Abstract
The fault response signals of an axle-box bearing of a rail vehicle have strongly non-linear and non-stationary characteristics, which can reflect the operating state of the running gears. This paper proposes a novel method for bearing fault diagnosis based on frequency-domain energy feature reconstruction (EFR) and composite multiscale permutation entropy (CMPE). First, a wavelet packet transform (WPT) is applied to decompose the vibration signals into multiple frequency bands. Then, considering that the bearing-localized defects cause the axle-box bearing system to resonate at a high frequency, which will lead to uneven energy distribution of the signal in the frequency domain, the energy factors of each frequency band are calculated by an energy feature extraction algorithm, from which the frequency band with maximum energy factor (which contains abundant fault information) is reconstructed to the time-domain signal. Next, the complexity of the reconstructed signals is calculated by CMPE as fault feature vectors. Finally, the feature vectors are input into a medium Gaussian support vector machine (MG-SVM) for bearing condition classification. The proposed method is validated by a public bearing data set and a wheelset-bearing system test bench data set. The experimental results indicate that the proposed method can effectively extract bearing fault features and provides a new solution for condition monitoring and fault diagnosis of rail vehicle axle-box bearings.
Highlights
As an important component affecting the operational safety of rail vehicles, the axle-box bearing of the running gear bears various dynamic impacts, such as vehicle body load and starting, traction, and braking forces during operation
A new method for fault diagnosis for rail vehicle axle-box bearings based on frequency-domain energy feature reconstruction, composite multiscale permutation entropy (CMPE), and medium Gaussian support vector machine (MG-SVM) is proposed
Based on the fact that fault impact can cause axle-box bearing system resonance and lead to an uneven energy distribution of the vibration signal in the frequency domain, the frequency band with maximum energy factor containing abundant fault information is reconstructed to a time-domain signal
Summary
As an important component affecting the operational safety of rail vehicles, the axle-box bearing of the running gear bears various dynamic impacts, such as vehicle body load and starting, traction, and braking forces during operation. As the axle-box bearing is affected by the wheel-rail high frequency impact and the alternating load of the primary suspension, the vibration signals show strongly non-linear and non-stationary characteristics, and the response signal of an early fault of a bearing is very weak, relative to the strong background noise. Extracting the features of bearing faults in the non-linear, multi-component amplitude and frequency modulated signals, and accurately identifying the bearing conditions has always been a difficult point in bearing fault diagnosis [1,2,3]. Bearing fault diagnosis consists of two aspects: fault feature extraction and fault type recognition. Time-frequency analysis methods can be used effectively to decompose and describe response signals of bearing early faults, including wavelet transform (WT), empirical mode
Sign-in/Register to view highlights & summary 
Published Version (
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