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

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.

[1]  Singiresu S Rao,et al.  A Comparative Study of Evidence Theories in the Modeling, Analysis, and Design of Engineering Systems , 2013 .

[2]  A. Kobi,et al.  Fault Diagnosis with Bayesian Networks: Application to the Tennessee Eastman Process , 2006, 2006 IEEE International Conference on Industrial Technology.

[3]  Belkacem Ould Bouamama,et al.  Graphical methods for diagnosis of dynamic systems: Review , 2014, Annu. Rev. Control..

[4]  D. Luenberger.  Observers for multivariable systems , 1966 .

[5]  Bernhard Maschke,et al.  Bond graph modelling for chemical reactors , 2006 .

[6]  Gibaek Lee,et al.  Multiple-Fault Diagnosis of the Tennessee Eastman Process Based on System Decomposition and Dynamic PLS , 2004 .

[7]  Reza Eslamloueyan,et al.  Designing a hierarchical neural network based on fuzzy clustering for fault diagnosis of the Tennessee-Eastman process , 2011, Appl. Soft Comput..

[8]  Steven X. Ding,et al.  Model-based Fault Diagnosis Techniques: Design Schemes, Algorithms, and Tools , 2008 .

[9]  Steven X. Ding,et al.  On observer-based fault detection for nonlinear systems , 2015, Syst. Control. Lett..

[10]  Fred Spiring,et al.  Introduction to Statistical Quality Control , 2007, Technometrics.

[11]  Leo H. Chiang,et al.  Fault diagnosis in chemical processes using Fisher discriminant analysis, discriminant partial least squares, and principal component analysis , 2000 .

[12]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[13]  Belkacem Ould Bouamama,et al.  Model-based Process Supervision: A Bond Graph Approach , 2008 .

[14]  Belkacem Ould Bouamama,et al.  Signed Bond Graph for health monitoring of PEM fuel cell , 2013 .

[15]  Belkacem Ould Bouamama,et al.  Functional and Behavior Models for the Supervision of an Intelligent and Autonomous System , 2011, IEEE Transactions on Automation Science and Engineering.

[16]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part III: Process history based methods , 2003, Comput. Chem. Eng..

[17]  Jianbo Yu,et al.  Local and global principal component analysis for process monitoring , 2012 .

[18]  Rémy Guyonneau,et al.  Model-based approach for fault diagnosis using set-membership formulation , 2016, Eng. Appl. Artif. Intell..

[19]  E. F. Vogel,et al.  A plant-wide industrial process control problem , 1993 .

[20]  Donghua Zhou,et al.  Generalized Reconstruction-Based Contributions for Output-Relevant Fault Diagnosis With Application to the Tennessee Eastman Process , 2011, IEEE Transactions on Control Systems Technology.

[21]  Sylvain Verron,et al.  Diagnostic et surveillance des processus complexes par réseaux bayésiens , 2007 .

[22]  Kaushik Ghosh,et al.  Optimal variable selection for effective statistical process monitoring , 2014, Comput. Chem. Eng..

[23]  Belkacem Ould Bouamama,et al.  Bond graphs for the diagnosis of chemical processes , 2012, Comput. Chem. Eng..

[24]  Forbes T. Brown,et al.  Engineering system dynamics : a unified graph-centered approach , 2006 .

[25]  Abdessamad Kobi,et al.  A Bayesian network dealing with measurements and residuals for system monitoring , 2016 .

[26]  Chen Jing,et al.  SVM and PCA based fault classification approaches for complicated industrial process , 2015, Neurocomputing.

[27]  Sylvain Verron,et al.  Bridging data-driven and model-based approaches for process fault diagnosis and health monitoring: A review of researches and future challenges , 2016, Annu. Rev. Control..

[28]  Jing Li,et al.  Fault detection and isolation of faults in a multivariate process with Bayesian network , 2010 .

[29]  Finn V. Jensen,et al.  Bayesian Networks and Decision Graphs , 2001, Statistics for Engineering and Information Science.

