Energy-Based Feature Extraction for Defect Diagnosis in Rotary Machines

This paper presents an energy-based approach to defect diagnosis in rotary machines and machine components, which enhances the ability of the continuous wavelet transform in feature extraction from vibration signals. Specifically, the energy content of the wavelet coefficients of vibration signal measured on rolling bearings has been evaluated for selecting appropriate base wavelet and decomposition scale such that identification of defect-induced signal features is significantly improved. Through subsequent envelope spectral analysis of the extracted signal features, the location of structural defect in the bearing being monitored can be identified. An experimental study performed on two ball bearings has shown that the developed approach is more effective in diagnosing bearing defects than using the traditional techniques.