Search for Author, Title, Keyword
RESEARCH PAPER
Multi-Connected Temporal Encoding Graph Neural Network for Complex Industrial Fault Diagnosis
,
 
,
 
,
 
 
 
 
More details
Hide details
1
Northeastern University at Qinhuangdao, China
 
2
Hebei Key Laboratory of Micro-Nano Precision Optical Sensing and Measurement Technology, China
 
3
Hebei Key Laboratory of Marine Perception Network and Data Processing, China.
 
 
Submission date: 2025-03-22
 
 
Final revision date: 2025-06-09
 
 
Acceptance date: 2025-07-25
 
 
Online publication date: 2025-08-02
 
 
Publication date: 2025-08-02
 
 
Corresponding author
Qiang Zhao   

Northeastern University at Qinhuangdao, China
 
 
 
HIGHLIGHTS
  • MCTEGNN: A novel graph neural network for complex industrial fault diagnosis.
  • Multi-connected graph captures comprehensive spatial-temporal dependencies.
  • Moving-pooling GNN effectively extracts local spatial-temporal features.
  • Decay matrix enhances graph accuracy by considering temporal distances.
  • Superior performance on TE, TFF and BF dataset validates the model's effectiveness.
KEYWORDS
TOPICS
ABSTRACT
In modern industry, the complex system scale is large and the process variables are highly coupled. Traditional fault diagnosis methods are inherently challenged in their ability to effectively integrate information, leading to inappropriate feature representations and inaccurate diagnosis outcomes. To address these issues, this paper proposes a Multi-Connected Temporal Encoding Graph Neural Network (MCTEGNN). For multi-connected graph construction, by additionally considering the correlation between different sensors at different timestamps and connecting sensors between all timestamps, a multi-connected graph can be formed to achieve comprehensive dependency modeling. Multi-connected graph convolution captures local dependencies by utilizing moving windows and time pooling, and then learns advanced features to use the moving pool GNN. The proposed method improves the problem of incomplete modeling caused by low efficiency in capturing data relationships. The experimental results on the three dataset demonstrate the effectiveness of the proposed MCTEGNN for faults diagnosis
ACKNOWLEDGEMENTS
This work was supported by National Natural Science Foundation of China (U21A20475), Natural Science Foundation of Hebei Province of China(E2022501017, F2020501040), Research Fund from the State Key Laboratory of Rolling and Automation, Northeastern University(2021RALKFKT007), Fundamental Research Funds for the Central Universities (N2223001).
eISSN:2956-3860
ISSN:1507-2711
Journals System - logo
Scroll to top