网站版权 © 《油气储运》编辑部 陕ICP备11014090号-10
地址：河北省廊坊市金光道51号（065000）；电话：0316-2176193 / 0316-2072055； 传真:0316-2177392； 网址：yqcy.paperonce.org
技术支持：西安三才科技实业有限公司 029-89381847；029-88222991
[1]宋福霖,赵弘,苗兴园.基于HMOGWO-RF的埋地管道点蚀深度机理-学习预测模型[J].油气储运,2024,43(11):1-17.
Song Fulin,Zhao Hong,Miao Xingyuan.Mechanism-learning prediction model for pitting corrosion depth of buried pipeline based on HMOGWO-RF[J].Oil & Gas Storage and Transportation,2024,43(11):1-17.
点击复制
Song Fulin,Zhao Hong,Miao Xingyuan.Mechanism-learning prediction model for pitting corrosion depth of buried pipeline based on HMOGWO-RF[J].Oil & Gas Storage and Transportation,2024,43(11):1-17.
基于HMOGWO-RF的埋地管道点蚀深度机理-学习预测模型
《油气储运》[ISSN:1000-8241/CN:13-1093/TE]
卷:
43
期数:
2024年11期
页码:
1-17
栏目:
出版日期:
2024-11-25
- Title:
- Mechanism-learning prediction model for pitting corrosion depth of buried pipeline based on HMOGWO-RF
- Keywords:
- buried pipeline; pitting depth; corrosion mechanism guidance; random forest; multi-objective grey wolf optimization; feature importance
- 分类号:
- TE832
- 文献标志码:
- A
- 摘要:
-
【目的】至2025年，中国油气管网规模将达到24×104 km，油气管道运输已然成为中国交通运输的重要方式之一。受管道周围土壤环境等因素影响，管道腐蚀现象时有发生，降低了管道的使用年限。为保障埋地管道的安全运行，需有效预测其所受腐蚀程度。【方法】将随机森林算法与多目标优化方法相结合，提出腐蚀机理引导下的埋地管道点蚀深度预测模型，将管道腐蚀的腐蚀机理知识引入到机器学习模型中，提高模型的可解释性。根据特征变量之间的交互作用机制，构建了新的特征变量，以更好地反映管道周围土壤环境的影响因素。通过随机森林算法中的基尼系数计算新特征空间中所有特征的重要性，利用混合多目标灰狼优化（Hybrid Multi-Objective Grey Wolf Optimization, HMOGWO）算法求解随机森林（Random Forest, RF）算法的最优超参数，并将特征选择融入多目标优化中。在多目标优化的过程中，综合考虑特征数量、预测准确率、模型稳定性3个优化目标，并设计综合评价指标，对比分析Pareto解集，以获取特征子集与最优超参数组合，得到最具代表性和优化性能的特征子集，提高模型稳定性与预测准确性。【结果】模型设计完成后，采用实际埋地管道的点蚀数据集对模型进行验证，三目标的HMOGWO算法与RF模型相结合后，模型的预测性能及稳定性远超三目标MOGWO算法、双目标HMOGWO算法、双目标MOGWO算法、单目标GWO算法与单目标PSO算法。【结论】该模型可以实现埋地管道最大点蚀深度的准确预测，所提出的腐蚀机理引导下的埋地管道点蚀深度预测模型可以提高管道腐蚀预测的可解释性与准确性，有助于延长管道的使用寿命，对于石油和天然气运输行业具有重要的应用实际意义。
- Abstract:
-
[Objective]According to the Medium and Long Term oil and Gas pipeline network planning, it is estimated that the scale of China's pipeline network will reach 240 000 kilometers in 2025, and now oil and gas pipeline transportation has become one of the important ways of transportation in China. However, due to the influence of soil environment and other factors around the pipeline, the corrosion phenomenon of the pipeline occurs from time to time, which reduces the service life of the pipeline. The main cause of pipeline accidents is the current part of the pipeline disrepair, resulting in A good deal of corrosion and leakage. Corrosion and leakage of pipelines have produced serious safety threats, and every pipeline accident has a great threat to the economy and safety of our country. [Methods]Therefore, this paper combines the random forest algorithm with the multi-objective optimization method to propose a prediction model for the pitting depth of buried pipeline under the guidance of corrosion mechanism. The knowledge of corrosion mechanism of pipeline corrosion is introduced into the machine learning model to improve the interpretability of the model. First, according to the interaction mechanism between the characteristic variables, new characteristic variables are constructed, which can better reflect the influencing factors of the soil environment around the pipeline. Secondly, through the calculation of the Gini coefficient