Evaluation of Rolling Bearing Performance Degradation Based on PCA-SVDD

Aiming at the problem that it is difficult to detect the early weak faults of rolling bearing in time, a rolling bearing performance degradation evaluation model based on principal component analysis (PCA) and support vector data description (SVDD) was proposed. PCA method was used to weighted fusion of the characteristic indexes of rolling bearing vibration signal in time domain and frequency domain, and a comprehensive characteristic index which can effectively and comprehensively describe the operation status of rolling bearing was constructed. The comprehensive characteristic indexes of normal samples were input into the SVDD model to complete the construction of evaluation model. The occurrence time of minor fault was determined by setting health alarm threshold, and the whole life test data of the rolling bearing was used for verification. The results show that compared with the SVDD model that the kurtosis index and the root mean square value as the characteristic index input, the evaluation model can detect the occurrence of early weak faults of rolling bearing earlier, and can describe the overall degradation of rolling bearing more accurately.