[30]  Torsten Jeinsch,et al.  A Survey of the Application of Basic Data-Driven and Model-Based Methods in Process Monitoring and Fault Diagnosis , 2011 .

[31]  Raghunathan Rengaswamy,et al.  A Signed Directed Graph and Qualitative Trend Analysis-Based Framework for Incipient Fault Diagnosis , 2007 .

[32]  G. Dauphin-Tanguy,et al.  Robust Fault Diagnosis by Using Bond Graph Approach , 2007, IEEE/ASME Transactions on Mechatronics.

[33]  Ping Zhang,et al.  Subspace method aided data-driven design of fault detection and isolation systems , 2009 .

[34]  Marcel Staroswiecki,et al.  Supervision of an industrial steam generator. Part I: Bond graph modelling , 2006 .

[35]  Yang Song,et al.  Parity space-based fault detection for linear discrete time-varying systems with unknown input , 2015, Autom..

[36]  Xiuxi Li,et al.  Nonlinear dynamic principal component analysis for on-line process monitoring and diagnosis , 2000 .

[37]  Mohd Azlan Hussain,et al.  Fault diagnosis of Tennessee Eastman process with multi- scale PCA and ANFIS , 2013 .

[38]  Belkacem Ould Bouamama,et al.  Signed Bond Graph for multiple faults diagnosis , 2014, Eng. Appl. Artif. Intell..

[39]  S. Joe Qin,et al.  Statistical process monitoring: basics and beyond , 2003 .

[40]  Arthur K. Kordon,et al.  Fault diagnosis based on Fisher discriminant analysis and support vector machines , 2004, Comput. Chem. Eng..

[41]  Petr Ekel,et al.  A new fault classification approach applied to Tennessee Eastman benchmark process , 2016, Appl. Soft Comput..

[42]  Tao Chen,et al.  Root cause analysis in multivariate statistical process monitoring: Integrating reconstruction-based multivariate contribution analysis with fuzzy-signed directed graphs , 2014, Comput. Chem. Eng..

[43]  Yew Seng Ng,et al.  Evaluation of decision fusion strategies for effective collaboration among heterogeneous fault diagnostic methods , 2011, Comput. Chem. Eng..

[44]  B. Ould Bouamama,et al.  Modelling and Simulation in Thermal and Chemical Engineering: A Bond Graph Approach , 1999 .

[45]  Rolf Isermann,et al.  Model-based fault-detection and diagnosis - status and applications , 2004, Annu. Rev. Control..

[46]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part I: Quantitative model-based methods , 2003, Comput. Chem. Eng..

[47]  J. Gertler.  Fault detection and isolation using parity relations , 1997 .

[48]  Didier Theilliol,et al.  Fault diagnosis and accommodation of a three-tank system based on analytical redundancy. , 2002, ISA transactions.

[49]  Silvia Joekes,et al.  An improved attribute control chart for monitoring non-conforming proportion in high quality processes , 2013 .

[50]  Ping Zhang,et al.  A comparison study of basic data-driven fault diagnosis and process monitoring methods on the benchmark Tennessee Eastman process , 2012 .

[51]  Abdessamad Kobi,et al.  Fault detection and identification with a new feature selection based on mutual information , 2008 .

[52]  Marcel Staroswiecki,et al.  Conflicts versus analytical redundancy relations: a comparative analysis of the model based diagnosis approach from the artificial intelligence and automatic control perspectives , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[53]  S. J. Qin,et al.  An alternative PLS algorithm for the monitoring of industrial process , 2001, Proceedings of the 2001 American Control Conference. (Cat. No.01CH37148).

[54]  Wolfgang Borutzky,et al.  Bond Graph Methodology: Development and Analysis of Multidisciplinary Dynamic System Models , 2009 .

[55]  Guoqiang Peter Zhang,et al.  Neural networks for classification: a survey , 2000, IEEE Trans. Syst. Man Cybern. Part C.