of random forest algorithm of the importance of all the characteristics of the new feature space; Then, the Hybrid multi-objective grey Wolf optimization (HMOGWO) algorithm was used to solve the optimal hyperparameters of the Random Forest (RF) algorithm, and the feature selection was integrated into the multi-objective optimization. In the process of multi-objective optimization, we comprehensively consider the three optimization objectives of feature number, prediction accuracy and model stability. A comprehensive evaluation index was designed to compare and analyze the Pareto solution set to obtain the feature subset and the optimal hyperparameter combination, so as to obtain the most representative feature subset with optimized performance, thereby improving the stability and prediction accuracy of the model. Finally, we use the pitting erosion data set of actual buried pipelines to verify the proposed pitting erosion depth prediction model. [Results]The results show that the three-objective HMOGWO algorithm combined with RF model is far superior to other models in model prediction performance and model stability compared with the three-objective MOGWO algorithm, dual-objective HMOGWO algorithm, dual-objective MOGWO algorithm, single-objective GWO algorithm and single-objective PSO algorithm. [Conclusion]From what has been discussed above, the model can realize buried pipeline predict the maximum pitting depth, this paper proposed pitting corrosion mechanism under the guide of buried pipeline depth prediction model can improve the interpretability of pipeline corrosion prediction and accuracy and helps to prolong the service life of pipelines. This has so important application and practical significance for the oil and gas transportation industry in the actual working condition and development process. It has also laid some very important foundation for the future study of learning the mechanism of pitting erosion depth of buried pipelines - learning prediction methods.
参考文献/References:
[1] 李秋扬，赵明华，任学军，王乐乐，冯学书，牛亚琨.中国油气管道建设现状及发展趋势[J].油气田地面工程，2019，38（增刊1）：14-17. DOI：10.3969/j.issn.1006-6896.2019.z1.004.
LI Q Y, ZHAO M H, REN X J, WANG L L, FENG X S, NIU Y K. Construction status and development trend of Chinese oil & gas pipeline[J]. Oil-Gas Field Surface Engineering, 2019, 38(S1): 14-17.
[2] 吴志平，陈振华，戴联双，胡亚博，毕武喜.油气管道腐蚀检测技术发展现状与思考[J].油气储运，2020，39（8）：851-860. DOI：10.6047/j.issn.1000-8241.2020.08.002.
WU Z P, CHEN Z H, DAI L S, HU Y B, BI W X. Development status and thinking of oil and gas pipeline corrosion detection technology[J]. Oil & Gas Storage and Transportation, 2020, 39(8): 851-860.
[3] 骆正山，徐龙寅，骆济豪，王小完.改进SSA-LSSVM模型在埋地管道点蚀深度预测中的应用[J].安全与环境学报，2023，23（9）：3115-3122. DOI：10.13637/j.issn.1009-6094.2022.0395.
LUO Z S, XU L Y, LUO J H, WANG X W. Application of improved SSA-LSSVM model in prediction of pitting depth of buried pipelines[J]. Journal of Safety and Environment, 2023, 23(9): 3115-3122.
[4] SIM S, COLE I S, CHOI Y S, BIRBILIS N. A review of the protection strategies against internal corrosion for the safe transport of supercritical CO2 via steel pipelines for CCS purposes[J]. International Journal of Greenhouse Gas Control, 2014, 29: 185-199. DOI: 10.1016/j.ijggc.2014.08.010.
