Rolling bearing fault diagnosis method and system, computer program and storage medium

Abstract

The invention relates to a rolling bearing fault diagnosis method and system, a computer program and a storage medium, and the method comprises the steps: carrying out the segmentation and two-dimensional stacking on a collected original vibration signal of a rolling bearing so as to obtain a two-dimensional sequence; substituting the two-dimensional sequence into a convolutional neural network branch, performing feature extraction to extract the time-domain features and the space-domain features at the same time; substituting the intercepted nth group of data into a long-short-term memory network branch to obtain data in the same format as the data operated by the convolutional neural network; weighting the data processed by the convolution network branch and the data processed by the long-short term memory network branch by using a parallel structure of a residual network, and substituting the weighted data into a pooling layer to carry out pooling operation; repeating the above steps to construct a network layer of the space-time neural network, constructing a plurality of layers, and substituting the output data into the final full connection layer for calculation; and performing classification by using softmax, and determining whether the rolling bearing has a fault or not and determining a fault type according to a classification result.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis of mechanical equipment, in particular to a method, system, computer program and storage medium for fault diagnosis of rolling bearings. Background technique [0002] Rolling bearings are one of the core components of rotating machinery such as gearboxes and turbomachinery, and their failure will directly affect the stable operation of mechanical equipment. Affected by the working environment, the original vibration signal of the rolling bearing is generally non-stationary and nonlinear, and the signal is often mixed with noise, and the amount of signal data is large, and the signal information contains both spatial domain information and time domain information. Diagnosis poses difficulties. Contents of the invention [0003] In view of the above problems, the object of the present invention is to provide a rolling bearing fault diagnosis method, system, computer program and storage me...

AI Technical Summary

Problems solved by technology

Affected by the working environment, the original vibration signal of the rolling bearing is generally non-stationary and nonlinear, and the signal is often mixed with noise, and the amount of signal data is large, and the signal information contains both spatial domain information and time domain information. Diagnosis presents difficulties

Images