RESEARCH PAPER
Remaining Useful Life Prediction Based on Cross-Temporal Dynamic Graph Convolutional Network
More details
Hide details
1
School of Automation, Guangdong University of Petrochemical Technology, China
2
School of Information and Control Engineering, Jilin Institute of Chemical Technology, China
Submission date: 2024-10-26
Final revision date: 2025-01-30
Acceptance date: 2025-03-23
Online publication date: 2025-03-27
Publication date: 2025-03-27
Corresponding author
Jixin Liu
School of Automation, Guangdong University of Petrochemical Technology, 2nd Guandu Road, 525000, Maoming, China
HIGHLIGHTS
- A GNN model for predicting RUL using multi-sensor data is proposed
- A dynamic graph generation method without a priori knowledge is designed
- A decay graph based on spatio-temporal distance is designed
KEYWORDS
TOPICS
ABSTRACT
Taking advantage of deep learning (DL) to extract hidden degradation signals from machinery monitoring data has led to significant advancements in predicting equipment's remaining useful life (RUL). However, existing methods that use similarity and adaptive adjacency matrices to construct graphs fail to reflect sensor relationships accurately. This article presents a cross-temporal dynamic graph convolutional network (CTDGCN) for RUL prediction to address this issue. The CTDGCN combines cross-temporal modeling with dynamic spatio-temporal graph construction, collecting multi-sensor time series signals to create dynamic graph embeddings. By constructing a cross-temporal sensor network, temporal and spatial features are extracted to design a decay graph based on temporal distance. This model utilizes decay and cross-temporal pooling layers to aggregate information and capture complicated spatio-temporal dependencies. Studies conducted on two cases indicate that the CTDGCN model significantly outperforms existing models in RUL prediction tasks.