An attention‐enhanced graph isomorphism network for chemical processes fault diagnosis
The Canadian Journal of Chemical Engineering · 31.05.2026
DOI: 10.1002/cjce.70456 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Canadian Journal of Chemical Engineering, online erschienen am 31.05.2026. Verfasst von Yan Chen und 6 weiteren Autor:innen. Die Arbeit nennt 17 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Fault diagnosis in chemical processes remains a challenging task due to strong variable coupling, complex nonlinear dynamics, and distributed fault‐related variations across the processes. To address these issues, this paper proposes an attention‐enhanced graph isomorphism network (AGIN) for chemical process fault diagnosis. Compared with conventional graph neural networks (GNNs), the proposed method alleviates the issues of over‐smoothed neighbourhood aggregation, enables adaptive interaction weighting, and enhances nonlinear representation capability. Specifically, a sum‐based graph isomorphism aggregation branch is introduced to preserve the structural diversity of neighbourhood feature distributions and improve sensitivity to subtle fault patterns. In parallel, a multi‐head graph attention branch is employed to adaptively capture heterogeneous interaction strengths among neighbouring samples. The outputs of the two branches are fused via residual addition and further refined by a channel attention mechanism, while multilayer perceptron‐based nonlinear transformation is adopted to enhance representation capability for complex process dynamics. Moreover, instead of introducing an additional sequence encoder, temporal dependencies are implicitly captured through message passing on temporally constructed neighbourhood graphs. Experimental results on two representative chemical process benchmarks, namely the continuous stirred tank reactor (CSTR) system and the three‐phase flow separation (TFF) process, demonstrate that AGIN consistently achieves superior diagnostic performance and learns more discriminative fault representations than competing methods.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Chen, Y., Wang, X., Yuan, Y., Ge, Z., Fang, G., Mei, Y., & Liu, Y. (2026). An attention‐enhanced graph isomorphism network for chemical processes fault diagnosis. The Canadian Journal of Chemical Engineering. https://doi.org/10.1002/cjce.70456
Vancouver
Chen Y, Wang X, Yuan Y, Ge Z, Fang G, Mei Y, et al. An attention‐enhanced graph isomorphism network for chemical processes fault diagnosis. The Canadian Journal of Chemical Engineering. 2026. doi:10.1002/cjce.70456
BibTeX
@article{Chen2026,
author = {Chen, Yan and Wang, Xiaoming and Yuan, Yating and Ge, Zhenjun and Fang, Gang and Mei, Yiduo and Liu, Yiqi},
title = {An attention‐enhanced graph isomorphism network for chemical processes fault diagnosis},
journal = {The Canadian Journal of Chemical Engineering},
year = {2026},
doi = {10.1002/cjce.70456}
}
EUVIMED