Dynamic kriging based fault detection and diagnosis approach for nonlinear noisy dynamic processes

This paper presents a hybrid approach to improve data-based Fault Detection and Diagnosis (FDD). It is applicable to nonlinear dynamic noisy processes, operated under time-varying inputs. The method is based on the combination of kriging models and Pattern Recognition Techniques. A set of Multivariate Dynamic Kriging-based predictors (MDKs) is built and used to estimate the process dynamic behavior, while static kriging models are used to smooth the eventually noisy process outputs. The estimated and the actual smoothed outputs are compared, taking advantage of the higher capacity of the residual patterns generated in this way to characterize the process state. The performance of the method is illustrated through its application to a well-known benchmark case study, for which the FDD performance has been significantly improved. This improvement is consistently maintained in different dynamic operating conditions and faulty situations, including scenarios with modified fault severities and fault styles.

[1]  Andy J. Keane,et al.  Engineering Design via Surrogate Modelling - A Practical Guide , 2008 .

[2]  Junfei Qiao,et al.  A fuzzy neural network approach for online fault detection in waste water treatment process , 2014, Comput. Electr. Eng..

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

[4]  Si-Zhao Joe Qin,et al.  Survey on data-driven industrial process monitoring and diagnosis , 2012, Annu. Rev. Control..

[5]  Abdessamad Kobi,et al.  Fault Detection and Diagnosis in a Bayesian Network classifier incorporating probabilistic boundary1 , 2015 .

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

[7]  Dino Isa,et al.  Active incremental Support Vector Machine for oil and gas pipeline defects prediction system using long range ultrasonic transducers. , 2014, Ultrasonics.

[8]  Antonio Espuña,et al.  Sequential dynamic optimization of complex nonlinear processes based on Kriging surrogate models , 2014 .

[9]  Morteza Sarailoo,et al.  A novel model predictive control scheme based on bees algorithm in a class of nonlinear systems: Application to a three tank system , 2015, Neurocomputing.

[10]  Edwin Lughofer,et al.  Residual-based fault detection using soft computing techniques for condition monitoring at rolling mills , 2014, Inf. Sci..

[11]  Thomas J. Santner,et al.  Design and analysis of computer experiments , 1998 .

[12]  Mimoun Zelmat,et al.  Variogram-based fault diagnosis in an interconnected tank system. , 2012, ISA transactions.

[13]  Antonio Espuña Camarasa,et al.  Kriging based fault detection and diagnosis approach for nonlinear noisy dynamic processes , 2016 .

[14]  Jie Chen,et al.  Model-based methods for fault diagnosis: some guide-lines , 1995 .

[15]  Moisès Graells,et al.  Fault diagnosis of chemical processes with incomplete observations: A comparative study , 2016, Comput. Chem. Eng..

[16]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[17]  Aníbal R. Figueiras-Vidal,et al.  Pattern classification with missing data: a review , 2010, Neural Computing and Applications.

[18]  Donald R. Jones,et al.  A Taxonomy of Global Optimization Methods Based on Response Surfaces , 2001, J. Glob. Optim..

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

[20]  Moisès Graells,et al.  A semi-supervised approach to fault diagnosis for chemical processes , 2010, Comput. Chem. Eng..

[21]  Aydin K. Sunol,et al.  Chemical plant fault diagnosis through a hybrid symbolic-connectionist machine learning approach , 1998 .

[22]  Antonio Espuña,et al.  Optimal Features Selection for Designing a Fault Diagnosis System , 2016 .

[23]  Kay Smarsly,et al.  A Decentralized Approach towards Autonomous Fault Detection in Wireless Structural Health Monitoring Systems , 2014 .

[24]  Noel A. C. Cressie,et al.  Statistics for Spatial Data: Cressie/Statistics , 1993 .

[25]  Jie Chen,et al.  Fault diagnosis in nonlinear dynamic systems via neural networks , 1994 .

[26]  Raghunathan Rengaswamy,et al.  New nonlinear residual feedback observer for fault diagnosis in nonlinear systems , 2008, Autom..

[27]  Antonio Espuña,et al.  Multistep Ahead Prediction Using Ordinary Kriging Applied to Modeling and Simulation Of Complex Nonlinear Dynamic Processes , 2015 .

[28]  Thomas Parisini,et al.  Identification of neural dynamic models for fault detection and isolation: the case of a real sugar evaporation process , 2005 .

[29]  M. Ierapetritou,et al.  A kriging method for the solution of nonlinear programs with black‐box functions , 2007 .