Bayesian Modeling of External Corrosion in Underground Pipelines Based on the Integration of Markov Chain Monte Carlo Techniques and Clustered Inspection Data

In this study, a model is developed to assess external corrosion in buried pipelines based on the uni- fication of Bayesian inferential structure derived from Markov chain Monte Carlo techniques using clustered inspection data. This proposed stochastic model com- bines clustering algorithms that can ascertain the simi- larity of corrosion defects and Monte Carlo simulation that can give an accurate probability density function es- timation of the corrosion rate. The metal loss rate is cho- sen as the indicator of corrosion damage propagation, obeying a generalized extreme value (GEV) distribution. Bayesian theory was employed to update the probability distribution of metal loss rate as well as the GEV param- eters in order to account for the model uncertainty. The proposed model was validated with direct and indirect inspection data extracted from a 110-km buried pipeline system.

[1]  Jonathan A. Tawn,et al.  A Bayesian Analysis of Extreme Rainfall Data , 1996 .

[2]  James L. Beck,et al.  Structural Model Updating and Health Monitoring with Incomplete Modal Data Using Gibbs Sampler , 2006, Comput. Aided Civ. Infrastructure Eng..

[3]  S. J. Dawson,et al.  Development of a Predictive Model for Pipeline External Corrosion Rates , 2007 .

[4]  Francisco Caleyo,et al.  A study on the reliability assessment methodology for pipelines with active corrosion defects , 2002 .

[5]  R. P. Bell,et al.  Modern Electrochemistry , 1966, Nature.

[6]  James L. Beck,et al.  Structural Health Monitoring via Measured Ritz Vectors Utilizing Artificial Neural Networks , 2006, Comput. Aided Civ. Infrastructure Eng..

[7]  Hava T. Siegelmann,et al.  Support Vector Clustering , 2002, J. Mach. Learn. Res..

[8]  Mahesh D. Pandey,et al.  Probabilistic Neural Network for Reliability Assessment of Oil and Gas Pipelines , 2002 .

[9]  VASSILIS S. KODOGIANNIS,et al.  A Clustering-Based Fuzzy Wavelet Neural Network Model for Short-Term Load Forecasting , 2013, Int. J. Neural Syst..

[10]  Geoffrey J. McLachlan,et al.  The EM Algorithm , 2012 .

[11]  Adrian E. Raftery,et al.  Model-Based Clustering, Discriminant Analysis, and Density Estimation , 2002 .

[12]  Maria Rizzi,et al.  A supervised method for microcalcification cluster diagnosis , 2013, Integr. Comput. Aided Eng..

[13]  Hojjat Adeli,et al.  Enhanced probabilistic neural network with local decision circles: A robust classifier , 2010, Integr. Comput. Aided Eng..

[14]  F. Caleyo,et al.  Probability distribution of pitting corrosion depth and rate in underground pipelines: A Monte Carlo study , 2009 .

[15]  David F. Barrero,et al.  A Genetic Graph-Based Approach for Partitional Clustering , 2014, Int. J. Neural Syst..

[16]  Digby D. Macdonald,et al.  Development of fast algorithms for estimating stress corrosion crack growth rate , 1999 .

[17]  Han Ping Hong,et al.  Inspection and maintenance planning of pipeline under external corrosion considering generation of new defects , 1999 .

[18]  T. Shibata,et al.  1996 W.R. Whitney Award Lecture: Statistical and Stochastic Approaches to Localized Corrosion , 1996 .

[19]  Z. Szklarska‐Śmiałowska,et al.  Pitting Corrosion of Metals , 1986 .

[20]  Andrzej Anderko,et al.  Computation of Rates of General Corrosion Using Electrochemical and Thermodynamic Models , 2001 .

[21]  Jian Zhang,et al.  Advanced Markov Chain Monte Carlo Approach for Finite Element Calibration under Uncertainty , 2013, Comput. Aided Civ. Infrastructure Eng..

[22]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Franck Schoefs,et al.  Assessment of ROC curves for inspection of random fields , 2009 .

[24]  D. Macdonald,et al.  Unification of the deterministic and statistical approaches for predicting localized corrosion damage. I. Theoretical foundation , 2004 .

[25]  Robert E. Melchers,et al.  Pitting Corrosion of Mild Steel in Marine Immersion Environment—Part 1: Maximum Pit Depth , 2004 .

