Causal temporal graph attention network for fault diagnosis of chemical processes

Jiaojiao Luo; Zhehao Jin; Heping Jin; Qian Li; Xu Ji; Yiyang Dai

doi:10.1016/j.cjche.2024.01.019

Your Location：

Home >

Browse articles >

Causal temporal graph attention network for fault diagnosis of chemical processes

Updated：2026-01-06

- Causal temporal graph attention network for fault diagnosis of chemical processes
- Chinese Journal of Chemical Engineering Vol. 70, Issue 6, Pages: 20-32(2024)
- Affiliations：
  
  1. School of Chemical Engineering, Sichuan University,Chengdu,China,610065
  2. China Three Gorges Corporation,Beijing,China,100038
- Author bio：
- Funds：
- DOI：10.1016/j.cjche.2024.01.019
  CLC：
- Published：2024
- Accepted：
Scan QR Code
Jiaojiao Luo, Zhehao Jin, Heping Jin, Qian Li, Xu Ji, Yiyang Dai. Causal temporal graph attention network for fault diagnosis of chemical processes[J]. Chinese Journal of Chemical Engineering, 2024, 70(6): 20-32.
DOI：

Jiaojiao Luo, Zhehao Jin, Heping Jin, Qian Li, Xu Ji, Yiyang Dai. Causal temporal graph attention network for fault diagnosis of chemical processes[J]. Chinese Journal of Chemical Engineering, 2024, 70(6): 20-32. DOI： 10.1016/j.cjche.2024.01.019.

摘要

Abstract

Fault detection and diagnosis (FDD) plays a significant role in ensuring the safety and stability of chemical processes. With the development of artificial intelligence (AI) and big data technologies

data-driven approaches with excellent performance are widely used for FDD in chemical processes. However

improved predictive accuracy has often been achieved through increased model complexity

which turns models into black-box methods and causes uncertainty regarding their decisions. In this study

a causal temporal graph attention network (CTGAN) is proposed for fault diagnosis of chemical processes. A chemical causal graph is built by causal inference to represent the propagation path of faults. The attention mechanism and chemical causal graph were combined to help us notice the key variables relating to fault fluctuations. Experiments in the Tennessee Eastman (TE) process and the green ammonia (GA) process showed that CTGAN achieved high performance and good explainability.

关键词

Keywords

references

Views

335

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

Attention-based long short-term memory fully convolutional network for chemical process fault diagnosis

Multi-dimensional key performance indicators construction methodology for the process safety management

From data to insight: Building a knowledge graph for risk analysis of hazardous chemical accidents

Physically-consistent-WGAN based small sample fault diagnosis for industrial processes

Distributed process monitoring based on Kantorovich distance-multiblock variational autoencoder and Bayesian inference

Related Author

Shanwei Xiong

Li Zhou

Gao Zihan

Zhao Dongfeng

Zhang Fuqun

Zhao Kai

Lu Xilei

Wan Lining

Related Institution

College of Environmental and Safety Engineering, Shenyang University of Chemical Technology

College of Mechanical and Electrical Engineering, China University of Petroleum (East China)

College of Chemical Engineering, China University of Petroleum (East China)

School of Chemical Engineering and Technology, Xinjiang University

Xinjiang Uygur Autonomous Region Academy of Safety Science and Technology

⁰