Detection of Simultaneous Bearing Faults Fusing Cross Correlation With Multikernel SVM

Detection of simultaneous bearing faults for condition monitoring (CM) of bearings using time-domain analysis is quite challenging and open area, particularly in noisy environment. This work presents a new scheme for simultaneous bearing fault detection using vibration signal (VS), in cases where single-point localized bearing fault and multiple-point compound fault (MPCF) coexist. Bearings of a 415-V, 3-kW, three-phase squirrel cage induction motor (SCIM) have been used for data collection, while the loading arrangement is done using a 110-V, 4-kW dc generator connected with a load box and coupled to the motor. A cross correlation (CC)-based time-domain feature extraction approach has been introduced. The neighborhood component analysis (NCA) technique has been applied to the CC-based features to reduce the complexity of the proposed model. Furthermore, the selected features have been fed into a multikernel support vector machine (MKSVM) to classify simultaneous bearing faults. This method has also been tested on signals contaminated with white Gaussian noise to verify reliability in the industrial environment. It is found that with only five features, the proposed model yields 100% classification performance metrics for raw signal (RS) and under noisy environments with a signal-to-noise ratio (SNR) of 20–50 dB for both full load (FL) and no-load (NL) conditions. In contrast, at 10-dB SNR value, performance decreases slightly, still an overall classification performance metric of more than 99% is achieved by this method. Furthermore, this method has enhanced performance when compared to earlier studies with publicly available databases for localized bearing failure identification.