PDF下载
[1]肖述辉,杜传甲,王成军.基于改进麻雀搜索算法优化BP神经网络的管道腐蚀速率预测模型[J].油气储运,2024,43(07):1-13.
　XIAO Shuhui,Du Chuanjia,WANG Chengjun.Pipeline corrosion rate prediction using BP neural network based on improved sparrow search algorithm[J].Oil & Gas Storage and Transportation,2024,43(07):1-13.
点击复制

基于改进麻雀搜索算法优化BP神经网络的管道腐蚀速率预测模型

《油气储运》[ISSN:1000-8241/CN:13-1093/TE] 卷: 43 期数: 2024年07期 页码: 1-13 栏目: 出版日期: 2024-07-25
Title:
Pipeline corrosion rate prediction using BP neural network based on improved sparrow search algorithm
作者:
肖述辉; 杜传甲; 王成军
1．陕西延长石油（集团）管道运输公司；2．西安建筑科技大学管理学院
Author(s):
XIAO Shuhui; Du Chuanjia; WANG Chengjun
1.Shaanxi Yanchang Petroleum Group Pipeline Company; 2.Department of Management，Xi’an University of Architecture and Technology
关键词:
管道腐蚀速率; 预测; MIS-SSA-BP神经网络; 算法优化
Keywords:
pipeline corrosion rate;  forecast;  MIS-SSA-BP neural network;  algorithm optimization
分类号:
TE88
文献标志码:
A
摘要:
【目的】为保障油气储运系统安全运行，需准确预测油气管道腐蚀速率。现有预测模型多基于BP神经网络建立，存在收敛速度慢、易陷入局部最优等不足。【方法】为解决上述问题，提出一种基于改进麻雀搜索算法优化BP神经网络的管道腐蚀速率预测模型，通过反向学习策略初始化种群，引入混合正余弦算法更新发现者位置，加入Levy飞行策略更新追随者位置对麻雀搜索算法进行改进。基于改进后的麻雀搜索算法对BP神经网络的权重和阈值进行寻优，从而提高参数选择的科学性。【结果】以100组20#钢材料试验获取的均匀腐蚀速率和点腐蚀速率的样本数据为例，分别建立BP、SSA-BP、MIS-SSA-BP神经网络管道腐蚀速率预测模型，对油气管道均匀腐蚀速率和点腐蚀速率进行训练、预测和模型对比。MIS-SSA-BP神经网络管道腐蚀速率预测模型的平均绝对误差、均方误差、均方误差根、平均绝对百分比误差均最小，且均匀腐蚀速率、点腐速率预测值与实测值的相对误差均低于5%，其各项评价指标及预测精度均显著优于BP、SSA-BP神经网络管道腐蚀速率预测模型。【结论】相关工作进一步验证了MIS-SSA-BP神经网络管道腐蚀速率预测模型良好的预测性能，为后续油气管道腐蚀速率预测研究提供了新的方法和思路。
Abstract:
[Objective]In order to accurately predict the corrosion rate of oil and gas pipelines and guarantee the safe operation of oil and gas storage and transportation systems, this paper proposes a pipeline corrosion rate prediction model based on the optimization of BP neural network with improved sparrow search algorithm. [Methods]The model first initializes the population through the reverse learning strategy, then introduces the hybrid sine-cosine algorithm to update the finder position, and finally adds the Levy flight strategy to update the follower position to improve the sparrow search algorithm. Based on the improved sparrow search algorithm the weights and thresholds of the BP neural network are optimization-seeking, which improves the scientificity of parameter selection. [Results]Taking the sample data of uniform corrosion rate and pitting corrosion rate obtained from 100 groups of 20# steel material tests as an example, the BP, SSA-BP and MIS-SSA-BP neural network pipeline corrosion rate prediction models are established respectively, and the uniform corrosion rate and pitting corrosion rate of oil and gas pipelines are trained, predicted and compared with the models. The results show that the average absolute error, mean square error, root mean square error, and average absolute percentage error of the MIS-SSA-BP neural network pipeline corrosion rate prediction model are the smallest, and the relative error values of the uniform corrosion rate and pitting corrosion rate prediction are lower than 5%, and its evaluation indexes and prediction accuracy are obviously better than that of the BP, SSA-BP neural network pipeline corrosion rate prediction model. [Conclusion]The evaluation indexes and prediction accuracy are significantly better than those of BP and SSA-BP neural network pipeline corrosion rate prediction model, which further verifies the good prediction performance of MIS-SSA-BP neural network pipeline corrosion rate prediction model, and provides a new method and idea for the subsequent corrosion rate prediction research of oil and gas pipelines. 

