Causal Graph Spatial-Temporal Autoencoder for Reliable and Interpretable Process Monitoring.

2026-02-03

IEEE Transactions on Neural Networks and Learning Systems

AI Summary

This work proposes a Causal Graph Spatio-Temporal Autoencoder (CGSTAE) to address the inadequate modeling of dynamic variable relationships and causal structure identification in industrial process monitoring. The method integrates a spatial self-attention mechanism to learn a dynamic correlation graph among process variables and employs a three-step algorithm grounded in the principle of causal invariance to extract a stable causal structure. This causal graph is then incorporated into a graph convolutional LSTM-based spatio-temporal autoencoder to achieve high-fidelity time-series reconstruction. Experimental results on the Tennessee Eastman process benchmark and real-world air separation unit data demonstrate that CGSTAE significantly improves fault detection accuracy, model generalization, and interpretability compared to existing approaches.

Technology Category

• Machine Learning: Causal Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Reasoning under Uncertainty: Causality

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in 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
• Web Mining and Content Analysis: Models for Web evolution

Abstract

To improve the reliability and interpretability of industrial process monitoring, this article proposes a causal graph spatial-temporal autoencoder (CGSTAE). The network architecture of CGSTAE combines two components: a correlation graph structure learning module based on spatial self-attention mechanism (SSAM) and a spatial-temporal encoder-decoder module utilizing graph convolutional long short-term memory (GCLSTM). The SSAM learns correlation graphs by capturing dynamic relationships between variables, while a novel three-step causal graph structure learning algorithm is introduced to derive a causal graph from these correlation graphs. The algorithm leverages a reverse perspective of causal invariance principle to uncover the invariant causal graph from varying correlations. The spatial-temporal encoder-decoder, built with GCLSTM units, reconstructs time series process data within a sequence-to-sequence framework. The proposed CGSTAE enables effective process monitoring and fault detection through two statistics in the feature space and residual space. Finally, we validate the effectiveness of CGSTAE in process monitoring through the Tennessee Eastman process (TEP) and a real-world air separation process (ASP).

Problem

• process monitoring
• reliability
• interpretability
• causal graph
• industrial process

Innovation

• Causal Graph Learning
• Spatial-Temporal Autoencoder
• Graph Convolutional LSTM
• Causal Invariance
• Process Monitoring