Method for evaluating and predicting performance and life of bearing through multi-feature fusion

Abstract

The invention discloses a method for evaluating and predicting the performance and life of a bearing through multi-feature fusion, and relates to a method for evaluating the performance of the bearing. According to the method, the Hausdorff distance is adopted in the similarity analysis of features, compared with the Euclidean distance, the Hausdorff distance considers the bidirectional distance in two groups of data, so that the method is more suitable for the similarity analysis of features, and a comprehensive evaluation criterion can consider the monotonicity and predictability of the degradation features. Moreover, the selected multiple features are fused, a feature fusion method based on class sensitivity-overlapping tendency is provided, the characteristics of the degradation features of a rolling bearing in different degradation stages are considered in the fusion process, and the staged tendency characteristics of the features are considered at the same time. In order to avoid interference of other factors, an overlapping tendency calculation method is provided when the characteristic tendency is analyzed. The method is used for performance degradation evaluation and residual life prediction of a rolling bearing, improves the accuracy of a residual life prediction result of the rolling bearing, and has good universality.

Description

technical field [0001] The invention relates to a method for evaluating bearing performance, in particular to a method for multi-feature fusion evaluation and prediction of bearing performance life. Background technique [0002] Rolling bearings are one of the most important parts of rotating machinery, and their operating conditions have a very important impact on the entire equipment. Once a failure occurs, it will affect the production efficiency of the equipment, causing property losses and even casualties. The service life is one of the important indicators to measure the performance of rolling bearings, and it has great discreteness. Even under the same batch and the same working conditions, the difference between the minimum life and the maximum life can reach dozens of times. When the rolling bearing fails, the existing treatment method is generally replacement and refurbishment, which will increase the maintenance cost of the equipment and cause unnecessary waste of...

AI Technical Summary

Problems solved by technology

At present, some related research methods are not mature enough, and artificial feature selection often leads to inaccurate feature selection and is greatly affected by subjective experience, lacking universality.

At the same time, the progressive characteristics of rolling bearing degradation characteristics in the whole life cycle have not been fully considered

Images