参考文献/References:

[1] 罗鹏，张一玲，蔡陪陪，郭正虹，陈洪源，王维斌.长输天然气管道内腐蚀事故调查分析与对策[J].全面腐蚀控制，2010，24（6）：16-21. DOI：10.3969/j.issn.1008-7818.2010.06.009.
LUO P, ZHANG Y L, CAI P P, GUO Z H, CHEN H Y, WANG W B. Analysis and countermeasures of natural gas transmission pipeline internal corrosion accidents[J]. Total Corrosion Control, 2010, 24(6): 16-21.
[2] GONG Y H, LI Y T. STAMP-based causal analysis of China-Donghuang oil transportation pipeline leakage and explosion accident[J]. Journal of Loss Prevention in the Process Industries, 2018, 56: 402-413. DOI: 10.1016/j.jlp.2018.10.001.
[3] 吕林林，王杰，祁庆芳，郭策，贺蓉蓉，孙小伟.基于KPCA-IGOA-ELM的油气混输管道腐蚀速率预测模型[J].油气储运，2023，42（7）：785-792. DOI：10.6047/j.issn.1000-8241.2023.07.007.
LYU L L, WANG J, QI Q F, GUO C, HE R R, SUN X W. Corrosion rate prediction model of oil-gas mixed transportation pipelines based on KPCA-IGOA-ELM[J]. Oil & Gas Storage and Transportation, 2023, 42(7): 785-792.
[4] 宋成立.多因素作用下油气集输管道的腐蚀行为及预测模型[D].西安：西北大学，2022.
SONG C L. Corrosion behavior and prediction model of oil and gas gathering pipelines under multi-factors[D]. Xi’an: Northwest University, 2022.
[5] ZHI Y J, FU D M, YANG T, ZHANG D W, LI X G, PEI Z B. Long-term prediction on atmospheric corrosion data series of carbon steel in China based on NGBM(1,1) model and genetic algorithm[J]. Anti-Corrosion Methods and Materials, 2019, 66(4): 403-411. DOI: 10.1108/ACMM-11-2017-1858.
[6] 巴振宁，韩亚鑫，梁建文.基于改进AHP和模糊综合评价法的燃气管道腐蚀风险评价[J].安全与环境学报，2018，18（6）：2103-2109. DOI：10.13637/j.issn.1009-6094.2018.06.009.
BA Z N, HAN Y X, LIANG J W. Risk assessment of the gas pipeline corrosion based on the improved AHP and fuzzy comprehensive evaluation method[J]. Journal of Safety and Environment, 2018, 18(6): 2103-2109.
 [7] PAUL S, MONDAL R. Computation of corrosion rates of steel with variation of Cl-, SO42-, CO32-, HCO3-, O2, CO2, pH and temperature, developed by modeling with artificial neural network[J]. Innovations in Corrosion and Materials Science, 2017, 7(2): 135-143. DOI: 10.2174/2352094907666171016124420.
[8] 骆正山，陈晨，王哲.优化的Gray Markov模型在埋地管道腐蚀速率预测中的应用[J].腐蚀与防护，2019，40（5）：313-317，326. DOI：10.11973/fsyfh-201905001.
LUO Z S, CHEN C, WANG Z. Application of improved Gray Markov dynamic model in predicting corrosion rates of oil and gas pipelines[J]. Corrosion and Protection, 2019, 40(5): 313-317, 326.
[9] 吴奇兵，张士超，曹义威，安广山，屈会智，陈泽光，等.基于模糊综合评价法的海上采油树安全分级[J].石油机械，2021，49（10）：65-70. DOI：10.16082/j.cnki.issn.1001-4578.2021.10.010.
WU Q B, ZHANG S C, CAO Y W, AN G S, QU H Z, CHEN Z G, et al. Safety classification of offshore Christmas tree based on fuzzy comprehensive evaluation method[J]. China Petroleum Machinery, 2021, 49(10): 65-70.
