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.