Transferable adaptive channel attention module for unsupervised cross-domain fault diagnosis

•A novel TACAM is proposed for cross-domain fault diagnosis of rotating machinery.•Shared features are differentially calibrated based on transferability.•The AS-FGS provides better generalizability for domain adaptation model.•Significant mitigation of negative transfer. Domain adaptation methods a...

Full description

Saved in:
Bibliographic Details
Published in:Reliability engineering & system safety 2022-10, Vol.226, p.108684, Article 108684
Main Authors: Shi, Yaowei, Deng, Aidong, Deng, Minqiang, Xu, Meng, Liu, Yang, Ding, Xue, Li, Jing
Format: Article
Language:English
Subjects:
Adaptation
Bells
Domain adaptation
Domains
Fault diagnosis
Fault transfer diagnosis
Feature extraction
Feature maps
Group size
Model accuracy
Modules
Reliability engineering
Rotating machinery
Shared features
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•A novel TACAM is proposed for cross-domain fault diagnosis of rotating machinery.•Shared features are differentially calibrated based on transferability.•The AS-FGS provides better generalizability for domain adaptation model.•Significant mitigation of negative transfer. Domain adaptation methods are widely applied to unsupervised cross-domain fault diagnosis. However, the existing studies always treat the extracted features equally and thus cannot effectively tackle the negative transfer caused by those non-transferable features. Besides, complex actual diagnosis scenarios impose higher generalization performance requirements on traditional domain adaptation models. Given all this, we develop a transferable adaptive channel attention module to enhance the positive transfer and improve models' performance. As a practical plug-and-play component, it can be universally applicable to any one of most domain adaptation models with different network structures. To actively guide domain adaptation, the transferable adaptive channel attention module continuously recalibrates the feature maps based on their transferability during training to improve shared features' domain-invariance and category-discriminability. Moreover, by establishing adaptive selection of feature group size and third-order statistical moment matching strategies, the effectiveness and broad applicability of the proposed module are further improved. Without bells and whistles, the results of two transfer diagnosis cases demonstrate the advantages of the transferable adaptive channel attention module for improving various domain adaptation models' accuracy and generalization performance.
ISSN:0951-8320
1879-0836
DOI:10.1016/j.ress.2022.108684