[10] ROCABRUNO-VALDÉS C I, GONZÁLEZ-RODRIGUEZ J G, DÍAZ-BLANCO Y, JUANTORENA A U, MUÑOZ-LEDO J A, EL-HAMZAOUI Y, et al. Corrosion rate prediction for metals in biodiesel using artificial neural networks[J]. Renewable Energy, 2019, 140: 592-601. DOI: 10.1016/j.renene.2019.03.065.
[11] 陈艳，康伟杰，姚铭，董彩常.基于FLUENT和神经网络预测海水弯管冲刷腐蚀的模型[J].腐蚀与防护，2019，40（6）：436-440. DOI：10.11973/fsyfh-201906009.
CHEN Y, KANG W J, YAO M, DONG C C. Prediction model for erosion-corrosion of seawater bend based on fluent and neural network[J]. Corrosion and Protection, 2019, 40(6): 436-440.
[12] 胡松青，石鑫，胡建春，任振甲，郭爱玲，高元军.基于BP神经网络的输油管道内腐蚀速率预测模型[J].油气储运，2010，29（6）：448-450. DOI：10.6047/j.issn.1000-8241.2010.06.014.
HU S Q, SHI X, HU J C, REN Z J, GUO A L, GAO Y J. BP neural network-based prediction model for internal corrosion rate of oil pipelines[J]. Oil & Gas Storage and Transportation, 2010, 29(6): 448-450.
[13] HU Q F, LIU Y C, ZHANG T, GENG S J, WANG F H. Modeling the corrosion behavior of Ni-Cr-Mo-V high strength steel in the simulated deep sea environments using design of experiment and artificial neural network[J]. Journal of Materials Science & Technology, 2019, 35(1): 168-175. DOI: 10.1016/j.jmst.2018.06.017.
[14] 朱庆杰，张建龙，陈艳华，赵炫皓，万永华.常州市燃气管网破坏的人工神经网络预测模型[J].工业安全与环保，2020，46（2）：44-48. DOI：10.3969/j.issn.1001-425X.2020.02.011.
ZHU Q J, ZHANG J L, CHEN Y H, ZHAO X H, WAN Y H. Artificial network prediction model for gas pipeline network failure in Changzhou city[J]. Industrial Safety and Environmental Protection, 2020, 46(2): 44-48.
[15] 凌晓，徐鲁帅，余建平，梁瑞.基于改进的BP神经网络的输油管道内腐蚀速率预测[J].传感器与微系统，2021，40（2）：124-127. DOI：10.13873/J.1000-9787(2021)02-0124-04.
LING X, XU L S, YU J P, LIANG R. Prediction of corrosion rate in oil pipeline based on improved BP neural network[J]. Transducer and Microsystem Technologies, 2021, 40(2): 124-127.
[16] 肖荣鸽，王栋，王勤学.基于ASO-BP神经网络的海底油气管道腐蚀速率预测[J].化学工业与工程，2022，39（6）：109-116. DOI：10.13353/j.issn.1004.9533.20216004.
XIAO R G, WANG D, WANG Q X. Prediction of corrosion rate of submarine oil and gas pipelines based on ASO-BP neural network[J]. Chemical Industry and Engineering, 2022, 39(6): 109-116.
[17] RUMELHART D E, HINTON G E, WILLIAMS R J. Learning representations by back-propagating errors[J]. Nature, 1986, 323(6088): 533-536. DOI: 10.1038/323533a0.
[18] RUMELHART D E, MCCLELLAND J L, CORPORATE PDP Research Group. Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations[M]. Cambridge: MIT Press, 1986: 1-547.
[19] SRIVASTAVA N, HINTON G, KRIZHEVSKY A, SUTSKEVER I, SALAKHUTDINOV R. Dropout: a simple way to prevent neural networks from overfitting[J]. Journal of Machine Learning Research, 2014, 15(1): 1929-1958. DOI: 10.5555/2627435.2670313.
