Bearing fault prediction method

Abstract

The invention discloses a bearing fault prediction method, and the method comprises the following steps: S1, extracting a bearing vibration signal feature vector from a bearing vibration signal; S2, deleting the signal interference in the bearing vibration signal feature vector through grey relational analysis, and obtaining a screened bearing vibration signal feature vector; S3, building a prediction model according to the screened bearing vibration signal feature vector, and outputting a fault prediction feature vector; S4, selecting a training sample from the fault prediction feature vector, and constructing a fault discrimination binary tree according to the training sample. Through the improvement of the prediction model, the method improves the adaptability of the prediction model, prevents the old bearing information from causing the old parameters of the prediction model, improves the prediction precision of the prediction model, and improves the recognition precision of a bearing fault.

Description

technical field [0001] The invention relates to the technical field of bearing fault prediction, in particular to a bearing fault prediction method. Background technique [0002] The EMU bogie automatic production line is designed according to the relevant assembly process of the EMU bogie, so as to automatically complete the functions of parts storage, positioning and transportation, assembly station lifting, bogie completion and dimension measurement. After investigation, it is found that after a period of operation, the production line equipment will inevitably break down, causing part or the whole line of the production line to be shut down for inspection, repair and maintenance. On the basis of the original planned maintenance, some unexpected maintenance has been added, which greatly affects the CRRC. The production of transportation equipment brings inconvenience. As the key equipment of the bogie automatic production line, the bearing is usually selected as the obje...

AI Technical Summary

Problems solved by technology

In the existing technology, there is a technology that applies the gray model GM(1,1) to the field of equipment failure prediction, but the prediction model is simply used, and the prediction model has not been improved

[0004] However, the traditional gray model GM (1, 1) development coefficient a and gray action b are one-time and invariant, which makes the prediction model not have good adaptability

That is, the existing prediction model cannot adapt to the new trend of change in the system affected by the latest information due to the continuous vibration of the system equipment into the new disturbance during the whole life cycle of bearing operation. Aging, so there is a problem of low prediction accuracy

[0005] At the same time, in the process of fault pattern recognition for the predicted value of the bearing state characteristics, the traditional support vector machine cannot effectively identify the bearing fault category. The classifier is improved, and it is very easy to misclassify the samples

Images