基于PSO-SVM模型的油气管道内腐蚀速率预测
|
摘要
目的针对油气管道的运行安全问题,建立油气管道内腐蚀速率预测新模型,对管道的内腐蚀状况进行准确预测。方法首先对内腐蚀的原理进行简单分析,探讨引起管道内腐蚀的主要原因。对PSO(粒子群算法)、SVM(支持向量机)以及PSO-SVM模型的原理及结构进行探讨,结合文献中获取的管道内腐蚀数据,使用PSO算法对SVM算法的参数C和g进行寻优。在此基础上,对Sine函数、Sigmoidal函数和Radial basis函数三种核函数进行对比优选。最终将PSO-SVM模型与GA-SVM模型、CV-SVM模型、LS-SVM模型和FOA-SVM模型四种模型进行预测误差对比,以此证明PSO-SVM模型的先进性。结果当SVM算法的参数C=83.9243、g=0.6972,核函数选择Sine函数时,PSO-SVM模型的平均绝对误差和均方根误差最小,平均绝对误差和均方根误差分别为0.58%和0.000618,但是该模型在使用的过程中,其训练数据所使用的时间为11.26 s,与GA-SVM模型、CV-SVM模型、LS-SVM模型和FOA-SVM模型四种模型相比,其预测误差较小,但训练数据所使用的时间较长。结论利用PSO-SVM模型对油气管道内腐蚀速率进行预测是可行的,预测误差相对较小,但是由于受限于数据训练速度问题,今后仍需要对该领域进行深入研究。
The work aims to establish a new prediction model of the corrosion rate in oil and gas pipelines for the operational safety problem of oil and gas pipelines, so as to accurately predict the internal corrosion conditions of pipelines. The principle of internal corrosion was firstly analyzed and the main causes of corrosion in pipelines were discussed. The principles and structures of PSO(particle swarm optimization), SVM(support vector machine) and PSO-SVM models were discussed. The parameters C and g of the SVM algorithm were optimized by PSO algorithm in combination with the internal corrosion data obtained in the pipeline. On the basis of this, the three kernel functions of the Sine function, the Sigmoidal function and the Radial basis function were compared and optimized. Finally, the prediction errors of the GA-SVM model, CV-SVM model, LS-SVM model and FOA-SVM model were compared to prove the advanced nature of the PSO-SVM model. When the SVM algorithm parameters C=83.9243, g=0.6972, and the kernel function was the Sine function, the average absolute error and root mean square error of the PSO-SVM model were the smallest, respectively 0.58% and 0.000 618, but the time for training data was11.26 s. Compared with the GA-SVM model, CV-SVM model, LS-SVM model and FOA-SVM model, the prediction error was small, but the training data took a long time. It is feasible to predict the corrosion rate in oil and gas pipelines by PSO-SVM model. The prediction error is relatively small, but due to the limitation of data training speed, it is still necessary to conduct in-depth research in this field.
The work aims to establish a new prediction model of the corrosion rate in oil and gas pipelines for the operational safety problem of oil and gas pipelines, so as to accurately predict the internal corrosion conditions of pipelines. The principle of internal corrosion was firstly analyzed and the main causes of corrosion in pipelines were discussed. The principles and structures of PSO(particle swarm optimization), SVM(support vector machine) and PSO-SVM models were discussed. The parameters C and g of the SVM algorithm were optimized by PSO algorithm in combination with the internal corrosion data obtained in the pipeline. On the basis of this, the three kernel functions of the Sine function, the Sigmoidal function and the Radial basis function were compared and optimized. Finally, the prediction errors of the GA-SVM model, CV-SVM model, LS-SVM model and FOA-SVM model were compared to prove the advanced nature of the PSO-SVM model. When the SVM algorithm parameters C=83.9243, g=0.6972, and the kernel function was the Sine function, the average absolute error and root mean square error of the PSO-SVM model were the smallest, respectively 0.58% and 0.000 618, but the time for training data was11.26 s. Compared with the GA-SVM model, CV-SVM model, LS-SVM model and FOA-SVM model, the prediction error was small, but the training data took a long time. It is feasible to predict the corrosion rate in oil and gas pipelines by PSO-SVM model. The prediction error is relatively small, but due to the limitation of data training speed, it is still necessary to conduct in-depth research in this field.
