A New Method of Fault Diagnosis in Rolling Bearings

The rolling bearing plays a crucial role in industry and life, which is widely used in mechanical equipment. Its health will affect the safe operation of the equipment so monitoring the working state of bearings is necessary. The fault feature extraction method based on the combination of complete ensemble and empirical mode decomposition with adaptive noise (CEEMDAN) and fuzzy entropy is divided into three parts. Firstly, the collected vibration signal is decomposed into several intrinsic mode functions (IMF) by CEEMDAN. And then four relatively large modes are selected by using the correlation coefficient. Finally, fuzzy entropies are calculated separately and the results can be made to a fault feature. Support vector machines (SVM) is used to train diagnostic model. The experimental result shows that the method can improve the effect of feature extraction.