A neural network-based bearing health status assessment method and device

Abstract

The present invention relates to the technical field of fault diagnosis, in particular to a neural network-based bearing health status evaluation method and device, firstly obtain training data, the training data is historical data representing the vibration signal of the bearing, and extract the characteristics of the training data Value and the fault type corresponding to the eigenvalue, then determine the preferred dimensionality reduction training data of the training data, and then calculate the mean value and covariance matrix corresponding to each fault type in the preferred dimensionality reduction training data, by receiving in real time performing dimensionality reduction on test data to obtain dimensionality reduction test data, calculating probability values ​​of the dimensionality reduction data under each fault type according to the mean value and covariance matrix, and using the fault type with the largest probability value as the fault type for bearing fault diagnosis, The invention improves the online prediction rate of bearing fault diagnosis.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis, in particular to a neural network-based bearing health status evaluation method and device. Background technique [0002] As an emerging comprehensive marginal subject, bearing fault diagnosis technology has initially formed a relatively complete subject system. As far as its technical means are concerned, vibration diagnosis technology has become the mainstream technology of bearing fault diagnosis. The rapid progress of computer technology and signal information processing technology has greatly promoted the development of bearing fault diagnosis and monitoring technology in a scientific and practical direction. [0003] However, in the current field of bearing fault diagnosis, there are often large-scale concurrent data, which brings great challenges to the real-time requirements of fault diagnosis, and it is urgent to improve the online prediction rate of bearing fault diagnosis. C...

AI Technical Summary

Problems solved by technology

[0003] However, in the current field of bearing fault diagnosis, there are often large-scale concurrent data, which brings great challenges to the real-time requirements of fault diagnosis, and it is urgent to improve the online prediction rate of bearing fault diagnosis

Images