the fault detection method based on the sample entropy can effectively detect rolling bearing failure. The fault feature extraction method based on the wavelet packet energy entropy can effectively extract the fault features of vibration signals and a multiclass relevance vector machine can identify the fault type and severity by means of the fault features contained in these signals. Compared with some existing bearing rolling fault diagnosis methods, the proposed method is excellent for fault diagnosis and severity analysis and improves the fault identification rate reaching as high as 99.47%.
Highlights
Rolling bearings, one of the important parts of rotating machinery, reduce the friction loss between mechanical components
To verify the effectiveness of the proposed rolling bearing fault diagnosis and severity analysis method, the experimental data selected in this paper are all obtained from the Bearing Data Center of
The rolling bearing was tested under four different loads of 0, 1, 2, and 3 horse power, each type of fault ranging from 0.007 inches to 0.040 inches in diameter
Summary
One of the important parts of rotating machinery, reduce the friction loss between mechanical components. To effectively extract the fault features from the non-linear and non-stationary vibration signals, many time–frequency analysis methods have been applied to rolling bearing fault diagnoses for vibration signal decomposition. A novel fault diagnosis and severity analysis method based on fast sample entropy (SampEn), wavelet packet energy entropy (WPEE), and multiclass relevance vector machine (mRVM) is presented for rolling bearings. The wavelet packet energy entropy is used to describe the characteristics and severity of different fault types This approach can solve the problem of a low fault diagnosis accuracy caused by the weak separability of feature vectors extracted from non-stationary and non-linear vibration signals.
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