[26]  Alaa Chateauneuf,et al.  Maintenance planning under imperfect inspections of corroded pipelines , 2013 .

[27]  Feng Fan,et al.  Structural reliability assessment by local approximation of limit state functions using a new cokriging technique , 2016 .

[28]  N. Metropolis,et al.  Equation of State Calculations by Fast Computing Machines , 1953, Resonance.

[29]  Phil Hopkins,et al.  SMART PIGS AND DEFECT ASSESSMENT CODES: COMPLETING THE CIRCLE , 2004 .

[30]  G. McLachlan,et al.  The EM algorithm and extensions , 1996 .

[31]  R. Melchers.  Modeling of Marine Immersion Corrosion for Mild and Low-Alloy Steels—Part 1: Phenomenological Model , 2003 .

[32]  Adrian E. Raftery,et al.  Bayesian Regularization for Normal Mixture Estimation and Model-Based Clustering , 2007, J. Classif..

[33]  Michael Collins,et al.  EM Algorithm , 2010, Encyclopedia of Machine Learning.

[34]  C. D. Waard,et al.  Carbonic Acid Corrosion of Steel , 1975 .

[35]  Adrian E. Raftery,et al.  How Many Clusters? Which Clustering Method? Answers Via Model-Based Cluster Analysis , 1998, Comput. J..

[36]  Ka-Veng Yuen,et al.  Peak Ground Acceleration Estimation by Linear and Nonlinear Models with Reduced Order Monte Carlo Simulation , 2010, Comput. Aided Civ. Infrastructure Eng..

[37]  A. Freeny,et al.  Statistical Principles for Research Design and Analysis , 1994 .

[38]  Wei Wang,et al.  Structural Reliability Assessment by Local Approximation of Limit State Functions Using Adaptive Markov Chain Simulation and Support Vector Regression , 2012, Comput. Aided Civ. Infrastructure Eng..

[39]  F. Caleyo,et al.  Predictive Model for Pitting Corrosion in Buried Oil and Gas Pipelines , 2009 .

[40]  Yichang Tsai,et al.  Automatic Detection of Deficient Video Log Images Using a Histogram Equity Index and an Adaptive Gaussian Mixture Model , 2010, Comput. Aided Civ. Infrastructure Eng..

[41]  Michael Havbro Faber,et al.  Hierarchical Modeling of Pipeline Defect Growth Subject to ILI Uncertainty , 2009 .

[42]  Geoffrey J. McLachlan,et al.  Mixture models : inference and applications to clustering , 1989 .

[43]  Jorge L. Alamilla,et al.  Stochastic modelling of corrosion damage propagation in active sites from field inspection data , 2008 .

[44]  John F. Kiefner,et al.  Calculation Of A Corrosion Rate Using Monte Carlo Simulation , 2007 .

[45]  Adrian E. Raftery,et al.  mclust Version 4 for R : Normal Mixture Modeling for Model-Based Clustering , Classification , and Density Estimation , 2012 .

[46]  Hojjat Adeli,et al.  A probabilistic neural network for earthquake magnitude prediction , 2009, Neural Networks.

[47]  Juan J. Salinas,et al.  Risk assessment methodology for pipeline systems , 1985 .

[48]  David Camacho,et al.  Adaptive k-Means Algorithm for Overlapped Graph Clustering , 2012, Int. J. Neural Syst..

[49]  Hojjat Adeli,et al.  Wavelet‐Clustering‐Neural Network Model for Freeway Incident Detection , 2003 .

[50]  Anil K. Jain.  Data clustering: 50 years beyond K-means , 2008, Pattern Recognit. Lett..

[51]  Daniel T. Larose,et al.  Discovering Knowledge in Data: An Introduction to Data Mining , 2005 .

[52]  Yanfeng Ouyang,et al.  Optimal Clustering of Railroad Track Maintenance Jobs , 2014, Comput. Aided Civ. Infrastructure Eng..

[53]  A W Peabody,et al.  Control of Pipeline Corrosion , 1978 .

[54]  W. K. Hastings,et al.  Monte Carlo Sampling Methods Using Markov Chains and Their Applications , 1970 .

[55]  Vipin Kumar,et al.  Introduction to Data Mining , 2022, Data Mining and Machine Learning Applications.

[56]  F. Caleyo,et al.  Markov chain modelling of pitting corrosion in underground pipelines , 2009 .