Real-time identification of performance degradation stages of rolling element bearings by RVCFI

Abstract

The rolling element bearing is a critical component, and its fault results in most of the faults in rotary machines. The performance condition monitoring of bearings can improve the safety of equipment and can provide a reasonable maintenance plan at the optimal time. To identify the initial fault time (IFT) and performance degradation stages of a bearing based on the sampling signal from the start to the current time in real time, the monitoring indicator of the initial fault (MIIF) and the monitoring indicator of the degradation stages (MIDS) are constructed. Firstly, multiple features with stable and high robustness are calculated based on the envelope spectrum of the vibration signal. And these features are standardized and integrated by the weighted-sum of multiple standardized features into a fused indicator. Then, the online variation coefficient of the fused indicator and its rate are calculated. Finally, the MIIF and MIDS can be obtained using the variation coefficient and cumulative sum based on the rate of the variation coefficient of the fused indicator, respectively. Meanwhile, the adaptivity and versatility of the multi-resolution singular value decomposition algorithm are also improved. The proposed methods are verified using two public tested data packets. It is shown from the results that the methods are able to efficiently identify the IFT and performance degradation stages of a bearing in a timely manner.