A Two-Stage Graph Spatiotemporal Model with Domain-Class Alignment for Fault Diagnosis Under Multi-Source Long-Tailed Distributions DOI
Qianwen Cui, Shuilong He, Jinglong Chen

et al.

Knowledge-Based Systems, Journal Year: 2025, Volume and Issue: unknown, P. 113698 - 113698

Published: May 1, 2025

Language: Английский

Health Evaluation Techniques Towards Rotating Machinery: A Systematic Literature Review and Implementation Guideline DOI
Weixiong Jiang, Jun Wu, Yifan Yang

et al.

Reliability Engineering & System Safety, Journal Year: 2025, Volume and Issue: 260, P. 110924 - 110924

Published: Feb. 20, 2025

Language: Английский

Citations

1
Graph Optimization Algorithm Enhanced by Dual-Scale Spectral Features with Contrastive Learning for Robust Bearing Fault Diagnosis DOI
Ying Li, Xiaoping Liu, Junhui Hu

et al.

Knowledge-Based Systems, Journal Year: 2025, Volume and Issue: unknown, P. 113275 - 113275

Published: March 1, 2025

Language: Английский

Citations

0
On cross-attention-based graph neural networks for fault diagnosis using multi-sensor measurement DOI
Zhenxing Ren, Yu Zhou

Structural Health Monitoring, Journal Year: 2025, Volume and Issue: unknown

Published: March 28, 2025

Rotating machinery fault diagnostics has received a lot of attention in recent years. As result, there been an increase research interest rotating machine intelligent detection, especially when using measurement from multi-sensors. However, accurate diagnosis is still challenged based on nonlinear and non-stationary vibration signals. On the other hand, not enough done structural information fusion multi-sensor due to complexity spatial–temporal correlation. This paper explores use signals for diagnostics, method cross-attention-based dual-branch graph neural network (CA-GNN) proposed. First, improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) used decompose Variational then further deconstruct highest-frequency subsequence after its parameters have optimized whale optimization algorithm. Next, we build CA-GNN, which contains two space branches high- low-frequency initially creating multiple sensor data sets. Information across both components can be efficiently fused. Lastly, experimental scenarios are illustrate suggested technique assess viability accuracy diagnosis. Results indicate that proposed diagnose health issues average up 99%, indicating method’s performance fulfill real-world requirements.

Language: Английский

Citations

0
A Two-Stage Graph Spatiotemporal Model with Domain-Class Alignment for Fault Diagnosis Under Multi-Source Long-Tailed Distributions DOI
Qianwen Cui, Shuilong He, Jinglong Chen

et al.

Knowledge-Based Systems, Journal Year: 2025, Volume and Issue: unknown, P. 113698 - 113698

Published: May 1, 2025

Language: Английский

Citations

0