A multi-domain semi-supervised fault diagnosis method and device for axial piston pump bearings

Abstract

The present invention provides a multi-domain semi-supervised fault diagnosis method for axial piston pump bearings, which includes obtaining source domain signals and target domain signals and performing transformation processing to obtain source domain samples and target domain samples; the source domain signal is a certain The vibration signal of known part of the fault information under the working condition; the target domain signal is the vibration signal of the unknown part of the fault information under another working condition; the trained semi-supervised fault diagnosis model is used to process the source domain samples after time-frequency transformation Carry out semi-supervised fault diagnosis in the source domain to obtain all labeled fault samples in the source domain; simultaneously import all labeled fault samples in the source domain and target domain samples after time-frequency transformation processing into the trained multi-target domain migration learning network for each The diagnosis results of all samples are obtained through the fault diagnosis of domain; the diagnosis results include normal, inner ring fault, outer ring fault and rolling element fault. The implementation of the invention can solve the cross-domain problem of existing axial piston pump bearing fault diagnosis.

Description

A multi-domain semi-supervised fault diagnosis method and device for axial piston pump bearing technical field The present invention relates to mechanical equipment fault diagnosis technical field, relate in particular to a kind of multi-domain semi-diagnosis of axial piston pump bearing Supervise fault diagnosis methods and devices. Background technique Axial piston pump plays an important role in industrial applications, with the rapid development of industry, for the axial column The requirements of plug pumps are becoming more and more stringent, and they are required to work for a long time under conditions such as high temperature, high pressure, and high speed. in this way Working for a long time in a difficult working environment can lead to the failure of some key components in the axial piston pump. bearing as one of It is a kind of vulnerable parts, the failure will be very serious, it may cause the entire production line to stop, resulting in economic l...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the embodiments of the present invention is to provide a multi-domain semi-supervised fault diagnosis method for axial piston pump bearings, which can solve the cross-domain problem of existing axial piston pump bearing fault diagnosis

Images