|本期目录/Table of Contents|

[1]胡亚平,张认认,李新宏,等.基于贝叶斯参数学习的海底原油管道腐蚀状态评估*[J].中国安全生产科学技术,2023,19(11):93-99.[doi:10.11731/j.issn.1673-193x.2023.11.013]
　HU Yaping,ZHANG Renren,LI Xinhong,et al.Assessment on corrosion state of subsea crude oil pipeline based on Bayesian parameter learning[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2023,19(11):93-99.[doi:10.11731/j.issn.1673-193x.2023.11.013]
点击复制

基于贝叶斯参数学习的海底原油管道腐蚀状态评估*
分享到：

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
19
期数:
2023年11期
页码:
93-99
栏目:
职业安全卫生管理与技术
出版日期:
2023-11-30

文章信息/Info

Title:
Assessment on corrosion state of subsea crude oil pipeline based on Bayesian parameter learning
文章编号:
1673-193X(2023)-11-0093-07
作者:
胡亚平; 张认认; 李新宏; 张璐瑶; 韩子月
（1.西安建筑科技大学 资源工程学院，陕西 西安 710055；
2.西安建筑科技大学 机电工程学院，陕西 西安 710055）
Author(s):
HU Yaping;  ZHANG Renren;  LI Xinhong;  ZHANG Luyao;  HAN Ziyue
(1.School of Resource Engineering,Xi’an University of Architecture and Technology,Xi’an Shaanxi 710055,China;
2.School of Mechanical and Electrical Engineering,Xi’an University of Architecture and Technology,Xi’an Shaanxi,710055,China)
关键词:
海底原油管道; 腐蚀状态; 贝叶斯参数学习; 腐蚀速率; 腐蚀坑深
Keywords:
subsea crude oil pipeline;  corrosion state;  Bayesian parameter learning;  corrosion rate;  corrosion pit depth
分类号:
X937
DOI:
10.11731/j.issn.1673-193x.2023.11.013
文献标志码:
A
摘要:
为有效预防海底原油管道腐蚀失效事故，提出1种基于贝叶斯参数学习的海底原油管道腐蚀状态评估方法。考虑均匀腐蚀、点蚀和微生物腐蚀等3种管道腐蚀类型，构建海底原油管道腐蚀因果关系概率网络模型。离散化模型节点状态，初始化各节点的状态概率，利用贝叶斯参数学习方法量化处于不同腐蚀状态下的管道腐蚀速率与腐蚀坑深的概率，并以某实际海底原油管道为例进行实例验证。研究结果表明：实例管道腐蚀速率处于“严重”、“高”、“中”、“低”状态的概率分别为0.45，0.32，0.19，0.04；腐蚀坑深处于“严重”、“高”、“中”、“低”状态的概率依次为0.38，0.29，0.24，0.08。这表明该管道遭受严重腐蚀风险的可能性较大，需采取措施降低管道失效风险。研究结果对于海底原油管道腐蚀失效风险管理具有重要意义。
Abstract:
In order to effectively prevent the corrosion failure accidents of subsea crude oil pipelines,an assessment method for the corrosion state of subsea crude oil pipeline based on Bayesian parameter learning was proposed.Considering three types of pipeline corrosion,namely uniform corrosion,pitting corrosion and microbiologically influenced corrosion (MIC),a probabilistic network model of the causality of subsea crude oil pipeline corrosion was constructed.The node states of the model were discretized,and the state probabilities of each node were initialized.The probabilities of pipeline corrosion rate and corrosion pit depth under different corrosion states were quantified by Bayesian parameter learning method,and an actual subsea crude oil pipeline was taken as an example for verification.The results show that the probability of pipeline corrosion rate being severe,high,moderate and low is 0.45,0.32,0.19 and 0.04,respectively,and the probabilities of corrosion pit depth being severe,high,moderate and low is 0.38,0.29,0.24 and 0.08,respectively.It shows that the pipeline is likely to suffer from serious corrosion risk,and the countermeasures should be taken to reduce the risk of pipeline failure.The research results are of great significance to the risk management on corrosion failure of subsea crude oil pipelines.

参考文献/References:

