Toward Adaptive and Interpretable Process Monitoring: Incremental Variational Graph Attention Autoencoder With Probabilistic Inference

• Published in: IEEE transactions on cybernetics Vol. 55; no. 9; pp. 4114 - 4127
• Main Authors: Lv, Mingjie, Li, Yonggang, Gao, Huanzhi, Sun, Bei, Yang, Chunhua, Gui, Weihua
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.09.2025
• Subjects: Adaptation models; Adaptive and interpretable process monitoring; Autoencoders; Bayes methods; Bayesian regularized self-organizing map (BSOM); causal discovery; Data models; Incremental learning; Probabilistic logic; Process monitoring; Real-time systems; Representation learning; Self-organizing feature maps; variational graph attention autoencoder with probabilistic inference (VGATEPi)
• ISSN: 2168-2267; 2168-2275; 2168-2275
• DOI: 10.1109/TCYB.2025.3583035

Complex industrial processes exhibit typical nonstationarity due to frequently fluctuating material flows and complex control loops. This poses three challenges for trustworthy process monitoring, including data drift, coordination of old and new knowledge, and interpretability. In this study, the adaptive and interpretable process monitoring problem is formulated as an online updating strategy and the spatial topology structure representation learning process monitoring problem. An incremental variational graph attention autoencoder with probabilistic inference framework is proposed, which aims to effectively learn continuously from dynamically changing industrial data to make interpretable monitoring results. First, an incremental learning strategy based on the Bayesian regularized self-organizing map is presented, which can distinguish between real faults and time-varying changes. Once normal samples are encountered, the itself and downstream model are elegantly updated with a dynamic down-sampling replay strategy without leading to catastrophic forgetting. Subsequently, a variational graph attention autoencoder with probabilistic inference is proposed, which endows interpretable spatial structural relationships through priors and effectively captures the variability of spatial latent representations suitable for nonstationary processes. Then, an incremental variational Bayesian inference is introduced to calculate the adaptive thresholds to adapt the system. In addition, an anomaly-aware graph attention localization mechanism is provided to localize fault root causes and propagation paths. Finally, the effectiveness of the proposed method is validated through two industrial applications. The results demonstrate that the proposed method can significantly enhance the performance of process monitoring, especially for reducing the false alarm rate (FAR) in process monitoring schemes. Moreover, it offers interpretable causal relationships among faults.