Shuliu Wu

Shuliu Wu

Auto-generated profile, based on publicly available information

Shuliu Wu

School of Computer Science and Technology, Guangdong University of Technology (GDUT), Guangzhou, China

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 February 2025 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
JZJian Zhu
Jian Zhu
SWShuliu Wu
Shuliu Wu
YXYutang Xiao
Yutang Xiao
BWBoyu Wang
Boyu Wang
RCRuichu Cai
Ruichu Cai
Recently, domain generalization (DG) methods have been actively researched for complex industrial fault diagnosis, which aims to learn generalized representations from historical working conditions to build a diagnosis model that can perform well on unseen working conditions. However, these methods ignore the interactions between monitoring variables, which may fail to learn feature representation with topological structure in non-Eudidean space. In addition, these methods assume the same label distribution across historical and unseen working conditions, which is generally challenging in practice, as the probability of faults varies across different working conditions. This label shift problem can negatively impact the generalization performance. To address these issues, a novel dual-contrastive multi-view graph attention network (DMGAT) is proposed in this article. Specifically, a multi-view graph attention network is designed to explore the intrinsic topological structure of the data, which learns an optimal graph structure that best serves DG by integrating both graph learning and graph convolution in a unified network architecture. In addition, a novel dual-weighted contrastive learning strategy is developed. Intra-domain contrastive learning facilitates the extraction of expressive node features, while inter-domain contrastive learning simultaneously considers the alignment and separation of semantic probability distributions to extract shared feature representations for multiple source domains under both domain and label shift. Furthermore, a label sampling probability is used to weight the inter-domain contrastive loss and the source domain classification loss, to encourage the model to learn from minor classes in fault diagnosis. Experiments on two cases demonstrate the superiority of the proposed method.