Degradation assessment of rolling bearing towards safety based on random matrix single ring machine learning

Publication date: October 2019Source: Safety Science, Volume 118Author(s): Guangxian Ni, Jinhai Chen, Heng WangAbstractAiming at problems of feature extraction of monitoring data may lose useful information and different feature extraction methods have great influence on the results in rolling bearing performance degradation assessment. A method which is based on random matrix theory to assess the degradation of rolling bearing is proposed to improve production safety. Firstly, the observation matrix was constructed by the raw data of rolling bearing health monitoring, and the random matrix model of rolling bearing operating states was established by the steps of normalization, singular matrix singular value decomposition and standardization. Then, three performance degradation indicators, the average spectral radius, the maximum eigenvalue, and the number of random points in the inner ring are proposed by constructing the linear eigenvalue statistic of the random matrix, combined with the single ring curve of the bearing operating states, to describe the fluctuation discipline of the random matrix elements and the variation law of the characteristic root distribution, thus characterize the statistical random characteristics of the operating states of the rolling bearing as a whole. Finally, the method was applied by the rolling bearing life test vibration data. And four different operation states of the bearing are selected to build the random matrix model and analysis. The ...
Source: Safety Science - Category: Occupational Health Source Type: research