[5] CALEYO F, VELÁZQUEZ J C, VALOR A, HALLEN J M. Probability distribution of pitting corrosion depth and rate in underground pipelines: a Monte Carlo study[J]. Corrosion Science, 2009, 51(9): 1925-1934. DOI: 10.1016/j.corsci.2009.05.019.
[6] 史航.含点蚀埋地长输管道悬空沉降失效评估方法研究[D].大庆：东北石油大学，2023.
SHI H. Study on failure evaluation method of suspended settlement of long-distance pipeline with pitting corrosion[D]. Daqing: Northeast Petroleum University, 2023.
[7] LI X H, GUO M M, ZHANG R R, CHEN G M. A data-driven prediction model for maximum pitting corrosion depth of subsea oil pipelines using SSA-LSTM approach[J]. Ocean Engineering, 2022, 261: 112062. DOI: 10.1016/j.oceaneng.2022.112062.
[8] 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.
[9] PENG S B, ZHANG Z, LIU E B, LIU W, QIAO W B. A new hybrid algorithm model for prediction of internal corrosion rate of multiphase pipeline[J]. Journal of Natural Gas Science and Engineering, 2021, 85: 103716.
[10] 闻亚星，吕坦，国滨，王锋，陈金忠，马义来.基于CART-熵权法的管道腐蚀状态评估及其应用[J].腐蚀与防护，2023，44（9）：16-21，100. DOI：10.11973/fsyfh-202309003.
WEN Y X, LYU T, GUO B, WANG F, CHEN J Z, MA Y L. Evaluation and its application of pipeline corrosion status based on CART-entropy weight method[J]. Corrosion and Protection, 2023, 44(9): 16-21, 100.
[11] 吴明，谢飞，陈旭，王丹，孙东旭.埋地油气管道腐蚀失效研究进展及思考[J].油气储运，2022，41（6）：712-722. DOI：10.6047/j.issn.1000-8241.2022.06.013.
WU M, XIE F, CHEN X, WANG D, SUN D X. Research progress and thinking on corrosion failure of buried oil and gas pipelines[J]. Oil & Gas Storage and Transportation, 2022, 41(6): 712-722.
[12] 陈一诺，董绍华.基于随机森林算法的管道缺陷预测方法[J].油气储运，2018，37（9）：975-979. DOI：10.6047/j.issn.1000-8241.2018.09.003.
CHEN Y N, DONG S H. Pipeline defect prediction method based on Random Forests algorithm[J]. Oil & Gas Storage and Transportation, 2018, 37(9): 975-979.
[13] MIRJALILI S, SAREMI S, MIRJALILI S M, DOS S. COELHO L. Multi-objective grey wolf optimizer: a novel algorithm for multi-criterion optimization[J]. Expert Systems with Applications, 2016, 47: 106-119. DOI: 10.1016/j.eswa.2015.10.039.
[14] 黄文聪，张凤顺，胡滢，余文锦，常雨芳.基于IMOGWO算法的无线电能传输系统参数优化[J/OL].控制工程：1-9[2023-10-20].https://doi.org/10.14107/j.cnki.kzgc.20220596. DOI：10.14107/j.cnki.kzgc.20220596.
HUANG W C, ZHANG F S, HU Y, YU W J, CHANG Y F. Parameter optimization of wireless power transfer system based on IMOGWO algorithm[J/OL]. Control Engineering of China: 1-9[2023-10-20]. https://doi.org/10.14107/j.cnki.kzgc.20220596.
[15] AL-KAYSSI A W. Use of water retention data and soil physical quality index S to quantify hard-setting and degree of soil compactness indices of gypsiferous soils[J]. Soil and Tillage Research, 2021, 206: 104805. DOI: 10.1016/j.still.2020.104805.
[16] DE MELO L B B, SILVA B M, PEIXOTO D S, CHIARINI T P A, DE OLIVEIRA G C, CURI N. Effect of compaction on the relationship between electrical resistivity and soil water content in oxisol[J]. Soil and Tillage Research, 2021, 208: 104876. DOI: 10.1016/j.still.2020.104876.