[20] 焦李成，杨淑媛，刘芳，王士刚，冯志玺.神经网络七十年：回顾与展望[J].计算机学报，2016，39（8）：1697-1716. DOI：10.11897/SP.J.1016.2016.01697.
JIAO L C, YANG S Y, LIU F, WANG S G, FENG Z X. Seventy years beyond neural networks: retrospect and prospect[J]. Chinese Journal of Computers, 2016, 39(8): 1697-1716.
[21] XUE J K, SHEN B. A novel swarm intelligence optimization approach: sparrow search algorithm[J]. Systems Science & Control Engineering, 2020, 8(1): 22-34. DOI: 10.1080/21642583.2019.1708830.
[22] ZHANG J N, XIA K W, HE Z P, YIN Z X, WANG S J. Semi-supervised ensemble classifier with improved sparrow search algorithm and its application in pulmonary nodule detection[J]. Mathematical Problems in Engineering, 2021, 2021: 6622935. DOI: 10.1155/2021/6622935.
[23] REN C Y, QIAO W, TIAN X. Natural gas pipeline corrosion rate prediction model based on BP Neural network[C]. Singapore: Fuzzy Engineering and Operations Research, 2012: 449-455.
[24] 郑度奎，胡晨章，蒲月华.基于人工神经网络的油气管道CO2腐蚀速率预测研究进展[J].热加工工艺，2021，50（18）：25-31. DOI：10.14158/j.cnki.1001-3814.20202208.
ZHENG D K, HU C Z, PU Y H. Research progress in prediction of CO2 corrosion rate of oil and gas pipeline based on artificial neural network[J]. Hot Working Technology, 2021, 50(18): 25-31.
[25] 钱敏，黄海松，范青松.基于反向策略的混沌麻雀搜索算法[J].计算机仿真，2022，39（8）：333-339，487. DOI：10.3969/j.issn.1006-9348.2022.08.065.
QIAN M, HUANG H S, FAN Q S. Chaotic sparrow search algorithm based on opposition-based strategy[J]. Computer Simulation, 2022, 39(8): 333-339, 487.
[26] TIZHOOSH H R. Opposition-based learning: a new scheme for machine intelligence[C]. Vienna: International Conference on Computational Intelligence for Modelling, Control and Automation and International Conference on Intelligent Agents, Web Technologies and Internet Commerce (CIMCA-IAWTIC'06), 2005: 695-701.
[27] 李爱莲，全凌翔，崔桂梅，解韶峰.融合正余弦和柯西变异的麻雀搜索算法[J].计算机工程与应用，2022，58（3）：91-99. DOI：10.3778/j.issn.1002-8331.2106-0148.
LI A L, QUAN L X, CUI G M, XIE S F. Sparrow search algorithm combining sine-cosine and Cauchy mutation[J]. Computer Engineering and Applications, 2022, 58(3): 91-99.
[28] MIRJALILI S. SCA: A sine cosine algorithm for solving optimization problems[J]. Knowledge-Based Systems, 2016, 96: 120-133. DOI: 10.1016/j.knosys.2015.12.022.
[29] 雍欣，高岳林，赫亚华，王惠敏.多策略融合的改进萤火虫算法[J].计算机应用，2022，42（12）：3847-3855. DOI：10.11772/j.issn.1001-9081.2021101830.
YONG X, GAO Y L, HE Y H, WANG H M. Improved firefly algorithm based on multi-strategy fusion[J]. Journal of Computer Applications, 2022, 42(12): 3847-3855.
[30] RASMUSSEN C E, WILLIAMS C K I. Gaussian processes for machine learning[M]. Cambridge: MIT Press, 2006: 79-102.

