Data-Based Fault Diagnosis Model Using a Bayesian Causal Analysis Framework

This paper provides a comprehensive data-driven diagnosis approach applicable to complex manufacturing industries. The proposed approach is based on the Bayesian network paradigm. Both the implementation of the Bayesian model (the structure and parameters of the network) and the use of the resulting model for diagnosis are presented. The construction of the structure taking into account the issue related to the explosion in the number of variables and the determination of the network’s parameters are addressed. A diagnosis procedure using the developed Bayesian framework is proposed. In order to provide the structured data required for the construction and the usage of the diagnosis model, a unitary traceability data model is proposed and its use for forward and backward traceability is explained. Finally, an industrial benchmark — the Tennessee Eastman process — is utilized to show the ability of the developed framework to make an accurate diagnosis.

[1]  M.G. Simoes,et al.  Bayesian Network Supervision on Fault Tolerant Fuel Cells , 2006, Conference Record of the 2006 IEEE Industry Applications Conference Forty-First IAS Annual Meeting.

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

[3]  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..

[4]  M. R. Khabbazi,et al.  Data Modeling of Traceability Information for Manufacturing Control System , 2009, 2009 International Conference on Information Management and Engineering.

[5]  Jun Zhang,et al.  Fault detection and diagnosis method for batch process based on ELM-based fault feature phase identification , 2014, Neural Computing and Applications.

[6]  Tiago J. Rato,et al.  Fault detection in the Tennessee Eastman benchmark process using dynamic principal components analysis based on decorrelated residuals (DPCA-DR) , 2013 .

[7]  Yacine Ouzrout,et al.  Knowledge Exchange in a Supply Chain Context , 2004, Virtual Enterprises and Collaborative Networks.

[8]  Zhengxin Chen,et al.  A Descriptive Framework for the Field of Data Mining and Knowledge Discovery , 2008, Int. J. Inf. Technol. Decis. Mak..

[9]  Yacine Ouzrout,et al.  Bayesian Network Building for Diagnosis in Industrial Domain based on Expert Knowledge and Unitary Traceability Data , 2015 .

[10]  David Heckerman,et al.  Bayesian Networks for Data Mining , 2004, Data Mining and Knowledge Discovery.

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

[12]  Yi Peng,et al.  Evaluation of clustering algorithms for financial risk analysis using MCDM methods , 2014, Inf. Sci..

[13]  Shengwei Wang,et al.  Sensor-fault detection, diagnosis and estimation for centrifugal chiller systems using principal-component analysis method , 2005 .

[14]  Fei Tao,et al.  Big Data in product lifecycle management , 2015, The International Journal of Advanced Manufacturing Technology.

[15]  Alberto Rodrigues da Silva,et al.  Data Modeling and Data Analytics: A Survey from a Big Data Perspective , 2015 .

[16]  Bernhard Mitschang,et al.  Warehousing Manufacturing Data - A Holistic Process Warehouse for Advanced Manufacturing Analytics , 2012, DaWaK.

[17]  Adrie J. M. Beulens,et al.  Managing traceability information in manufacture , 2003, Int. J. Inf. Manag..

[18]  Paulo Eigi Miyagi,et al.  Detection and treatment of faults in automated machines based on Petri nets and Bayesian networks , 2003, 2003 IEEE International Symposium on Industrial Electronics ( Cat. No.03TH8692).

[19]  Sameer Kumar,et al.  A knowledge based reliability engineering approach to manage product safety and recalls , 2014, Expert Syst. Appl..

[20]  James A. Stori,et al.  A Bayesian network approach to root cause diagnosis of process variations , 2005 .

[21]  Feng Jia,et al.  An Intelligent Fault Diagnosis Method Using Unsupervised Feature Learning Towards Mechanical Big Data , 2016, IEEE Transactions on Industrial Electronics.

[22]  Hanlin Liu,et al.  A Data-Driven Fault Diagnosis Methodology in Three-Phase Inverters for PMSM Drive Systems , 2017, IEEE Transactions on Power Electronics.

[23]  J. Manyika.  Big data: The next frontier for innovation, competition, and productivity , 2011 .

[24]  Yingning Qiu,et al.  Bayesian network for wind turbine fault diagnosis. , 2012 .

[25]  Nam-Ho Kyong,et al.  Subsystem level fault diagnosis of a building's air-handling unit using general regression neural networks , 2004 .

[26]  Yi Peng,et al.  FAMCDM: A fusion approach of MCDM methods to rank multiclass classification algorithms , 2011 .

[27]  Miriam A. M. Capretz,et al.  Data management in cloud environments: NoSQL and NewSQL data stores , 2013, Journal of Cloud Computing: Advances, Systems and Applications.

[28]  Richard D. Braatz,et al.  Fault Detection and Diagnosis in Industrial Systems , 2001 .

[29]  Jean-Baptiste Denis,et al.  Bayesian Networks , 2014 .

[30]  D. Thompson,et al.  Construction of Bayesian networks for diagnostics , 2000, 2000 IEEE Aerospace Conference. Proceedings (Cat. No.00TH8484).

[31]  Qian Fan,et al.  Multi-source information fusion based fault diagnosis of ground-source heat pump using Bayesian network , 2014 .

[32]  Víctor C. Ramirez,et al.  Learning Bayesian Networks for Systems Diagnosis , 2006, Electronics, Robotics and Automotive Mechanics Conference (CERMA'06).

[33]  Sanjay Ghemawat,et al.  MapReduce: Simplified Data Processing on Large Clusters , 2004, OSDI.

[34]  J. Pearl.  Causality: Models, Reasoning and Inference , 2000 .

[35]  In Lee,et al.  Big data: Dimensions, evolution, impacts, and challenges , 2017 .

[36]  Moe Thandar Wynn,et al.  Data and process requirements for product recall coordination , 2011, Comput. Ind..

[37]  Yi Peng,et al.  Evaluation of Classification Algorithms Using MCDM and Rank Correlation , 2012, Int. J. Inf. Technol. Decis. Mak..

[38]  Petter Olsen,et al.  How to define traceability , 2013 .

[39]  B. Akhgar,et al.  Application of Big Data for National Security: A Practitioner’s Guide to Emerging Technologies , 2015 .

[40]  Yi Peng,et al.  Ensemble of Software Defect Predictors: an AHP-Based Evaluation Method , 2011, Int. J. Inf. Technol. Decis. Mak..

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

[42]  Yacine Ouzrout,et al.  Using Unitary Traceability for an Optimal Product Recall , 2014, APMS.

[43]  Sébastien Henry,et al.  Quality Improvement of Product Data Exchanged Between Engineering and Production Through the Integration of Dedicated Information Systems , 2012 .

[44]  Russ M. Dabbas,et al.  Mining semiconductor manufacturing data for productivity improvement - an integrated relational database approach , 2001, Comput. Ind..

[45]  Bernhard Mitschang,et al.  Data Mining-driven Manufacturing Process Optimization , 2012 .

[46]  Q. Peter He,et al.  A New Fault Diagnosis Method Using Fault Directions in Fisher Discriminant Analysis , 2005 .

[47]  Rolf Isermann,et al.  Supervision, fault-detection and fault-diagnosis methods — An introduction , 1997 .

[48]  Constantin F. Aliferis,et al.  The max-min hill-climbing Bayesian network structure learning algorithm , 2006, Machine Learning.