Search

Rolling element bearings (REBs) are vital parts of rotating machinery across various industries. For preventing breakdowns and damages during operation, it is crucial to establish appropriate techniques for condition monitoring and fault diagnostics of these bearings. The development of machine learning (ML) brings a new way of diagnosing the fault of rolling element bearings. In the current work, ML models, namely, Support Vector Machine (SVM) and K-Nearest Neighbor (KNN), are used to classify the faults associated with different ball bearing elements. Using open-source Case Western Reserve University (CWRU) bearing data, machine learning classifiers are trained with extracted time-domain and frequency-domain features. The results show that frequency-domain features are more convincing for the training of ML models, and the KNN classifier has a high level of accuracy compared to SVM. [ABSTRACT FROM AUTHOR]

Rolling element bearings are widely employed in rotating machines. The health monitoring and the residual life prediction of bearings are significant to the reliable operation of the equipment. This paper deals with the principle of a time-domain-based residual life prediction method for rolling element bearings. In particular, a quantitative evaluation of bearing degradation is performed by evaluating the sensitivity of the 13 time-domain features. Meanwhile, the optimal feature set is generated through a sensitivity evaluation analysis approach. Next, the max-min normalization and the multiple linear regression (MLR) methods are applied to construct a healthy index. Based on the healthy index, the degradation trajectory is obtained by using the locally weighted scatterplot smoothing (LOWESS) method. Two data sets generated by the outer race fault are used to verify the effectiveness of the proposed method. The experimental results show that the proposed method can realize the residual life prediction of rolling element bearings effectively. [ABSTRACT FROM AUTHOR]