Multi-Level Temporal Graph Networks with Local-Global Fusion for Industrial Fault Diagnosis

2026-04-20

AI Summary

This work addresses the challenge of modeling complex multiscale spatiotemporal dependencies among sensor variables in industrial processes, which exhibit dynamic non-Euclidean structures that conventional graph neural networks struggle to capture effectively, thereby limiting fault diagnosis performance. To overcome this limitation, the authors propose a structure-aware multilevel temporal graph network that constructs dynamic Pearson correlation graphs to characterize inter-variable relationships. The framework integrates LSTM modules for temporal feature extraction with graph convolutional layers to learn spatial dependencies, and introduces a multi-granularity graph pooling mechanism to progressively distill higher-order structural information. This design enables effective fusion of local details and global patterns. Experimental results on the Tennessee Eastman benchmark dataset demonstrate that the proposed method significantly outperforms existing baselines, particularly exhibiting superior diagnostic accuracy under complex fault scenarios.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing

Abstract

Fault detection and diagnosis are critical for the optimal and safe operation of industrial processes. The correlations among sensors often display non-Euclidean structures where graph neural networks (GNNs) are widely used therein. However, for large-scale systems, local, global, and dynamic relations extensively exist among sensors, and traditional GNNs often overlook such complex and multi-level structures for various problems including the fault diagnosis. To address this issue, we propose a structure-aware multi-level temporal graph network with local-global feature fusion for industrial fault diagnosis. First, a correlation graph is dynamically constructed using Pearson correlation coefficients to capture relationships among process variables. Then, temporal features are extracted through long short-term memory (LSTM)-based encoder, whereas the spatial dependencies among sensors are learned by graph convolution layers. A multi-level pooling mechanism is used to gradually coarsen and learn meaningful graph structures, to capture higher-level patterns while keeping important fault related details. Finally, a fusion step is applied to combine both detailed local features and overall global patterns before the final prediction. Experimental evaluations on the Tennessee Eastman process (TEP) demonstrate that the proposed model achieves superior fault diagnosis performance, particularly for complex fault scenarios, outperforming various baseline methods.

Problem

• industrial fault diagnosis
• graph neural networks
• multi-level structures
• sensor correlations
• non-Euclidean data

Innovation

• Multi-level Temporal Graph Networks
• Local-Global Fusion
• Dynamic Graph Construction
• Graph Pooling
• Industrial Fault Diagnosis