Fault diagnosis of SKF-6205 bearing with modified empirical mode decomposition

Rolling element bearings are broadly used in the rotating machines to support static and dynamic loads. In this research, the advance signal processing techniques are use for processing of bearing fault signals. Experimental validation with genuine vibration signals calculated from bearings with seeded defects on bearing elements. The model-based fault diagnosis method has attempted to diagnose incipient fault detection and classification of bearing with data driven approach. Feature extraction technique has been developed with hybrid signal processing technique based on the band pass filter nature of Empirical mode decomposition (EMD), the resonant frequency bands have owed in specific mono component signals called Intrinsic Mode Functions (IMFs). Synchronized resonant frequency band (SRFB) is obtained on based of orthogonal real wavelet using spectral kurtosis. Biorthogonal 5.5 wavelet, a real wavelet has been selected as a suitable wavelet for WPT based on “Maximum Relative Wavelet Energy” and “Maximum Energy-to-Shannon entropy ratio”. Three, Feature extraction techniques like continuous wavelet transform (CWT), wavelet packet transform (WPT) and modified Hilbert Huang Transforms (HHT) are compared on bases of their classification accuracy with different classification algorithm and filters. Various supervised classifiers have been compared through a common platform of Waikato Environment for Knowledge Analysis (WEKA) and concluded the k- nearest neighbour (KNN) as an effective available classifier for rolling element bearing. Further, asymmetric proximity function based KNN (APF-KNN) has out performs with modified feature selection criteria. Feature extraction through modified HHT and APFKNN has been future as a most effectual fault classification method. For testing any unknown data, simplified method has been demonstrated, which make the proposed data driven approach more realistic, faster and automated.