引文
[1]王海涛,孔明慧.三次指数平滑法预测管道腐蚀速率的应用[J].腐蚀与防护,2016,37(1):8-11.WANG Hai-tao,KONG Ming-hui.Application of cubic exponential smoothing method to pipeline corrosion rate forecasting[J].Corrosion&protection,2016,37(1):8-11.
[2]ZAGIDULLIN R N,ZAGIDULLIN S N,YAMALEEV RF,et al.Compositions for corrosion protection of chemical,petrochemical,and oil-and-gas equipment and pipelines[J].Chemical&petroleum engineering,2015,51(5):1-5.
[3]VANAEI H R,ESLAMI A,EGBEWANDE A.A review on pipeline corrosion,in-line inspection(ILI),and corrosion growth rate models[J].International journal of pressure vessels&piping,2017,149:43-54.
[4]宫川宝.天然气长输管道腐蚀分析与防控措施[J].腐蚀与防护,2017,38(7):562-565.GONG Chuan-bao.Corrosion analysis and control measures of long distance natural gas pipeline[J].Corrosion&protection,2017,38(7):562-565.
[5]刘晓东,李著信.基于灰色组合模型的管道腐蚀速率预测[J].压力容器,2007,24(3):15-19.LIU Xiao-dong,LI Zhu-xin.Predicting corrosion rate of pipeline based on grey combinatorial model[J].Pressure vessel technology,2007,24(3):15-19.
[6]石红艳,甘淳静,王志彬,等.基于复化Simpson公式和插值的管道腐蚀速率预测[J].天然气与石油,2008,26(5):33-37.SHI Hong-yan,GAN Chun-jing,WANG Zhi-bin,et al.Application of GM(1,1)model in corrosion predication of oil and gas pipelines based on duplicated simpson formula and interpolation[J].Natural gas and oil,2008,26(5):33-37.
[7]章玉婷,杨剑锋.基于BP神经网络的管道腐蚀速率预测[J].全面腐蚀控制,2013(9):67-71.ZHANG Yu-ting,YANG Jian-feng.Corrosion rate prediction of pipeline based on BP artificial neural network[J].Total corrosion control,2013(9):67-71.
[8]刘宏波,王书淼,高铸,等.CO2?H2S对油气管道内腐蚀影响机制[J].油气储运,2007,26(12):43-46.LIU Hong-bo,WANG Shu-miao,GAO Zhu,et al.Study on the internal corrosion mechanism of CO2?H2S to oil/gas pipelines[J].Oil&gas storage and transportation,2007,26(12):43-46.
[9]王丹,袁世娇,吴小卫,等.油气管道CO2/H2S腐蚀及防护技术研究进展[J].表面技术,2016,45(3):31-37.WANG Dan,YUAN Shi-jiao,WU Xiao-wei,et al.Research progress of CO2/H2S corrosion in oil and gas pipelines and the protection techniques[J].Surface technology,2016,45(3):31-37.
[10]程远鹏,李自力,毕海胜,等.含油集输管道CO2腐蚀速率预测的研究进展[J].腐蚀与防护,2015,36(3):207-212.CHENG Yuan-peng,LI Zi-li,BI Hai-sheng,et al.Progress in prediction of CO2 corrosion rate affected by oil in gathering pipelines[J].Corrosion&protection,2015,36(3):207-212.
[11]郑东宏,车得福,贺林,等.油气管道CO2腐蚀过程中弹状流的影响[J].腐蚀与防护,2007,28(2):77-81.ZHENG Dong-hong,CHE De-fu,HE Lin,et al.Effect of slug flow on CO2 corrosion of pipelines in oil and gas industry[J].Corrosion&protection,2007,28(2):77-81.
[12]WAN M A M Z,AZIZ I A,HARON N S,et al.CO2 corrosion rate determination mechanism implementing de Waard-Milliams model for oil&gas pipeline[C]//20163rd International Conference on Computer and Information Sciences.[s.l.]:IEEE,2016:298-303.
[13]OSSAI C I,BOSWELL B,DAVIES I J.Modelling the effects of production rates and physico-chemical parameters on pitting rate and pit depth growth of onshore oil and gas pipelines[J].British corrosion journal,2016,51(5):342-351.
