Early Weak Fault Diagnosis of Rolling Bearing Based on Multilayer Reconstruction Filter
Open Access
- 1 January 2021
- journal article
- research article
- Published by Wiley in Shock and Vibration
- Vol. 2021 (1)
Abstract
The early weak fault characteristics of rolling bearings are extremely weak and are easily overwhelmed by other noises. In order to effectively extract the characteristics of the early weak faults of the rolling bearings and draw on the multilayer wavelet decomposition idea, a method for diagnosing the early weak faults of the rolling bearing based on the multilayer reconstruction filter is proposed. As we all know, empirical wavelet transform (EWT) makes full use of wavelet filter bank, and variational mode decomposition (VMD) uses Wiener filter bank. This paper fully combines the advantages of the above two methods, adaptively determines the number of modes through empirical wavelet decomposition and divides the original signal, extracts the frequency band that contains the fault characteristic information, and effectively eliminates noise interference. These steps are repeated until the optimal component of the condition is obtained. In the output layer, the weak fault impact components are further separated by the strong filtering and signal decomposition capability of VMD. The advantages of the proposed method are proved by the experiment of weak fault of rolling bearing and the accelerated failure experiment of full life. The proposed method has the advantages of reducing noise influence and adaptive estimation of decomposed modes, which can be applied more efficiently in practice.Keywords
This publication has 29 references indexed in Scilit:
- Fractional frequency band entropy for bearing fault diagnosis under varying speed conditionsMeasurement, 2021
- Multiple Time-Frequency Curve Classification for Tacho-Less and Resampling-Less Compound Bearing Fault Detection Under Time-Varying Speed ConditionsIEEE Sensors Journal, 2020
- Acoustic signal based fault detection on belt conveyor idlers using machine learningAdvanced Powder Technology, 2020
- Intelligent acoustic-based fault diagnosis of roller bearings using a deep graph convolutional networkMeasurement, 2020
- Improved Empirical Wavelet Transform for Compound Weak Bearing Fault Diagnosis with Acoustic SignalsApplied Sciences, 2020
- Compound Bearing Fault Detection Under Varying Speed Conditions With Virtual Multichannel Signals in Angle DomainIEEE Transactions on Instrumentation and Measurement, 2020
- Gearbox fault diagnosis using acoustic signals, continuous wavelet transform and adaptive neuro-fuzzy inference systemApplied Acoustics, 2019
- Fault diagnosis of single-phase induction motor based on acoustic signalsMechanical Systems and Signal Processing, 2019
- An Improved VMD With Empirical Mode Decomposition and Its Application in Incipient Fault Detection of Rolling BearingIEEE Access, 2018
- Early fault diagnosis of bearing and stator faults of the single-phase induction motor using acoustic signalsMeasurement, 2018