Memory-based collaborative filtering bearing current damage fault identification method

Abstract

The invention discloses a collaborative filtering bearing current damage fault identification method based on a memory. The method comprises the following steps: 1) constructing a joint scoring matrixof bearing state identification; and 2) calculating a bearing state prediction score of the fault data in the bearing state identification joint score matrix according to the training data in the bearing state identification joint score matrix in combination with various similarity measurement indexes. According to the method, the collaborative filtering recommendation system is applied to faultidentification of the bearing current damage, the method is simple in step and easy to implement, and the fault of the bearing current damage can be effectively identified.

Description

technical field [0001] The invention relates to the field of bearing fault diagnosis, in particular to a memory-based collaborative filtering bearing current damage fault identification method. Background technique [0002] It is the core goal of fault diagnosis to separate the essential features existing in the fault signal from other interference parts, and to mine fault feature values ​​deeply to obtain as much effective feature information as possible from the fault signal. Since the current damage process of the bearing is a slow and complicated process, the signal of the current damage fault is weak and very stable. In order to obtain comprehensive and complete monitoring data, more sensors are often used for the monitoring of the current damage fault, which makes the arrangement of the sensors The density has increased sharply, and the monitoring time has also continued to increase, and the amount of monitoring data faced has shown explosive growth. In addition, ther...

AI Technical Summary

Problems solved by technology

However, the collaborative filtering recommendation system is based on the corresponding scoring matrix. For the identification of the rolling bearing state, there is no specific scoring rule, and the corresponding scoring matrix cannot be established.

Images