Shaft temperature change model construction method and module, bearing health monitoring method and system

Abstract

The invention provides a shaft temperature change model construction method and module, a bearing health monitoring method and system. The model construction method comprises step 1, grouping shaft temperature data to obtain a shaft temperature matrix, and setting a weight matrix; step 2, constructing a model temperature array by using the weight matrix and the shaft temperature matrix; step 3, updating the weight matrix by using the shaft temperature matrix and the model temperature array, returning to step 2, and updating the model temperature array according to the updated weight matrix; and step 4, judging whether shaft temperature data changes of the model temperature array are all smaller than a change threshold; when a shaft temperature data change not smaller than the change threshold exists, returning to step 3, cyclically updating the weight matrix and the model temperature array, till the shaft temperature data changes in the model temperature array are all smaller than thechange threshold; and when the shaft temperature data changes are all smaller than the change threshold, constructing a shaft temperature change model using the weight matrix in the model temperaturearray as a final weight matrix.

Description

technical field [0001] The invention relates to the technical field of mechanical fault prediction, and in particular to a shaft temperature change model construction method, a shaft temperature change model construction module, a bearing health monitoring method and a bearing health monitoring system. Background technique [0002] Failure prediction and health management PHM (Prognostics and Health Management) technology originated in the US Air Force. With the continuous development of technology, this technology has also been popularized to other complex equipment. In recent years, there have been many related researches. Although these studies focus on the health status of mechanical parts, they are difficult to replicate directly because of the wide variety of application scenarios and components. [0003] The existing early warning of bearing health status mainly adopts shaft temperature early warning and vibration early warning, specifically: [0004] The existing sh...

AI Technical Summary

Problems solved by technology

[0009] (1) The early warning value comes from expert experience, and the data obtained based on experience is only an approximate value, which cannot adapt to different climates, seasons, environments and other factors

For example, the temperature difference between the north and the south of our country is large. If a unified standard is used to judge, the failure rate of the northern train will actually be lower, and there will be safety hazards in it.

[0010] (2) Threshold early warning can only judge whether the current condition of the bearing is healthy or faulty, but cannot judge the degree of wear of the bearing

[0016] (2) The external mechanical interference is large, the shaking of the train itself, and the track change during operation will also occur.

Images