Integrated pipeline corrosion growth modeling and reliability analysis using dynamic Bayesian network and parameter learning technique

2019 ◽  
Vol 16 (8) ◽  
pp. 1161-1176
Author(s):  
Wei Xiang ◽  
Wenxing Zhou
Keyword(s):  
Bayesian Network ◽  
Reliability Analysis ◽  
Dynamic Bayesian Network ◽  
Growth Modeling ◽  
Parameter Learning ◽  
Learning Technique ◽  
Pipeline Corrosion

scholarly journals Dynamic Reliability Analysis of Corroded Pipeline Using Bayesian Network

2018 ◽  
Vol 7 (4.35) ◽  
pp. 210
Author(s):  
Nurul Sa’aadah Sulaiman ◽  
Henry Tan
Keyword(s):  
Bayesian Network ◽  
Reliability Analysis ◽  
Structural Reliability ◽  
Dynamic Bayesian Network ◽  
Operating Pressure ◽  
Dynamic Reliability ◽  
Time Dynamic ◽  
Remaining Service Life ◽  
Reliability Method ◽  
Deterioration Process

Maintenance and integrity management of hydrocarbons pipelines face the challenges from uncertainties in the data available. This paper demonstrates a way for pipeline remaining service life prediction that integrates structural reliability analysis, accumulated corrosion knowledge, and inspection data on a sound mathematical foundation. Pipeline defects depth grows with time according to an empirical corrosion power law, and this is checked for leakage and rupture probability. The pipeline operating pressure is checked with the degraded failure pressure given by ASME B31G code for rupture likelihood. As corrosion process evolves with time, Dynamic Bayesian Network (DBN) is employed to model the stochastic corrosion deterioration process. From the results obtained, the proposed DBN model for pipeline reliability is advanced compared with other traditional structural reliability method whereby the updating ability brings in more accurate prediction results of structural reliability. The comparisons show that the DBN model can achieve a realistic result similar to the conventional method, Monte Carlo Simulation with very minor discrepancy.

Corrosion Growth Modeling by Learning a Dynamic Bayesian Network From Multiple In-Line Inspection Data

2018 ◽  
Author(s):  
Wei Xiang ◽  
Wenxing Zhou
Keyword(s):  
Bayesian Networks ◽  
Bayesian Network ◽  
Failure Probability ◽  
Dynamic Bayesian Network ◽  
Time Dependent ◽  
Parameter Learning ◽  
Random Errors ◽  
Defect Depth ◽  
Corrosion Defects ◽  
Dependent Failure

This paper establishes a dynamic Bayesian network to model the growth of corrosion defects on energy pipelines. The integrated model characterizes the growth of defect depth by a homogeneous gamma process and considers the biases and random errors associated with the in-line inspection (ILI) tools. The distributions of the mean value and coefficient of variation of the annual growth of defect depth are learned from multiple ILI data using the parameter learning technique of Bayesian networks. With the same technique, the distributions of the biases and standard deviation of random errors associated with ILI tools are learned from ILI data and their corresponding field measurements. An example with real corrosion management data is used to illustrate the process of developing the model structure, learning model parameters and predicting the corrosion growth and time-dependent failure probability. The results indicate that the model can in general predict the growth of corrosion defects with reasonable accuracy and the ILI-reported and field-measured depth can be used to update the time-dependent failure probability in a near-real-time manner. In comparison with existing growth models, the graphical feature of Bayesian networks makes it more intuitive and transparent to users. The employment of parameter learning provides a semi-automated and convenient approach to elicit the probabilistic information from ILI and field measurement data. The above advantages will facilitate the application of the model in the practice of corrosion management in pipeline industry.

Reliability Analysis of Subsea Separation and Boosting System Using Dynamic Bayesian Network

2017 ◽  
Author(s):  
Jiayong Zhu ◽  
Andres Hernandez ◽  
Ankita Taneja ◽  
Bin Zhang ◽  
M. Sam Mannan
Keyword(s):  
Bayesian Network ◽  
Reliability Analysis ◽  
Dynamic Bayesian Network
Sign in / Sign up

Export Citation Format

Share Document