Server maintenance is scheduled for Saturday, December 21st between 6am-10am CST.

During that time, parts of our website will be affected until maintenance is completed. Thank you for your patience.

Menu
Search
Filters
Close
Menu

51314-3851-Corrosion Threat Assessment Using Bayesian Networks

Picture for Corrosion Threat Assessment Using Bayesian Networks
Available for download
Product Number: 51314-3851-SG
ISBN: 3851 2014 CP
Author: Francois Ayello
Publication Date: 2014
$0.00
$0.00
$0.00
Many engineers are inclined to not trust models; this is particularly true in the field of corrosion. Suspicion comes from modeled results which are inconsistent with field data. The difference between modeled results and the real world has three reasons. First no model is accurate in all situations. Second the input data used to run the models is never exact. And third the operator's knowledge of the system is often missing. In order to increase confidence and reduce the gap between modeled results and field data it is necessary to address all three sources of uncertainties.A solution is proposed: (1) never trust one model only run multiple models (2) run the models multiple times for all possible input parameters (Monte Carlo method) and (3) combine the output of different models as well as the operator's knowledge in a graphical interface (Bayesian network). The results of the multiple simulations are not numbers but a function of all the possible outcomes predicted by the models.This paper presents a Bayesian networks created to assess the probability of pipeline failure due to internal corrosion. The model created quantifies likelihood (and uncertainty) of pipeline failure as well as all causative factors. For a pipeline operator is necessary to reduce both the uncertainty and the likelihood itself. The uncertainty is reduced by gathering data and the likelihood is reduced by mitigation. Therefore results of the Bayesian networks can be used both to prioritize inspections (reduce uncertainty) and prioritize mitigation (reduce likelihood of failure). Results of a blind-test of the model performed in collaboration with Kuwait Oil Company are also presented.Key words: Bayesian network internal corrosion direct risk assessment uncertainty prioritization 
Many engineers are inclined to not trust models; this is particularly true in the field of corrosion. Suspicion comes from modeled results which are inconsistent with field data. The difference between modeled results and the real world has three reasons. First no model is accurate in all situations. Second the input data used to run the models is never exact. And third the operator's knowledge of the system is often missing. In order to increase confidence and reduce the gap between modeled results and field data it is necessary to address all three sources of uncertainties.A solution is proposed: (1) never trust one model only run multiple models (2) run the models multiple times for all possible input parameters (Monte Carlo method) and (3) combine the output of different models as well as the operator's knowledge in a graphical interface (Bayesian network). The results of the multiple simulations are not numbers but a function of all the possible outcomes predicted by the models.This paper presents a Bayesian networks created to assess the probability of pipeline failure due to internal corrosion. The model created quantifies likelihood (and uncertainty) of pipeline failure as well as all causative factors. For a pipeline operator is necessary to reduce both the uncertainty and the likelihood itself. The uncertainty is reduced by gathering data and the likelihood is reduced by mitigation. Therefore results of the Bayesian networks can be used both to prioritize inspections (reduce uncertainty) and prioritize mitigation (reduce likelihood of failure). Results of a blind-test of the model performed in collaboration with Kuwait Oil Company are also presented.Key words: Bayesian network internal corrosion direct risk assessment uncertainty prioritization 
Product tags
Also Purchased
Picture for A BAYESIAN NETWORK BASED PIPELINE RISK MANAGEMENT
Available for download

51312-01123-A BAYESIAN NETWORK BASED PIPELINE RISK MANAGEMENT

Product Number: 51312-01123-SG
ISBN: 01123 2012 CP
Author: Francois Ayello
Publication Date: 2012
$20.00
Picture for Internal Corrosion Direct Assessment Using Bayesian Networks Modeling With Limited Data-A Case Study
Available for download

51316-7078-Internal Corrosion Direct Assessment Using Bayesian Networks Modeling With Limited Data-A Case Study

Product Number: 51316-7078-SG
ISBN: 7078 2016 CP
Author: Shan Guan
Publication Date: 2016
$20.00

Bayesian networks (BN) are useful tools for corrosion modeling. This paper is a case study demonstrating how to perform Internal Corrosion Direct Assessment (ICDA) using BN modeling with limited data.  A BN model was developed for ICDA of a 50 km refined oil pipeline.  Internal corrosion probability of failure along the pipeline was assessed.
Picture for Probabilistic Model for Stress Corrosion Cracking of Underground Pipelines Using Bayesian Networks
Available for download

51313-02616-Probabilistic Model for Stress Corrosion Cracking of Underground Pipelines Using Bayesian Networks

Product Number: 51313-02616-SG
ISBN: 02616 2013 CP
Author: Swati Jain
Publication Date: 2013
$20.00
Categories
Industry
Recently viewed
Popular tags
View all

Association for Materials Protection and Performance

© AMPP All Rights Reserved.
Membership Terms of Content Use
Contact Customer Support