[14]王丹,谢飞,吴明,等.硫化氢环境中管道钢的腐蚀及防护[J].油气储运,2009,28(9):10-13.WANG Dan,XIE Fei,WU Ming,et al.Corrosion and corrosion control of pipe steel in hydrogen sulfide environment[J].Oil&gas storage and transportation,2009,28(9):10-13.
[15]王晶,栾春波.硫化氢腐蚀对X80管线钢断裂韧性的影响[J].材料研究学报,2016,30(3):179-185.WANG Jing,LUAN Chun-bo.Effect of hydrogen sulfide corrosion on fracture toughness of X80 pipeline steel[J].Chinese journal of materials research,2016,30(3):179-185.
[16]吴庆伟,王金龙,张平.基于FOA-SVM模型的输油管道内腐蚀速率预测[J].腐蚀与防护,2017,38(9):732-736.WU Qing-wei,WANG Jin-long,ZHANG Ping.Prediction of oil pipeline internal corrosion rate based on FOA-SVM model[J].Corrosion&protection,2017,38(9):732-736.
[17]POURBASHEER E,AALIZADEH R,MOHAMMAD RG,et al.QSAR study ofα1β4 integrin inhibitors by GA-MLR and GA-SVM methods[J].Structural chemistry,2014,25(1):355-370.
[18]DUCHêNE S,DUCHêNE D A,GIALLONARDO F D,et al.Cross-validation to select bayesian hierarchical models in phylogenetics[J].Bmcevolutionary biology,2016,16(1):1-8.
[19]CHAUCHARD F,SVENSSON J,AXELSSON J,et al.Localization of embedded inclusions using detection of fluorescence:Feasibility study based on simulation data,LS-SVM modeling and EPO pre-processing[J].Chemometrics&intelligent laboratory systems,2008,91(1):34-42.
[20]SUDHEER C,MAHESWARAN R,PANIGRAHI B K,et al.A hybrid SVM-PSO model for forecasting monthly streamflow[J].Neural computing&applications,2014,24(6):1381-1389.
[21]刘广迎,李翔.基于SVM模型的中国电力需求预测[J].制造业自动化,2010,32(3):159-162.LIU Guang-ying,LI Xiang.SVM-based models for forecasting electricity demand in china[J].Manufacturing automation,2010,32(3):159-162.
[2]ZAGIDULLIN R N,ZAGIDULLIN S N,YAMALEEV RF,et al.Compositions for corrosion protection of chemical,petrochemical,and oil-and-gas equipment and pipelines[J].Chemical&petroleum engineering,2015,51(5):1-5.
[3]VANAEI H R,ESLAMI A,EGBEWANDE A.A review on pipeline corrosion,in-line inspection(ILI),and corrosion growth rate models[J].International journal of pressure vessels&piping,2017,149:43-54.
[4]宫川宝.天然气长输管道腐蚀分析与防控措施[J].腐蚀与防护,2017,38(7):562-565.GONG Chuan-bao.Corrosion analysis and control measures of long distance natural gas pipeline[J].Corrosion&protection,2017,38(7):562-565.
[5]刘晓东,李著信.基于灰色组合模型的管道腐蚀速率预测[J].压力容器,2007,24(3):15-19.LIU Xiao-dong,LI Zhu-xin.Predicting corrosion rate of pipeline based on grey combinatorial model[J].Pressure vessel technology,2007,24(3):15-19.
[6]石红艳,甘淳静,王志彬,等.基于复化Simpson公式和插值的管道腐蚀速率预测[J].天然气与石油,2008,26(5):33-37.SHI Hong-yan,GAN Chun-jing,WANG Zhi-bin,et al.Application of GM(1,1)model in corrosion predication of oil and gas pipelines based on duplicated simpson formula and interpolation[J].Natural gas and oil,2008,26(5):33-37.
[7]章玉婷,杨剑锋.基于BP神经网络的管道腐蚀速率预测[J].全面腐蚀控制,2013(9):67-71.ZHANG Yu-ting,YANG Jian-feng.Corrosion rate prediction of pipeline based on BP artificial neural network[J].Total corrosion control,2013(9):67-71.