[17] HUSSON O, HUSSON B, BRUNET A, BABRE D, ALARY K, SARTHOU J P, et al. Practical improvements in soil redox potential (Eh) measurement for characterisation of soil properties. Application for comparison of conventional and conservation agriculture cropping systems[J]. Analytica Chimica Acta, 2016, 906: 98-109. DOI: 10.1016/j.aca.2015.11.052.
[18] MIRJALILI S, MIRJALILI S M, LEWIS A. Grey wolf optimizer[J]. Advances in Engineering Software, 2014, 69: 46-61. DOI: 10.1016/j.advengsoft.2013.12.007.
[19] XIA Y Y, ZHANG C, WANG C X, LIU H J, SANG X X, LIU R, et al. Prediction of bending strength of glass fiber reinforced methacrylate-based pipeline UV-CIPP rehabilitation materials based on machine learning[J]. Tunnelling and Underground Space Technology, 2023, 140: 105319. DOI: 10.1016/j.tust.2023.105319.
[20] 方晓彤，张立涛，闫秀霞，董春肖.基于BAS-BP神经网络的医药供应链协同绩效智能评价[J].计算机应用与软件，2023，40（8）：59-66，113. DOI：10.3969/j.issn.1000-386x.2023.08.010.
FANG X T, ZHANG L T, YAN X X, DONG C X. Intelligent evaluation of pharmaceutical supply chain collaborative performance based on BAS-BP neural network[J]. Computer Applications and Software, 2023, 40(8): 59-66, 113.
[21] 梁海波，王怡，贾武升.基于机器学习的天然气钢质管道缺陷检测方法研究[J].安全与环境学报，2023，23（10）：3528-3537. DOI：10.13637/j.issn.1009-6094.2022.1150.
LIANG H B, WANG Y, JIA W S. Research on defect detection method for natural gas steel pipeline based on machine learning[J]. Journal of Safety and Environment, 2023, 23(10): 3528-3537.
[22] VELÁZQUEZ J C, CALEYO F, VALOR A, HALLEN J M. Predictive model for pitting corrosion in buried oil and gas pipelines[J]. Corrosion, 2009, 65(5): 332-342. DOI: 10.5006/1.3319138.
相似文献/References:
[1]周祥.埋地钢质管道外涂层缺陷的安全质量分级评价[J].油气储运,2011,30(04):299.[doi:10.6047/j.issn.1000-8241.2011.04.017]
Zhou Xiang.Safety quality grading evaluation on the external coating defects of buried steel pipeline[J].Oil & Gas Storage and Transportation,2011,30(11):299.[doi:10.6047/j.issn.1000-8241.2011.04.017]
[2]付吉强,吴明,杜明俊,等.埋地管道周围土壤湿热耦合相变过程的数值计算[J].油气储运,2011,30(01):30.[doi:10.6047/j.issn.1000-8241.2011.01.008]
Fu Jiqiang,Wu Ming,Du Mingjun,et al.Numerical calculation on heat-moisture coupling and phase change process of the soil around buried pipeline[J].Oil & Gas Storage and Transportation,2011,30(11):30.[doi:10.6047/j.issn.1000-8241.2011.01.008]
[3]陈杨,王为民,陈伟聪,等.基于故障树与模糊理论的埋地管道风险评价[J].油气储运,2011,30(07):481.[doi:10.6047/j.issn.1000-8241.2011.07.001]
Chen Yang,Wang Weimin,Chen Weicong,et al.Risk assessment of the buried pipeline based on the fault tree and fuzzy theory[J].Oil & Gas Storage and Transportation,2011,30(11):481.[doi:10.6047/j.issn.1000-8241.2011.07.001]
