Process Safety Assessment Considering Multivariate Non-linear Dependence Among Process Variables

Abstract Nonlinear dependencies among highly correlated variables of a multifaceted process system pose significant challenges for process safety assessment. The copula function is a flexible statistical tool to capture complex dependencies and interactions among process variables in the causation of process faults. An integration of the copula function with the Bayesian network provides a framework to deal with such complex dependence. This study attempts to compare the performance of the copula-based Bayesian network with that of the traditional Bayesian network in predicting failure of a multivariate time dependent process system. Normal and abnormal process data from a small-scale pilot unit were collected to test and verify performances of failure models. Results from analysis of the collected data establish that the performance of copula-based Bayesian network is robust and superior to the performance of traditional Bayesian network. The structural flexibility, consideration of non-linear dependence among variables, uncertainty and stochastic nature of the process model provide the copula-based Bayesian network distinct advantages. This approach can be further tested and implemented as an online process monitoring and risk management tool.

[1]  Faisal Khan,et al.  Correlation and Dependency in Multivariate Process Risk Assessment , 2015 .

[2]  Samir Chatterjee,et al.  e-Risk Management with Insurance: A Framework Using Copula Aided Bayesian Belief Networks , 2006, Proceedings of the 39th Annual Hawaii International Conference on System Sciences (HICSS'06).

[3]  Miroslaw J. Skibniewski,et al.  A dynamic Bayesian network based approach to safety decision support in tunnel construction , 2015, Reliab. Eng. Syst. Saf..

[4]  Youngkyu Jin,et al.  Forecasting Quarterly Inflow to Reservoirs Combining a Copula-Based Bayesian Network Method with Drought Forecasting , 2018 .

[5]  Faisal Khan,et al.  Loss scenario analysis and loss aggregation for process facilities , 2015 .

[6]  M. Tenney,et al.  Introduction to Copulas , 2003 .

[7]  Min Li,et al.  Risk assessment of mine ignition sources using fuzzy Bayesian network , 2019, Process Safety and Environmental Protection.

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

[9]  Yunpeng Ma,et al.  Real-time reliability evaluation methodology based on dynamic Bayesian networks: A case study of a subsea pipe ram BOP system. , 2015, ISA transactions.

[10]  Luigi Portinale,et al.  Improving the analysis of dependable systems by mapping fault trees into Bayesian networks , 2001, Reliab. Eng. Syst. Saf..

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

[12]  Weiwen Peng,et al.  Reliability assessment of complex electromechanical systems under epistemic uncertainty , 2016, Reliab. Eng. Syst. Saf..

[13]  Emiliano A. Valdez,et al.  Understanding Relationships Using Copulas , 1998 .

[14]  Faisal Khan,et al.  Failure probability analysis of the urban buried gas pipelines using Bayesian networks , 2017 .

[15]  Stephen Butt,et al.  Safety and risk analysis of managed pressure drilling operation using Bayesian network , 2015 .

[16]  Nima Khakzad,et al.  Safety analysis in process facilities: Comparison of fault tree and Bayesian network approaches , 2011, Reliab. Eng. Syst. Saf..

[17]  Faisal Khan,et al.  Dynamic hazard identification and scenario mapping using Bayesian network , 2017 .

[18]  Hamid Moradkhani,et al.  A Bayesian Framework for Probabilistic Seasonal Drought Forecasting , 2013 .

[19]  Mary Ann Lundteigen,et al.  A DBN-Based Risk Assessment Model for Prediction and Diagnosis of Offshore Drilling Incidents , 2016, Bayesian Networks in Fault Diagnosis.

[20]  Salim Ahmed,et al.  Multivariate probabilistic safety analysis of process facilities using the Copula Bayesian Network model , 2016, Comput. Chem. Eng..

[21]  Faisal Khan,et al.  Human Error Probability Assessment During Maintenance Activities of Marine Systems , 2017, Safety and health at work.

[22]  R. Clemen,et al.  Correlations and Copulas for Decision and Risk Analysis , 1999 .

[23]  Ming Yang,et al.  An integrated approach for dynamic economic risk assessment of process systems , 2018 .

[24]  Gal Elidan,et al.  Copula Bayesian Networks , 2010, NIPS.

[25]  Faisal Khan,et al.  Design of scenario-based early warning system for process operations , 2015 .

[26]  A. Sebastian,et al.  A Copula-Based Bayesian Network for Modeling Compound Flood Hazard from Riverine and Coastal Interactions at the Catchment Scale: An Application to the Houston Ship Channel, Texas , 2018 .

[27]  Elad Eban,et al.  Dynamic Copula Networks for Modeling Real-valued Time Series , 2013, AISTATS.

[28]  Faisal Khan,et al.  Copula-based Bayesian network model for process system risk assessment , 2019, Process Safety and Environmental Protection.

[29]  Luigi Portinale,et al.  Radyban: A tool for reliability analysis of dynamic fault trees through conversion into dynamic Bayesian networks , 2008, Reliab. Eng. Syst. Saf..

[30]  Min Xie,et al.  Bayesian Network-Based Risk Analysis Methodology: A Case of Atmospheric and Vacuum Distillation Unit , 2018, Bayesian Networks for Reliability Engineering.

[31]  Lamine Mili,et al.  Hybrid Copula Bayesian Networks , 2016, Probabilistic Graphical Models.

[32]  Shengnan Wu,et al.  Dynamic risk analysis of hydrogen sulfide leakage for offshore natural gas wells in MPD phases , 2019, Process Safety and Environmental Protection.

[33]  R. Nelsen.  An Introduction to Copulas , 1998 .

[34]  Faisal Khan,et al.  Modeling and Testing of Temporal Dependency in the Failure of a Process System , 2019 .

[35]  M. Sam Mannan,et al.  Bayesian network based dynamic operational risk assessment , 2016 .