Model-based fault detection and diagnosis of complex chemical processes: A case study of the Tennessee Eastman process

Abstract

Fault detection and diagnosis for industrial systems has been an important field of research during the past years. Among these systems, the Tennessee Eastman process is extensively used as a realistic benchmark to test and compare different fault detection and diagnosis strategies. In this context, data-driven approach has been widely applied for fault detection and diagnosis of the Tennessee Eastman process, by exploiting the massive amount of available measurement data. However, only few published works had attempted to deal with the dynamic behavior of the whole system including the mixing zone, circulating pumps, the reactor, the separator, the stripper, and so on, because of the difficulty of modeling physical phenomena that may occur in such complex system. In this article, an accurate model of the Tennessee Eastman process, properly tailored for fault detection and diagnosis purposes, is provided. This model shows better fault detection and diagnosis performances than all the others proposed in the literature and gives better or comparable results with the data-driven approaches. This work uses the bond graph methodology to systematically develop computational and graphical model. This methodology provides a physical understanding of the system and a description of its dynamic behavior. The bond graph model is then used for monitoring purposes by generating formal fault indicators, called residuals, and algorithms for fault detection and diagnosis. Hence, abnormal situations are detected by supervising the residuals’ evolution and faults are isolated using the nature of the violated residuals. Therefore, the dynamic model of the Tennessee Eastman process can now be used as a basis to achieve accurately different analysis through the causal and structural features of the bond graph tool.

Keywords

Fault detection fault diagnosis model-based methods bond graph Tennessee Eastman process

Get full access to this article

View all access options for this article.

References

Venkatasubramanian

Rengaswamy

Kavuri

et al . A review of process fault detection and diagnosis—part III: process history based methods. Comput Chem Eng 2003; 27(3): 327–346.

Venkatasubramanian

Rengaswamy

Yin

et al . A review of process fault detection and diagnosis—part I: quantitative model-based methods. Comput Chem Eng 2003; 27(3): 293–311.

Ding

Zhang

Jeinsch

et al . A survey of the application of basic data-driven and model-based methods in process monitoring and fault diagnosis. IFAC Proc Vol 2011; 44: 12380–12388.

Qin

. Statistical process monitoring: basics and beyond. J Chemometr 2003; 17(8–9): 480–502.

Zhang

. Neural networks for classification: a survey. IEEE T Syst Man Cy C 2000; 30(4): 451–462.

. Local and global principal component analysis for process monitoring. J Process Contr 2012; 22(7): 1358–1373.

Pearl

. Probabilistic reasoning in intelligent systems: networks of plausible inference. Burlington, MA: Morgan Kaufmann, 2014.

Nielsen

. Bayesian networks and decision graphs. New York: Springer, 2007.

Montgomery

. Introduction to statistical quality control. Hoboken, NJ: John Wiley & Sons, 2007.

10.

Joekes

Barbosa

. An improved attribute control chart for monitoring non-conforming proportion in high quality processes. Control Eng Pract 2013; 21(4): 407–412.

11.

Kruger

Wang

Chen

et al . An alternative PLS algorithm for the monitoring of industrial process. In: Proceedings of the 2001 American control conference, vol. 6, Arlington, VA, 25–27 June 2001, pp.4455–4459. New York: IEEE.

12.

Isermann

. Model-based fault-detection and diagnosis—status and applications. Annu Rev Control 2005; 29(1): 71–85.

13.

Ding

. Model-based fault diagnosis techniques: design schemes, algorithms, and tools. Berlin: Springer, 2008.

14.

Paynter

. Analysis and design of engineering systems. Cambridge, MA: MIT Press, 1961.

15.

Ould-Bouamama

El Harabi

Abdelkrim

et al . Bond graphs for the diagnosis of chemical processes. Comput Chem Eng 2012; 36: 301–324.

16.

Chatti

Ould-Bouamama

Gehin

et al . Signed bond graph for multiple faults diagnosis. Eng Appl Artif Intel 2014; 36: 134–147.

17.

Gertler

. Fault detection and isolation using parity relations. Control Eng Pract 1997; 5(5): 653–661.

18.

Zhong

Song

Ding

. Parity space-based fault detection for linear discrete time-varying systems with unknown input. Automatica 2015; 59: 120–126.

19.

Luenberger

. Observers for multivariable systems. IEEE T Automat Contr 1966; 11(2): 190–197.

20.

Yang

Ding

. On observer-based fault detection for nonlinear systems. Syst Control Lett 2015; 82: 18–25.

21.

Tidriri

Chatti

Verron

et al . Bridging data-driven and model-based approaches for process fault diagnosis and health monitoring: a review of researches and future challenges. Annu Rev Control 2016; 42: 63–81.

22.

Theilliol

Noura

Ponsart

. Fault diagnosis and accommodation of a three-tank system based on analytical redundancy. ISA Trans 2002; 41(3): 365–382.

23.

Chatti

Ould-Bouamama

Gehin

et al . Signed bond graph for health monitoring of PEM fuel cell. In: Proceedings of the 5th international conference of development of fuel cells, Karlsruhe, 16–18 April 2013, pp.1–6.

24.

Chatti

Gehin

Ould-Bouamama

et al . Functional and behavior models for the supervision of an intelligent and autonomous system. IEEE T Autom Sci Eng 2013; 10(2): 431–445.

25.

Ould-Bouamama

Medjaher

Samantaray

et al . Supervision of an industrial steam generator. Part I: bond graph modelling. Control Eng Pract 2006; 14(1): 71–83.

