Method for predicting remaining service life of rolling bearing based on time-varying Kalman filtering

Abstract

The invention discloses a rolling bearing residual service life prediction method based on time-varying Kalman filtering, and the method can automatically match the characteristics of different degradation stages of a rolling bearing, and respectively builds time-varying Kalman filter models based on a linear function and a quadratic nonlinear function. The degeneration state of the bearing is adaptively judged according to the time-shifting window filtering relative error index factor, a Kalman filter is automatically switched to process monitoring data in different stages, and effective prediction of the remaining service life of the bearing is achieved.

Description

technical field [0001] The invention belongs to the technical fields of mechanical fault prediction, health management and signal processing, and relates to a remaining service life prediction method based on time-varying Kalman filtering. Background technique [0002] The support and transmission parts of mechanical equipment such as bearings, gears, shafts, etc. are key components. Once the part fails, the mechanical equipment will not work normally, and serious safety accidents will occur, which will bring huge losses to production and life. If the fault can be detected as soon as possible, and even the occurrence of the fault can be predicted, it will be more valuable in practice. Since rolling bearings are widely used in rotating machinery and are prone to failure, the research on the prediction of the remaining service life of rolling bearings has received more and more attention. [0003] At present, most of the research is on life prediction technology based on dat...

AI Technical Summary

Problems solved by technology

Finally, the switch Kalman filter method uses three models to filter and estimate the probability of the three models at each calculation point, and the calculation cost is relatively high

Images