[8]刘宏波,王书淼,高铸,等.CO2?H2S对油气管道内腐蚀影响机制[J].油气储运,2007,26(12):43-46.LIU Hong-bo,WANG Shu-miao,GAO Zhu,et al.Study on the internal corrosion mechanism of CO2?H2S to oil/gas pipelines[J].Oil&gas storage and transportation,2007,26(12):43-46.
[9]王丹,袁世娇,吴小卫,等.油气管道CO2/H2S腐蚀及防护技术研究进展[J].表面技术,2016,45(3):31-37.WANG Dan,YUAN Shi-jiao,WU Xiao-wei,et al.Research progress of CO2/H2S corrosion in oil and gas pipelines and the protection techniques[J].Surface technology,2016,45(3):31-37.
[10]程远鹏,李自力,毕海胜,等.含油集输管道CO2腐蚀速率预测的研究进展[J].腐蚀与防护,2015,36(3):207-212.CHENG Yuan-peng,LI Zi-li,BI Hai-sheng,et al.Progress in prediction of CO2 corrosion rate affected by oil in gathering pipelines[J].Corrosion&protection,2015,36(3):207-212.
[11]郑东宏,车得福,贺林,等.油气管道CO2腐蚀过程中弹状流的影响[J].腐蚀与防护,2007,28(2):77-81.ZHENG Dong-hong,CHE De-fu,HE Lin,et al.Effect of slug flow on CO2 corrosion of pipelines in oil and gas industry[J].Corrosion&protection,2007,28(2):77-81.
[12]WAN M A M Z,AZIZ I A,HARON N S,et al.CO2 corrosion rate determination mechanism implementing de Waard-Milliams model for oil&gas pipeline[C]//20163rd International Conference on Computer and Information Sciences.[s.l.]:IEEE,2016:298-303.
[13]OSSAI C I,BOSWELL B,DAVIES I J.Modelling the effects of production rates and physico-chemical parameters on pitting rate and pit depth growth of onshore oil and gas pipelines[J].British corrosion journal,2016,51(5):342-351.
[14]王丹,谢飞,吴明,等.硫化氢环境中管道钢的腐蚀及防护[J].油气储运,2009,28(9):10-13.WANG Dan,XIE Fei,WU Ming,et al.Corrosion and corrosion control of pipe steel in hydrogen sulfide environment[J].Oil&gas storage and transportation,2009,28(9):10-13.
[15]王晶,栾春波.硫化氢腐蚀对X80管线钢断裂韧性的影响[J].材料研究学报,2016,30(3):179-185.WANG Jing,LUAN Chun-bo.Effect of hydrogen sulfide corrosion on fracture toughness of X80 pipeline steel[J].Chinese journal of materials research,2016,30(3):179-185.
[16]吴庆伟,王金龙,张平.基于FOA-SVM模型的输油管道内腐蚀速率预测[J].腐蚀与防护,2017,38(9):732-736.WU Qing-wei,WANG Jin-long,ZHANG Ping.Prediction of oil pipeline internal corrosion rate based on FOA-SVM model[J].Corrosion&protection,2017,38(9):732-736.
[17]POURBASHEER E,AALIZADEH R,MOHAMMAD RG,et al.QSAR study ofα1β4 integrin inhibitors by GA-MLR and GA-SVM methods[J].Structural chemistry,2014,25(1):355-370.
[18]DUCHêNE S,DUCHêNE D A,GIALLONARDO F D,et al.Cross-validation to select bayesian hierarchical models in phylogenetics[J].Bmcevolutionary biology,2016,16(1):1-8.
[19]CHAUCHARD F,SVENSSON J,AXELSSON J,et al.Localization of embedded inclusions using detection of fluorescence:Feasibility study based on simulation data,LS-SVM modeling and EPO pre-processing[J].Chemometrics&intelligent laboratory systems,2008,91(1):34-42.
[20]SUDHEER C,MAHESWARAN R,PANIGRAHI B K,et al.A hybrid SVM-PSO model for forecasting monthly streamflow[J].Neural computing&applications,2014,24(6):1381-1389.
[21]刘广迎,李翔.基于SVM模型的中国电力需求预测[J].制造业自动化,2010,32(3):159-162.LIU Guang-ying,LI Xiang.SVM-based models for forecasting electricity demand in china[J].Manufacturing automation,2010,32(3):159-162.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |