A Comparative Study on the Vibration Signal-Based Damage Detection for Rotor-Bearing System in Speed-Up Process:The Feature Extraction Approach

The goal of system monitoring and diagnostics is to minimize economic losses, to increase stability, to maximize productivity, and to maintain product quality in manufacturing. The feature extraction from the signals acquired in rotating machine is required for performance evaluation, condition monitoring, and fault diagnostics. In this paper, we extracted the distinctive features from vibration signals gathered in rotor-bearing system during acceleration in order to monitor an abnormal condition by using various kinds of signal processing methods such as the Fast Fourier Transform, Short-Time Fourier Transform, Wigner-Ville Distribution, and Discrete Wavelet Transform.