Bearing fault diagnosis method and system based on multi-scale information fusion

Abstract

The invention discloses a bearing fault diagnosis method and system based on multi-scale information fusion. The method comprises the steps that a vibration signal and a torque signal of a bearing tobe subjected to fault diagnosis are acquired; fourier transform is carried out on the obtained vibration signal and torque signal of the bearing subjected to fault diagnosis; and inputting the vibration signal and the torque signal of the bearing subjected to fault diagnosis obtained after Fourier transform into the multi-scale information fusion fault diagnosis model, and outputting the fault type of the bearing to be subjected to fault diagnosis. The network structure provided by the invention can effectively extract complementary fault features in the bearing vibration signal and the torquesignal, and improves the accuracy of fault diagnosis to a great extent.

Description

technical field [0001] The present disclosure relates to the technical field of bearing fault diagnosis, in particular to a bearing fault diagnosis method and system based on multi-scale information fusion. Background technique [0002] The statements in this section merely mention background art related to the present disclosure and do not necessarily constitute prior art. [0003] With the continuous development of intelligent manufacturing, industrial systems are becoming more and more intelligent, and at the same time becoming more and more complex, and the losses caused by equipment damage are also increasing. Early fault detection can not only eliminate the faults before causing huge economic losses, but also avoid major safety accidents. However, due to the complexity and nonlinearity of industrial systems, it is difficult to establish accurate mathematical models. Due to the rapid development of information technology, a large amount of operating data has been gene...

AI Technical Summary

Problems solved by technology

In addition, the feature extraction network and classifier are designed separately, which consumes a lot of time and cannot achieve global optimization

[0006] 2) Most of these methods belong to the shallow structure, and it is difficult to learn effective feature representation and nonlinear mapping relationship of complex systems

However, in complex industrial systems, it is difficult to obtain complete fault information. Using a single signal source will lead to incomplete fault features extracted from the signal, and poor generalization ability of the network.

[0011] 2) Single network structure

In order to improve the performance of fault diagnosis, many studies only focus on increasing the depth of the network, which not only cannot extract the multi-scale fault features in the signal, but also leads to the phenomenon of gradient disappearance, which makes it difficult to update the parameters and brings great difficulties to the training of the network. big obstacle

Images