26.

Lee

Han

Yoon

. Multiple-fault diagnosis of the Tennessee Eastman process based on system decomposition and dynamic PLS. Ind Eng Chem Res 2004; 43(25): 8037–8048.

27.

Chiang

Russell

Braatz

. Fault diagnosis in chemical processes using Fisher discriminant analysis, discriminant partial least squares, and principal component analysis. Chemometr Intell Lab 2000; 50(2): 243–252.

28.

Ding

Zhang

Naik

et al . Subspace method aided data-driven design of fault detection and isolation systems. J Process Contr 2009; 19(9): 1496–1510.

29.

Lin

Qian

. Nonlinear dynamic principal component analysis for on-line process monitoring and diagnosis. Comput Chem Eng 2000; 24(2): 423–429.

30.

Alcala

Qin

et al . Generalized reconstruction based contributions for output-relevant fault diagnosis with application to the Tennessee Eastman process. IEEE T Contr Syst T 2011; 19(5): 1114–1127.

31.

Verron

Tiplica

Kobi

. Fault diagnosis with Bayesian networks: application to the Tennessee Eastman process. In: Proceedings of the IEEE international conference on industrial technology (ICIT), Mumbai, India, 15–17 December 2006, pp.98–103. New York: IEEE.

32.

Maurya

Rengaswamy

Venkatasubramanian

. A signed directed graph and qualitative trend analysis-based framework for incipient fault diagnosis. Chem Eng Res Des 2007; 85(10): 1407–1422.

33.

Chiang

Kotanchek

Kordon

. Fault diagnosis based on fisher discriminant analysis and support vector machines. Comput Chem Eng 2004; 28(8): 1389–1401.

34.

Yin

Ding

Haghani

et al . A comparison study of basic data-driven fault diagnosis and process monitoring methods on the benchmark Tennessee Eastman process. J Process Contr 2012; 22(9): 1567–1581.

35.

D’Angelo

Palhares

Camargos Filho

et al . A new fault classification approach applied to Tennessee Eastman benchmark process. Appl Soft Comput 2016; 49: 676–686.

36.

Jing

Hou

. SVM and PCA based fault classification approaches for complicated industrial process. Neurocomputing 2015; 167: 636–642.

37.

Eslamloueyan

. Designing a hierarchical neural network based on fuzzy clustering for fault diagnosis of the Tennessee–Eastman process. Appl Soft Comput 2011; 11(1): 1407–1415.

38.

Ghosh

Ramteke

Srinivasan

. Optimal variable selection for effective statistical process monitoring. Comput Chem Eng 2014; 60: 260–276.

39.

Lau

Ghosh

Hussain

et al . Fault diagnosis of Tennessee Eastman process with multi-scale PCA and ANFIS. Chemometr Intell Lab 2013; 120: 1–14.

40.

Chen

Yang

. Root cause analysis in multivariate statistical process monitoring: Integrating reconstruction-based multivariate contribution analysis with fuzzy-signed directed graphs. Comput Chem Eng 2014; 64: 167–177.

41.

Brown

. Engineering system dynamics: a unified graph-centered approach. Boca Raton, FL: CRC Press, 2006.

42.

Thoma

Ould-Bouamama

. Modelling and simulation in thermal and chemical engineering: a bond graph approach. Berlin: Springer, 2013.

43.

Borutzky

. Bond graph methodology: development and analysis of multidisciplinary dynamic system models. Berlin: Springer, 2009.

44.

Couenne

Jallut

Maschke

et al . Bond graph modelling for chemical reactors. Math Comp Model Dyn 2006; 12(2–3): 159–174.

45.

Ould-Bouamama

Biswas

Loureiro

et al . Graphical methods for diagnosis of dynamic systems: review. Annu Rev Control 2014; 38(2): 199–219.

46.

Samantaray

Ould-Bouamama

. Model-based process supervision: a bond graph approach. Berlin: Springer, 2008.

47.

Chatti

Guyonneau

Hardouin

et al . Model-based approach for fault diagnosis using set-membership formulation. Eng Appl Artif Intel 2016; 55: 307–319.

48.

Downs

Vogel

. A plant-wide industrial process control problem. Comput Chem Eng 1993; 17(3): 245–255.

49.

Verron

Tiplica

. Fault detection and isolation of faults in a multivariate process with Bayesian network. J Process Contr 2010; 20(8): 902–911.

50.

Atoui

Verron

Kobi

. A Bayesian network dealing with measurements and residuals for system monitoring. T I Meas Control 2016; 38(4): 373–384.

51.

Ghosh

Srinivasan

. Evaluation of decision fusion strategies for effective collaboration among heterogeneous fault diagnostic methods. Comput Chem Eng 2011; 35(2): 342–355.

52.

Verron

. Diagnostic et surveillance des processus complexes par réseaux bayésiens. Angers: Université d’Angers, 2007.

53.

Verron

Tiplica

Kobi

. Fault detection and identification with a new feature selection based on mutual information. J Process Contr 2008; 18(5): 479–490.

54.

Cordier

Dague

Levy

et al . Conflicts versus analytical redundancy relations: a comparative analysis of the model based diagnosis approach from the artificial intelligence and automatic control perspectives. IEEE T Syst Man Cy B 2004; 34(5): 2163–2177.

55.

Djeziri

Merzouki

Ould-Bouamama

et al . Robust fault diagnosis by using bond graph approach. IEEE/ASME T Mech 2007; 12(6): 599–611.