Multi-source-domain variable-working-condition mechanical fault diagnosis method for incomplete category data
The invention relates to a mechanical parameter mode recognition method, in particular to a multi-source-domain variable-working-condition mechanical fault diagnosis method for incomplete category data, which is used for solving the problem that the same fault type is required to be shared between a...
Saved in:
Main Authors | , , , , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
13.01.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention relates to a mechanical parameter mode recognition method, in particular to a multi-source-domain variable-working-condition mechanical fault diagnosis method for incomplete category data, which is used for solving the problem that the same fault type is required to be shared between a source domain and a target domain in the existing fault diagnosis method based on transfer learning, but in an actual scene, the fault diagnosis efficiency is greatly improved. And a complete data set containing all fault categories is difficult to collect on the same working condition or equipment. According to the multi-source-domain variable-working-condition mechanical fault diagnosis method for incomplete category data, a cyclic generative adversarial network is constructed and trained to supplement missing samples in a multi-source-domain sample set; the method further aims at the problem of inconsistent data distribution of a plurality of source domains and a target domain, adopts a multi-source domain adap |
---|---|
Bibliography: | Application Number: CN202211358570 |