Unified Health Domain Relation Learning for Train Transmission Systems Fault Detection under Complex Operating Conditions

Z. Chen*, Zhixu Duan*, H.-Z. Huang (* equal contribution)

Structural Health Monitoring (SHM, CAS Q2) 2026

A unified health-domain relation learning approach enhances fault detection under complex operating conditions.

[Paper]

Decoupling Intrinsic Fault Features from Domain Variations via Domain-Attribute Fusion for Unseen-Domain Fault Diagnosis

Zhixu Duan, et al.

Submitted to Advanced Engineering Informatics (AEI, CAS Q1) 2026 Minor Revision

A domain-attribute fusion model decouples intrinsic fault features, improving unseen-domain diagnosis robustness.

Collaborative Teacher-Student Learning: Simulated Domain Attacks for Class-Intrinsic Feature Learning in Multi-Domain Generalized Fault Diagnosis

Zhixu Duan, et al.

Submitted to IEEE Transactions on Industrial Informatics (IEEE TII, CAS Q1)Under Review. 2026

A collaborative teacher-student learning framework enhances multi-domain generalized fault diagnosis.

Reinforcing Cross-Domain Few-Shot Fault Diagnosis of Train Transmission Systems via Reducing Intra-Class and Maximizing Inter-Class Variations

R. Liu, Zhixu Duan, et al.

Submitted to Advanced Engineering Informatics (AEI, CAS Q1)Under Review. 2026

A domain-attribute fusion model decouples intrinsic fault features, improving unseen-domain diagnosis robustness.

Open-Set Fault Diagnosis Using CLIP with Forward-Reverse Reasoning

Z. Chen*, Zhixu Duan*, H.-Z. Huang (* equal contribution)

Submitted to Computers in Industry (COMPUT IND, CAS Q1) 2026 Minor Revision

A CLIP-based forward-reverse reasoning model enable for fault diagnosis.