An intelligent fault diagnosis system for process plant using a functional HAZOP and DBN integrated methodology

Integration of a functional HAZOP approach with dynamic Bayesian network (DBN) reasoning is presented in this contribution. The presented methodology can unveil early deviations in the fault causal chain on line. A functional HAZOP study is carried out firstly where a functional plant model (i.e., MFM) assists in a goal oriented decomposition of the plant purpose into the means of achieving the purpose. DBN model is then developed based on the functional HAZOP results to provide a probability-based knowledge representation which is appropriate for the modeling of causal processes with uncertainty. An intelligent fault diagnosis system (IFDS) is proposed based on the whole integrated framework, and investigated in a case study of process plants at a petrochemical corporation. The study shows that the IFDS provides a very efficient paradigm for facilitating HAZOP studies and for enabling reasoning to reveal potential causes and/or consequences far away from the site of the deviation online. An integration of functional HAZOP and DBN is presented for fault diagnosis.Functional HAZOP study helps for hazard scenario analysis with means-end concepts.DBN model provides a probability-based knowledge representation with uncertainty.The IFDS is validated with pilot application on a real petrochemical plant.

[1]  Adel Alaeddini,et al.  Using Bayesian networks for root cause analysis in statistical process control , 2011, Expert Syst. Appl..

[2]  Chuei-Tin Chang,et al.  Fault diagnosis with automata generated languages , 2011, Comput. Chem. Eng..

[3]  H. J. Pasman,et al.  A holistic approach to control process safety risks: Possible ways forward , 2013, Reliab. Eng. Syst. Saf..

[4]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part II: Qualitative models and search strategies , 2003, Comput. Chem. Eng..

[5]  Ahmad Khademzadeh,et al.  A new self-diagnosing approach based on petri nets and correlation graphs for fault management in wireless sensor networks , 2013, J. Syst. Archit..

[6]  Anders L. Madsen,et al.  Applications of object-oriented Bayesian networks for condition monitoring, root cause analysis and decision support on operation of complex continuous processes , 2005, Comput. Chem. Eng..

[7]  José Luis de la Mata,et al.  Automating HAZOP studies using D-higraphs , 2012, Comput. Chem. Eng..

[8]  Yu Wang,et al.  Fault propagation behavior study and root cause reasoning with dynamic Bayesian network based framework , 2015 .

[9]  Venkat Venkatasubramanian,et al.  Prognostic and diagnostic monitoring of complex systems for product lifecycle management: Challenges and opportunities , 2005, Comput. Chem. Eng..

[10]  Hossam A. Gabbar,et al.  Simulation-based fault propagation analysis—Application on hydrogen production plant , 2014 .

[11]  Venkat Venkatasubramanian,et al.  Intelligent systems for HAZOP analysis of complex process plants , 2000 .

[12]  Luis Puigjaner,et al.  On-line fault diagnosis system support for reactive scheduling in multipurpose batch chemical plants , 2001 .

[13]  Peter A. Wieringa,et al.  Reasoning with multilevel flow models , 1999 .

[14]  Jie Yu,et al.  Identification of probabilistic graphical network model for root-cause diagnosis in industrial processes , 2014, Comput. Chem. Eng..

[15]  Hossam A. Gabbar,et al.  Improved qualitative fault propagation analysis , 2007 .

[16]  Sten Bay Jørgensen,et al.  A functional HAZOP methodology , 2010, Comput. Chem. Eng..

[17]  Mariarosa Giardina,et al.  Safety study of an LNG regasification plant using an FMECA and HAZOP integrated methodology , 2015 .

[18]  Raghunathan Rengaswamy,et al.  A signed directed graph-based systematic framework for steady-state malfunction diagnosis inside control loops , 2006 .

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

[20]  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..

[21]  Raghunathan Rengaswamy,et al.  Application of signed digraphs-based analysis for fault diagnosis of chemical process flowsheets , 2004, Eng. Appl. Artif. Intell..

[22]  Faisal Khan,et al.  Dynamic safety analysis of process systems by mapping bow-tie into Bayesian network , 2013 .

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

[24]  Stuart J. Russell,et al.  Dynamic bayesian networks: representation, inference and learning , 2002 .

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

[26]  Paul Baybutt,et al.  A critique of the Hazard and Operability (HAZOP) study , 2015 .

[27]  Tao Xia,et al.  SDG multiple fault diagnosis by real-time inverse inference , 2005, Reliab. Eng. Syst. Saf..

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

[29]  Gregory F. Cooper,et al.  A Bayesian method for the induction of probabilistic networks from data , 1992, Machine Learning.

[30]  Morten Lind,et al.  Modeling goals and functions of complex industrial plants , 1994, Appl. Artif. Intell..

[31]  Haibin Yuan,et al.  Network Topology for the Application Research of Electrical Control System Fault Propagation , 2011 .