Details
| Original language | English |
|---|---|
| Article number | 110684 |
| Journal | Reliability Engineering and System Safety |
| Volume | 255 |
| Early online date | 26 Nov 2024 |
| Publication status | Published - Mar 2025 |
Abstract
In recent years, unsupervised domain adaptation (UDA) has gained widespread application in addressing intelligent fault diagnosis under variable operating conditions. However, how to effectively model data structure information and integrate it into UDA has hindered the application of intelligent fault diagnosis in the industry. To solve this issue, a multi-scale and multi-structure information-embedded unsupervised graph transfer network for fault diagnosis is proposed. Specifically, a novel node feature extractor is first designed for feature embedding. To better fuse multi-scale information and obtain more effective features, a multi-scale convolutional layer and a hybrid attention module are utilized. Secondly, an adaptive similarity graph-constructing method based on the inner-product kernel is adopted to convert the node features into graph data. Next, the graph neural network (GNN) is introduced to obtain graph-structured information. Finally, a joint domain adaptation module is designed to cope with the covariance drift problem in cross-domain fault diagnosis. The proposed method exhibited state-of-the-art performance in the experiments of three case studies.
Keywords
- Graph neural networks, Intelligent fault diagnosis, Transfer learning, Unsupervised domain adaptation, Variable operating conditions
ASJC Scopus subject areas
- Engineering(all)
- Safety, Risk, Reliability and Quality
- Engineering(all)
- Industrial and Manufacturing Engineering
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Reliability Engineering and System Safety, Vol. 255, 110684, 03.2025.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Unsupervised graph transfer network with hybrid attention mechanism for fault diagnosis under variable operating conditions
AU - Lei, Zihao
AU - Tian, Feiyu
AU - Su, Yu
AU - Wen, Guangrui
AU - Feng, Ke
AU - Chen, Xuefeng
AU - Beer, Michael
AU - Yang, Chunsheng
PY - 2025/3
Y1 - 2025/3
N2 - In recent years, unsupervised domain adaptation (UDA) has gained widespread application in addressing intelligent fault diagnosis under variable operating conditions. However, how to effectively model data structure information and integrate it into UDA has hindered the application of intelligent fault diagnosis in the industry. To solve this issue, a multi-scale and multi-structure information-embedded unsupervised graph transfer network for fault diagnosis is proposed. Specifically, a novel node feature extractor is first designed for feature embedding. To better fuse multi-scale information and obtain more effective features, a multi-scale convolutional layer and a hybrid attention module are utilized. Secondly, an adaptive similarity graph-constructing method based on the inner-product kernel is adopted to convert the node features into graph data. Next, the graph neural network (GNN) is introduced to obtain graph-structured information. Finally, a joint domain adaptation module is designed to cope with the covariance drift problem in cross-domain fault diagnosis. The proposed method exhibited state-of-the-art performance in the experiments of three case studies.
AB - In recent years, unsupervised domain adaptation (UDA) has gained widespread application in addressing intelligent fault diagnosis under variable operating conditions. However, how to effectively model data structure information and integrate it into UDA has hindered the application of intelligent fault diagnosis in the industry. To solve this issue, a multi-scale and multi-structure information-embedded unsupervised graph transfer network for fault diagnosis is proposed. Specifically, a novel node feature extractor is first designed for feature embedding. To better fuse multi-scale information and obtain more effective features, a multi-scale convolutional layer and a hybrid attention module are utilized. Secondly, an adaptive similarity graph-constructing method based on the inner-product kernel is adopted to convert the node features into graph data. Next, the graph neural network (GNN) is introduced to obtain graph-structured information. Finally, a joint domain adaptation module is designed to cope with the covariance drift problem in cross-domain fault diagnosis. The proposed method exhibited state-of-the-art performance in the experiments of three case studies.
KW - Graph neural networks
KW - Intelligent fault diagnosis
KW - Transfer learning
KW - Unsupervised domain adaptation
KW - Variable operating conditions
UR - http://www.scopus.com/inward/record.url?scp=85210534873&partnerID=8YFLogxK
U2 - 10.1016/j.ress.2024.110684
DO - 10.1016/j.ress.2024.110684
M3 - Article
VL - 255
JO - Reliability Engineering and System Safety
JF - Reliability Engineering and System Safety
SN - 0951-8320
M1 - 110684
ER -