Fault detection of rolling bearing based on FFT and classification

Abstract

The rolling bearing carries a load by placing rolling elements between two bearing rings. It is a key device in the railway vehicles for monitoring work states to ensure high reliability and better performance of rotating machine. The states of rolling bearings can be detected by the measurement of vibration signals with effective process, features extraction and analysis. The propose of this paper is to establish an efficient and robust signal processing technique and classification mechanism to detect the fault of rolling bearing. Firstly Fast Fourier Transform is used to extract features and then these parameters are input into various classification schemes for accurate fault detection. Ensemble Rapid Centroid Estimation is proposed and then compared with Artificial Neural Network, and Principal Components Analysis. The simulation analyses the approaches of fault detection and the accuracy of identification.Then the linear performance of the data is proved by least square regularized regression.Finally various schemes are compared and analyzed to obtained the most efficient method for fault detection.

Integrating synthetic minority oversampling and gradient boosting decision tree for bogie fault diagnosis in rail vehicles

“…They show good performance in fault diagnosis individually or in combination. [18][19][20][21][22] The energy and entropy parameters, like energy, torque, Shannon entropy, energy entropy, which contain more information, are also added to this paper to show the characteristic of bogie vibration and get a better diagnosis result in different situations.…”

Effectiveness Analysis of PMSM Motor Rolling Bearing Fault Detectors Based on Vibration Analysis and Shallow Neural Networks

“…In general, rolling bearings consist of a cage in which the rolling elements are placed and properly separated. The cage is located between the inner ring, which is placed on the machine shaft, and the outer ring [21]. The rolling bearing structure is shown in Figure 1.…”

“…Most often, they result from improper assembly, often they are also caused by improper selection of the bearing to the drive requirements and its improper operation [26][27][28][29]. Depending on which element of the bearing is spot damaged, different damage symptoms appear in the spectrum of the mechanical vibration signal [13,21,24,25].…”

“…Therefore, methods are being sought to eliminate this human factor and automate the detection process. At present, this task is more often performed by neural networks (NNs), which can act as detectors and/or classifiers of damages, minimizing human participation in the diagnostic process [1,5,[14][15][16][17][18][19][20][21][22][23].…”

Bearing Fault Diagnosis Approach under Data Quality Issues

“…The main advantage of this method is that the mathematical modeling for the physical setup is not needed and classical signal processing techniques can be exploited in noise reduction and feature extraction. These methods include several diagnostic techniques in the time and frequency domains, including kernel density estimation (KDE), root mean square (RMS) [1], crest factor (CF) [2], Kurtosis [3,4], Fast Fourier transform [5], wavelet transform [6], and wavelet packet transform (WPT) [7]. The main challenge is the stage of preprocessing the raw vibration measurements to attenuate noise and extract the original signal.…”