相似文献/References:

[1]党学博.海底管道腐蚀与剩余寿命的灰色预测[J].油气储运,2011,30(07):486.[doi:10.6047/j.issn.1000-8241.2011.07.002]
　Dang Xuebo.Prediction of corrosion and residual life of submarine pipeline with grey theory[J].Oil & Gas Storage and Transportation,2011,30(07):486.[doi:10.6047/j.issn.1000-8241.2011.07.002]
[2]赵佳丽?,吴长春,孙伶,等.基于最小二乘支持向量机的原油管道能耗预测[J].油气储运,2011,30(12):945.[doi:10.6047/j.issn.1000-8241.2011.12.017]
　Zhao Jiali,Wu Changchun,Sun Ling,et al.Energy consumption prediction of crude oil pipeline based on the least square support vector machine[J].Oil & Gas Storage and Transportation,2011,30(07):945.[doi:10.6047/j.issn.1000-8241.2011.12.017]
[3]朱本廷,吴明,陈军.基于灰色系统理论改进模型的储罐腐蚀速率预测[J].油气储运,2010,29(9):679.[doi:10.6047/j.issn.1000-8241.2010.09.011]
　Zhu Benting,Wu Ming,Chen Jun.Corrosion Rate Prediction of Tank Based on Modified Grey System Theory Model[J].Oil & Gas Storage and Transportation,2010,29(07):679.[doi:10.6047/j.issn.1000-8241.2010.09.011]
[4]于桂杰,付雷,赵清娜,等.累积法预测在役管道腐蚀极限厚度计算方法[J].油气储运,2011,30(08):643.[doi:10.6047/j.issn.1000-8241.2011.08.012]
　Yu Guijie,Fu Lei,Zhao Qingna,et al.Cumulative-sum method to predict the corrosion limit thickness of in-service pipeline[J].Oil & Gas Storage and Transportation,2011,30(07):643.[doi:10.6047/j.issn.1000-8241.2011.08.012]
[5]唐奕,范小霞,龚剑,等.付纳输气管道清管器运行距离和时间预测[J].油气储运,2010,29(8):627.[doi:10.6047/j.issn.1000-8241.2010.08.020]
　Tang Yi,Fan Xiaoxia,Gong Jian.Forecast on Running Distance and Time of Pig in FuNa Gas Transmission Pipeline[J].Oil & Gas Storage and Transportation,2010,29(07):627.[doi:10.6047/j.issn.1000-8241.2010.08.020]
[6]饶心,张国忠,胡月,等.人工神经网络预测含蜡原油的屈服应力[J].油气储运,2009,28(11):17.[doi:10.6047/j.issn.1000-8241.2009.11.003]
　RAO Xin,ZHANG Guozhong.Artificial Neural Network Model to Predict Yield Stress of Waxy Crude Oil[J].Oil & Gas Storage and Transportation,2009,28(07):17.[doi:10.6047/j.issn.1000-8241.2009.11.003]
[7]王帅华,秦晓霞,姬蕊,等.MATLAB神经网络在管道土壤腐蚀评价中的应用[J].油气储运,2009,28(11):57.[doi:10.6047/j.issn.1000-8241.2009.11.016]
　WANG Shuaihua,QIN Xiaoxia.Application of MATLAB Neural Network in Soil Corrosion Evaluation of Pipeline[J].Oil & Gas Storage and Transportation,2009,28(07):57.[doi:10.6047/j.issn.1000-8241.2009.11.016]
[8]杨静,叶帆.雅克拉气田集输管道腐蚀预测与防治[J].油气储运,2009,28(7):40.[doi:10.6047/j.issn.1000-8241.2009.07.012]
　YANG Jing,YE Fan.Prediction and Prevention of Corrosion in Gathering Lines of Yakela Condensate Gasfield[J].Oil & Gas Storage and Transportation,2009,28(07):40.[doi:10.6047/j.issn.1000-8241.2009.07.012]
[9]谭羽非,林涛.凝析气藏地下储气库单井注采能力分析[J].油气储运,2008,27(3):27.[doi:10.6047/j.issn.1000-8241.2008.03.007]
　TAN Yufei,LIN Tan.Analysis on the Single-well Capacity of Injection Withdrawal in Underground Gas Storage Reservoir[J].Oil & Gas Storage and Transportation,2008,27(07):27.[doi:10.6047/j.issn.1000-8241.2008.03.007]
[10]罗文华,周祥,吴岚,等.管道最大腐蚀坑深的极值统计方法及软件研制[J].油气储运,2007,26(8):34.[doi:10.6047/j.issn.1000-8241.2007.08.010]
　LUO Wenhua,ZHOU Xiang.Statistics of Extreme Value to Analyse the Maximum Depth of Corrosion Pit and Software Development[J].Oil & Gas Storage and Transportation,2007,26(07):34.[doi:10.6047/j.issn.1000-8241.2007.08.010]
[11]肖述辉,杜传甲,王成军.改进麻雀搜索算法优化BP神经网络管道腐蚀速率预测模型[J].油气储运,2024,43(07):760.[doi:10.6047/j.issn.1000-8241.2024.07.005]
　XIAO Shuhui,DU Chuanjia,WANG Chengjun.Pipeline corrosion rate prediction model using BP neural network based on improved sparrow search algorithm[J].Oil & Gas Storage and Transportation,2024,43(07):760.[doi:10.6047/j.issn.1000-8241.2024.07.005]

备注/Memo

基金项目：陕西省公益性地质调查项目“陕西省国有自然资源资产管理评价体系研究设计”，202202。
作者简介：肖述辉，男，1982年出生，高级工程师，2014年硕士毕业于西安石油大学机械工程专业，现主要从事油气储运管理方向的研究工作。地址：陕西省延安市宝塔区枣园街道枣园路延长石油公司，716000。电话：15319559459。E-mail：9109509@qq.com
通信作者：杜传甲，男，1993年出生，2017年硕士毕业于西安建筑科技大学工业工程专业，现主要从事复杂系统决策与分析方向的研究工作。地址：陕西省西安市碑林区西安建筑科技大学雁塔校区，710055。电话：18291862590。E-mail：cjdu@xauat.edu.cn

更新日期/Last Update: 2024-05-17