［1］方娜,陈国明,朱红卫,等.海底管道泄漏事故统计分析［J］.油气储运,2014,33(1):99-103. FANG Na,CHEN Guoming,ZHU Hongwei,et al.Statistical analysis of leakage accidents of submarine pipeline［J］.Oil Gas Storage Transp,2014,33(1):99-103.
［2］WANG Y C,XU L Y,SUN J L,et al.Mechano-electrochemical interaction for pipeline corrosion:a review［J］.Journal of Pipeline Science and Engineering,2021,1(1):1-16.
［3］Manual for determining the remaining strength of corroded pipelines:ASME B31G—1991［S］.New York:The American Society of Mechanical Engineers,1991.
［4］Oil and gas pipeline systems:CSA Z662-07［S］.Ontario,Canada:Canadian Standards Association,2007.
［5］Recommended practice for corroded pipeline:DNV-RP-F101［S］.Oslo,Norway:Det Norske,2015.
［6］王威,陈国民,陈琦,等.海底腐蚀缺陷管道可靠性分析及风险评估［J］.海洋工程装备与技术,2018,5(6):390-395. WANG Wei,CHEN Guomin,CHEN Qi,et al.Reliability calculation analysis and risk assessment of submarine pipelines under corrosion defects ［J］.Journal of Ocean Engineering Equipment,2018,5(6):390-395.
［7］张晓,帅健.基于FITNET FFS模型的腐蚀管道失效概率敏感性分析［J］.中国安全生产科学技术,2018,14(8):80-85. ZHANG Xiao,SHUAI Jian.Sensitivity analysis on failure probability of corroded pipeline based on FITNET FFS model［J］.Journal of Safety Science and Technology,2018,14(8):80-85.
［8］ZHOU W X.System reliability of corroding pipelines［J］.International Journal of Pressure Vessels and Piping,2010,87(10):587-595.
［9］韩文海,周晶.腐蚀海底管道可靠性分析［J］.石油学报,2015,36(4):516-520. HAN Wenhai,ZHOU Jing.Reliability analysis of corroded subsea pipeline［J］.Acta Petrolei Sinica,2015,36(4):516-520.
［10］王晓敏,骆正山,赵乐新.腐蚀和残余应力对油气管道不规则区可靠性的影响分析［J］.表面技术,2020,49(4):278-283. WANG Xiaomin,LUO Zhengshan，ZHAO Lexin.Corrosion and residual stress on reliability of lrregular area of pipeline［J］.Surface Technology,2020,49(4):278-283.
［11］WEN K,HE L,LIU J,et al.An optimization of artificial neural network modeling methodology for the reliability assessment of corroding natural gas pipelines［J］.Journal of Loss Prevention in the Process Industries,2019,60:1-8.
［12］冯超,贾澳银,李陈涛,等.基于 PSO-GPR 含缺陷管道失效应力预测［J］.力学与实践,2023,45(2):260-266. FENG Chao,JIA Aoyin,LI Chentao,et al.Failure stress prediction of defective pipeline based on PSO-GPR［J］.Mechanics in Engineering,2023,45(2):260-266.
［13］WANG W,HE X M,LI Y T,et al.Risk analysis on corrosion of submarine oil and gas pipelines based on hybrid Bayesian network［J］.Ocean Engineering,2022,260:111957.
［14］王辉,纪翔,洪亮.基于优化贝叶斯网络的油气管道失效风险安全评价［J］.化工安全与环境,2023,36(1):35-40. WANG Hui,JI Xiang,HONG Liang.Safety assessment of failure risk of oil and gas pipeline based on optimized Bayesian network［J］.Chemical Safety & Environment,2023,36(1):35-40.
［15］LIAO W H,JI Q.Learning Bayesian network parameters under incomplete data with domain knowledge［J］.Pattern Recognition,2009,42(11):3046-3056.
［16］MASEGOSA A R,FEELDERS A J,VANDERGAAG L C.Learning from incomplete data in Bayesian networks with qualitative influences［J］.International Journal of Approximate Reasoning,2016,69:18-34.
［17］ZHOU Y,FENTON N,ZHU C.An empirical study of Bayesian network parameter learning with monotonic influence constraints［J］.Decision Support Systems,2016,87:69-79.
［18］XIANG W,ZHOU W.Bayesian network model for predicting probability of third-party damage to underground pipelines and learning model parameters from incomplete datasets［J］.Reliability Engineering & System Safety,2021,205:107262.
［19］KAMIL M Z,TALEBBERROUANE M,KHAN F,et al.Data-driven operational failure likelihood model for microbiologically influenced corrosion［J］.Process Safety and Environmental Protection,2021,153:472-485.
［20］SHABARCHIN O,TESFAMARIAM S.Internal corrosion hazard assessment of oil & gas pipelines using Bayesian belief network model［J］.Journal of Loss Prevention in the Process Industries,2016,40:479-495.
［21］LI X H,JIA R C,ZHANG R R,et al.A KPCA-BRANN based data-driven approach to model corrosion degradation of subsea oil pipelines［J］.Reliability Engineering & System Safety,2022,219:108231.
［22］BEECH I B,GAVLARDE C C.Recent advances in the study of biocorrosion:an overview［J］.Revista De Microbiologia,1999,30(3):117-190.
［23］ALJAROUDI S S,ULHAMID A,ALGAHTANI M M.Failure of crude oil pipeline due to microbiologically induced corrosion［J］.Corrosion Engineering,Science and Technology,2011,46(4):568-579.
［24］PAIK J K.Advanced method for the development of an empirical model to predict time-dependent corrosion wastage［J］.Corrosion Science,2012,63:51-58.
［25］MACHUC L L.Microbiologically influenced corrosion:a review focused on hydrotest fluids in subsea pipelines［J］.ACA Corrosion and Prevention 2014,141:117-125.
［26］POTS B F M,KAPUSTA S D,JOHN R C,et al.Improvements on de Waard-Milliams corrosion prediction and applications to corrosion management［C］//CORROSION 2002.Denver,Colorado:OnePetro,2002:1-19.
［27］AYELLO F,JAIN S,SRIDHAR N,et al.Quantitive assessment of corrosion probability—a Bayesian network approach［J］.Corrosion,2014,70(11):1128-1147.

相似文献/References:

备注/Memo

备注/Memo:
收稿日期： 2023-07-04
* 基金项目： 国家自然科学基金项目(52004195);陕西省高校科协青年人才托举计划项目(20220429)
作者简介： 胡亚平，硕士研究生，主要研究方向为海底管道结构安全与风险评估。
通信作者： 张认认，硕士，助理工程师，主要研究方向为油气管柱/道安全可靠性评估。
更新日期/Last Update: 2023-12-06