Causal temporal graph attention network for fault diagnosis of chemical processes

doi:10.1016/j.cjche.2024.01.019

摘要/Abstract

摘要： 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: Chemical processes, Safety, Fault diagnosis, Causal discovery, Attention mechanism, Explainability

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.

Key words: Chemical processes, Safety, Fault diagnosis, Causal discovery, Attention mechanism, Explainability

Jiaojiao Luo, Zhehao Jin, Heping Jin, Qian Li, Xu Ji, Yiyang Dai. Causal temporal graph attention network for fault diagnosis of chemical processes[J]. 中国化学工程学报, 2024, 70(6): 20-32.

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.

参考文献

[1] P.D. Christofides, J.F. Davis, N.H. El-Farra, D. Clark, K.R.D. Harris, J.N. Gipson, Smart plant operations: Vision, progress and challenges, AlChE. J. 53 (11) (2007) 2734-2741.
[2] S. Yin, S.X. Ding, X.C. Xie, H. Luo, A review on basic data-driven approaches for industrial process monitoring, IEEE Trans. Ind. Electron. 61 (11) (2014) 6418-6428.
[3] S. Yin, Z.H. Huang, Performance monitoring for vehicle suspension system via fuzzy positivistic C-means clustering based on accelerometer measurements, IEEE/ASME Trans. Mechatron. 20 (5) (2015) 2613-2620.
[4] C. Nan, F. Khan, M.T. Iqbal, Real-time fault diagnosis using knowledge-based expert system, Process. Saf. Environ. Prot. 86 (1) (2008) 55-71.
[5] P.M. Frank, Analytical and qualitative model-based fault diagnosis-A survey and some new results, Eur. J. Contr. 2 (1) (1996) 6-28.
[6] D. Peng, Y. Xu, Q.X. Zhu, Study and application of case-based extension fault diagnosis for chemical process, Chin. J. Chem. Eng. 21 (4) (2013) 366-375.
[7] X.Y. Chen, X.F. Yan, Fault diagnosis in chemical process based on self-organizing map integrated with fisher discriminant analysis, Chin. J. Chem. Eng. 21 (4) (2013) 382-387.
[8] M. Alauddin, F. Khan, S. Imtiaz, S. Ahmed, A bibliometric review and analysis of data-driven fault detection and diagnosis methods for process systems, Ind. Eng. Chem. Res. 57 (32) (2018) 10719-10735.
[9] N. Md Nor, C.R. Che Hassan, M.A. Hussain, A review of data-driven fault detection and diagnosis methods: Applications in chemical process systems, Rev. Chem. Eng. 36 (4) (2020) 513-553.
[10] J.V. Kresta, J.F. MacGregor, T.E. Marlin, Multivariate statistical monitoring of process operating performance, Can. J. Chem. Eng. 69 (1) (1991) 35-47.
[11] L.H. Chiang, E.L. Russell, R.D. Braatz, Fault diagnosis in chemical processes using Fisher discriminant analysis, discriminant partial least squares, and principal component analysis, Chemom. Intell. Lab. Syst. 50 (2) (2000) 243-252.
[12] B. Xiao, Y.G. Li, B. Sun, C.H. Yang, K.K. Huang, H.Q. Zhu, Decentralized PCA modeling based on relevance and redundancy variable selection and its application to large-scale dynamic process monitoring, Process. Saf. Environ. Prot. 151 (2021) 85-100.
[13] J.X. Zhang, W.J. Luo, Y.Y. Dai, Y.M. Yao, Cycle temporal algorithm-based multivariate statistical methods for fault diagnosis in chemical processes, Chin. J. Chem. Eng. 47 (2022) 54-70.
[14] W.D. Tian, Y.J. Ren, Y.X. Dong, S.G. Wang, L.Z. Bu, Fault monitoring based on mutual information feature engineering modeling in chemical process, Chin. J. Chem. Eng. 27 (10) (2019) 2491-2497.
[15] J.M. Lee, S.J. Qin, I.B. Lee, Fault detection of non-linear processes using kernel independent component analysis, Can. J. Chem. Eng. 85 (4) (2007) 526-536.
[16] L.F. Cai, X.M. Tian, S. Chen, A process monitoring method based on noisy independent component analysis, Neurocomputing 127 (2014) 231-246.
[17] C.H. Zhao, F.R. Gao, A nested-loop Fisher discriminant analysis algorithm, Chemom. Intell. Lab. Syst. 146 (2015) 396-406.
[18] L.Y. Jiang, L. Xie, S.Q. Wang, Fault diagnosis for batch processes by improved multi-model fisher discriminant analysis, Chin. J. Chem. Eng. 14 (3) (2006) 343-348.
[19] G. Yang, X.H. Gu, Fault diagnosis of complex chemical processes based on enhanced naive Bayesian method, IEEE Trans. Instrum. Meas. 69 (7) (2020) 4649-4658.
[20] M. Onel, C.A. Kieslich, E.N. Pistikopoulos, A nonlinear support vector machine-based feature selection approach for fault detection and diagnosis: Application to the Tennessee Eastman process, AIChE J. 65 (3) (2019) 992-1005.
