Multi-feature fusion method

Abstract

The invention relates to the field of rotating machinery fault prediction and health management, in particular to a multi-feature fusion method used in rolling bearing performance degradation evaluation. According to the method, in order to solve the problem of redundancy possibly occurring in multiple features extracted from a mixed domain in rolling bearing performance degradation evaluation, a method for carrying out feature selection by combining similarity analysis based on a Hausdorff distance and a comprehensive evaluation criterion is provided. In the similarity analysis of the features, a Hausdorff distance is adopted, and compared with an Euclidean distance, the Hausdorff distance considers a bidirectional distance in two groups of data, so that the method is more suitable for the similarity analysis of the features, and in addition, 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, and the fusion process considers the characteristics of the rolling bearing degradation features in different degradation stages and also considers the stage tendency of the features. In order to avoid interference of other factors, a feature overlapping tendency calculation method is provided, and the situation that local optimum is caused when the tendency of a long sequence with the large fluctuation amplitude is calculated is avoided.

Description

technical field [0001] The invention relates to the field of fault prediction and health management of rotating machinery, in particular to a multi-feature fusion method used in performance degradation evaluation of rolling bearings. Background technique [0002] With the rapid development of science and technology, modern mechanical equipment has begun to develop in a more intelligent direction, and rotating machinery is widely used in industry. The core components of many manufacturing equipment are rotating machinery. As one of the most widely used parts in rotating machinery, rolling bearings often operate in very complex environments. Once a failure occurs, it will cause huge property losses and may even threaten life safety. 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 resources. The service life is one of the important ...

AI Technical Summary

Problems solved by technology

[0003] Different from the signal feature extraction in fault diagnosis, for the performance degradation characteristics of rolling bearings, continuous feature analysis of the signals is required, and the signals will show strong randomness with the degradation of rolling bearings. Therefore, for the trend of rolling bearing signals However, due to the complexity of rolling bearing vibration signals, this method often leads to inaccurate selection of features and is greatly affected by subjective experience. suitability

Images