[4]胡士信,陆家榆,张本革,等.邻近强电线路管道交流干扰参数的测试方法[J].油气储运,2011,30(03):203.[doi:10.6047/j.issn.1000-8241.2011.03.012]
Hu Shixin,Lu Jiayu,Zhang Benge,et al.Test method of AC interference parameters for pipeline adjacent power transmission lines[J].Oil & Gas Storage and Transportation,2011,30(11):203.[doi:10.6047/j.issn.1000-8241.2011.03.012]
[5]李朝阳,马贵阳,刘亮.埋地输油管道泄漏油品扩散模拟[J].油气储运,2011,30(09):674.[doi:10.6047/j.issn.1000-8241.2011.09.008]
Li Zhaoyang,Ma Guiyang,Liu Liang,et al.Diffusion simulation on leaked oil for buried pipelines[J].Oil & Gas Storage and Transportation,2011,30(11):674.[doi:10.6047/j.issn.1000-8241.2011.09.008]
[6]王鸿膺,蒋涛,秦晓霞,等.川气东送管道土壤腐蚀埋片试验[J].油气储运,2010,29(10):769.[doi:10.6047/j.issn.1000-8241.2010.10.013]
Wang Hongying,Jiang Tao,Qin Xiaoxia.Field Coupon Testing on the Soil Corrosivity of Sichuan-East Gas Pipeline[J].Oil & Gas Storage and Transportation,2010,29(11):769.[doi:10.6047/j.issn.1000-8241.2010.10.013]
[7]薛致远,张丰,毕武喜,等.东北管网阴极保护通电/断电电位测量与分析[J].油气储运,2010,29(10):772.[doi:10.6047/j.issn.1000-8241.2010.10.014]
Xue Zhiyuan,Zhang Feng,Bi Wuxi.The Measurement and Analysis of On/Off-potential in Northeast Oil Pipeline Networks[J].Oil & Gas Storage and Transportation,2010,29(11):772.[doi:10.6047/j.issn.1000-8241.2010.10.014]
[8]刘仕鳌 蒲红宇 刘书文 蒋洪.埋地管道应力分析方法[J].油气储运,2012,31(4):274.[doi:10.6047/j.issn.1000-8241.2012.04.009]
Liu Shiao,Pu Hongyu,Liu Shuwen,et al.Stress analysis method of buried pipeline[J].Oil & Gas Storage and Transportation,2012,31(11):274.[doi:10.6047/j.issn.1000-8241.2012.04.009]
[9]吴峰,李向阳,张治军.埋地参数对管道同沟敷设传热的影响[J].油气储运,2010,29(11):835.[doi:10.6047/j.issn.1000-8241.2010.11.009]
Wu Feng,Li Xiangyang,Zhang Zhijun.Influence of Buried Parameters for Heat Transfer of Pipelines Laid in One Ditch[J].Oil & Gas Storage and Transportation,2010,29(11):835.[doi:10.6047/j.issn.1000-8241.2010.11.009]
[10]赵雄,周卫军,郭瑞.SPAE评价法在管道防腐层性能评价中的应用[J].油气储运,2009,28(11):54.[doi:10.6047/j.issn.1000-8241.2009.11.015]
ZHAO Xiong,ZHOU Weijun.Application of SPAE Method in Coating Performance Evaluation of Pipelines[J].Oil & Gas Storage and Transportation,2009,28(11):54.[doi:10.6047/j.issn.1000-8241.2009.11.015]
备注/Memo
基金项目：国家自然科学基金资助项目“海底油气管道封堵致振机理及气动减振控制方法研究”，51575528；中国石油大学（北京）前瞻导向及培育项目，2462022QEDX011。
作者简介：宋福霖，男，1998年生，在读博士生，2020年毕业于辽宁石油化工大学过程装备与控制工程专业，现主要从事无损检测研究方向。地址：北京市昌平区府学路18号，102249。电话：13342127149。Email：2379991464@qq.com
通信作者：赵弘，女，1975年生，教授，博士生导师，2003年博士毕业于西安交通大学机械电子工程专业，现主要从事无损检测研究方向。地址：北京市昌平区府学路18号，102299。电话：13522390529，Email：hzhao_cn@163.com
更新日期/Last Update:
2024-09-09