[21] S. Mahadevan, S.L. Shah, Fault detection and diagnosis in process data using one-class support vector machines, J. Process. Contr. 19 (10) (2009) 1627-1639.
[22] Y. Mao, Z. Xia, Z. Yin, Y.X. Sun, Z. Wan, Fault diagnosis based on fuzzy support vector machine with parameter tuning and feature selection, Chin. J. Chem. Eng. 15 (2) (2007) 233-239.
[23] G.Z. Wang, J.C. Liu, Y. Li, Fault diagnosis using kNN reconstruction on MRI variables, J. Chemom. 29 (7) (2015) 399-410.
[24] C. Li, R.V. Sanchez, G. Zurita, M. Cerrada, D. Cabrera, R.E. Vasquez, Gearbox fault diagnosis based on deep random forest fusion of acoustic and vibratory signals, Mech. Syst. Signal Process. 76-77 (2016) 283-293.
[25] W.K. Sun, A.R.C. Paiva, P. Xu, A. Sundaram, R.D. Braatz, Fault detection and identification using Bayesian recurrent neural networks, Comput. Chem. Eng. 141 (2020) 106991.
[26] C.Y. Lou, X.S. Li, M.A. Atoui, Bayesian network based on an adaptive threshold scheme for fault detection and classification, Ind. Eng. Chem. Res. 59 (34) (2020) 15155-15164.
[27] Y.Y. Dai, J.S. Zhao, Fault diagnosis of batch chemical processes using a dynamic time warping (DTW)-based artificial immune system, Ind. Eng. Chem. Res. 50 (8) (2011) 4534-4544.
[28] L. Ming, J.S. Zhao, Feature selection for chemical process fault diagnosis by artificial immune systems, Chin. J. Chem. Eng. 26 (8) (2018) 1599-1604.
[29] Z.C. Wei, X. Ji, L. Zhou, Y.G. Dang, Y.Y. Dai, A novel deep learning model based on target transformer for fault diagnosis of chemical process, Process. Saf. Environ. Prot. 167 (2022) 480-492.
[30] L. Deng, Y. Zhang, Y.Y. Dai, X. Ji, L. Zhou, Y.G. Dang, Integrating feature optimization using a dynamic convolutional neural network for chemical process supervised fault classification, Process. Saf. Environ. Prot. 155 (2021) 473-485.
[31] H. Wu, J.S. Zhao, Deep convolutional neural network model based chemical process fault diagnosis, Comput. Chem. Eng. 115 (2018) 185-197.
[32] S.Y. Zhang, K.X. Bi, T. Qiu, Bidirectional recurrent neural network-based chemical process fault diagnosis, Ind. Eng. Chem. Res. 59 (2) (2020) 824-834.
[33] A. Kopbayev, F. Khan, M. Yang, S.Z. Halim, Gas leakage detection using spatial and temporal neural network model, Process. Saf. Environ. Prot. 160 (2022) 968-975.
[34] L. Zhang, Z.H. Song, Q.H. Zhang, Z.P. Peng, Generalized transformer in fault diagnosis of Tennessee Eastman process, Neural Comput. Appl. 34 (11) (2022) 8575-8585.
[35] S.W. Xiong, L. Zhou, Y.Y. Dai, X. Ji, Attention-based long short-term memory fully convolutional network for chemical process fault diagnosis, Chin. J. Chem. Eng. 56 (2023) 1-14.
[36] P. Linardatos, V. Papastefanopoulos, S. Kotsiantis, Explainable AI: A review of machine learning interpretability methods, Entropy 23 (1) (2020) 18.
[37] D.Y. Wu, J.S. Zhao, Process topology convolutional network model for chemical process fault diagnosis, Process. Saf. Environ. Prot. 150 (2021) 93-109.
[38] D.Y. Wu, X.T. Bi, J.S. Zhao, ProTopormer: Toward understandable fault diagnosis combining process topology for chemical processes, Ind. Eng. Chem. Res. 62 (21) (2023) 8350-8361.
[39] M. Vukovic, S. Thalmann, Causal discovery in manufacturing: A structured literature review, J. Manuf. Mater. Process. 6 (1) (2022) 10.
[40] S. Shimizu, P.O. Hoyer, A. Hyvärinen, A. Kerminen, A linear non-gaussian acyclic model for causal discovery, J. Mach. Learn. Res. 7 (2006) 2003-2030.
[41] P.K. Parida, T. Marwala, S. Chakraverty, Altered-LiNGAM (ALiNGAM) for solving nonlinear causal models when data is nonlinear and noisy, Commun. Nonlinear Sci. Numer. Simul. 52 (2017) 190-202.
[42] P. Velickovic, G. Cucurull, A. Casanova, A. Romero, P. Lio, Y. Bengio, Graph attention networks, In: International Conference on Learning Representations, Vancouver, BC, Canada, 2018.
[43] J.B. Yu, Machine health prognostics using the Bayesian-inference-based probabilistic indication and high-order particle filtering framework, J. Sound Vib. 358 (2015) 97-110.
[44] A. Bathelt, N.L. Ricker, M. Jelali, Revision of the Tennessee Eastman process model, IFAC-PapersOnLine 48 (8) (2015) 309-314.
[45] L. Maaten, G.E. Hinton, Visualizing Data using t-SNE, J. Mach. Learn. Res. 9 (2008) 2579-2605.