基于KPCA-BAS-GRNN的埋地管道外腐蚀速率预测
|
摘要
目的提高埋地管道外腐蚀速率的预测精度。方法建立基于核主成分分析法(KPCA)和天牛须搜索(BAS)算法优化的广义回归神经网络(GRNN)腐蚀速率预测模型,通过KPCA对原始数据进行预处理,提取影响管道外腐蚀的主要因素,应用GRNN建立埋地管道外腐蚀速率预测的数学模型,并采用BAS算法对模型进行优化,减小了人为设置参数的影响。以川气东送埋地管段为例,分析选取出12种关键影响因素,建立了埋地管道外腐蚀指标体系,借助MATLAB-R2014a编写程序进行仿真,并与实际值进行对比。结果模型的预测结果与实际值基本一致,KPCA可有效降低指标体系的维度,提取出包含原始信息97.9%的3个主因素—土壤电阻率、氧化还原电位、氯离子含量,简化了运算过程。采用的BAS-GRNN模型将预测精度提高到7.83%以内,平均相对误差5.21%,决定系数取值0.93。与其他模型相比,该模型性能较好,预测精度更高。结论采用KPCA提取的主要影响因素符合工程实际,建立的BAS-GRNN模型预测精度高,有较好的适应性,为埋地管道外腐蚀速率预测提供了新思路,对管道的维护更新工作提供了参考依据。
The work aims to improve the prediction accuracy of the external corrosion rate of buried pipeline. The corrosion rate prediction model of buried pipeline was established based on kernel principal component analysis(KPCA) and the general regression neural network(GRNN) optimized by Beetle antennae search(BAS) algorithm. The main factors affecting external corrosion of buried pipeline were extracted by preprocessing the original data through KPCA. GRNN was used to build a mathematical model to predict the external corrosion rate of buried pipeline and BAS algorithm was adopted to optimize the model to reduce the effects of artificially set parameters. In addition, the pipelines buried in natural gas transmission project from Sichuan to East were utilized as an example to analyze 12 key influencing factors and establish the external corrosion index system of buried pipeline. MATLAB-R2014 a software was used for simulation processing, and compared with the actual values. The predicted results of the model were basically consistent with the actual values. KPCA could effectively reduce the dimensions of the indicator system and extract three main factors with 97.9% original information, including soil resistivity, oxidation-reduction potential and Cl-content. Thus, the calculation process was simplified. BAS-GRNN model was adopted to improve the prediction accuracy to 7.83%. The average relative error was 5.21%, and the determination coefficient was 0.93. Compared with other models, this model had better performance and higher prediction accuracy. Thus, the main influencing factors extracted by KPC Accord with engineering practice. BAS-GRNN model provides a new idea for the prediction of external corrosion rate of buried pipeline and a reference basis for the maintenance and updating of buried pipeline by higher precision and better adaptability.
The work aims to improve the prediction accuracy of the external corrosion rate of buried pipeline. The corrosion rate prediction model of buried pipeline was established based on kernel principal component analysis(KPCA) and the general regression neural network(GRNN) optimized by Beetle antennae search(BAS) algorithm. The main factors affecting external corrosion of buried pipeline were extracted by preprocessing the original data through KPCA. GRNN was used to build a mathematical model to predict the external corrosion rate of buried pipeline and BAS algorithm was adopted to optimize the model to reduce the effects of artificially set parameters. In addition, the pipelines buried in natural gas transmission project from Sichuan to East were utilized as an example to analyze 12 key influencing factors and establish the external corrosion index system of buried pipeline. MATLAB-R2014 a software was used for simulation processing, and compared with the actual values. The predicted results of the model were basically consistent with the actual values. KPCA could effectively reduce the dimensions of the indicator system and extract three main factors with 97.9% original information, including soil resistivity, oxidation-reduction potential and Cl-content. Thus, the calculation process was simplified. BAS-GRNN model was adopted to improve the prediction accuracy to 7.83%. The average relative error was 5.21%, and the determination coefficient was 0.93. Compared with other models, this model had better performance and higher prediction accuracy. Thus, the main influencing factors extracted by KPC Accord with engineering practice. BAS-GRNN model provides a new idea for the prediction of external corrosion rate of buried pipeline and a reference basis for the maintenance and updating of buried pipeline by higher precision and better adaptability.
引文
[1]VANAEIH 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 and piping,2017,149:43-54.
[2]李斌,邢希金,张鑫,等.酸性环境下溶解氧对低合金管材点蚀的影响[J].表面技术,2017,46(3):246-252.LI Bin,XING Xi-jin,ZHANG Xin,et al.Effects of dissolved oxygen on pitting of low alloy tubes in acidic environment[J].Surface technology,2017,46(3):246-252.
[3]李兆玲,杨任继,陈浩.氯离子和直流电流密度对X65钢的腐蚀研究[J].表面技术,2017,46(8):254-258.LI Zhao-ling,YANG Ren-ji,CHEN Hao.Corrosion of X65steel under influence of Cl-and direct current density[J].Surface technology,2017,46(8):254-258.
[4]谭才渊,殷启帅,杨进,等.渤海某油田L80油管腐蚀机理研究[J].表面技术,2017,46(3):236-245.TAN Cai-yuan,YIN Qi-shuai,YANG Jin,et al.Corrosion mechanism of L80 tubing in a Bohai oilfield[J].Surface technology,2017,46(3):236-245.
[5]VELAZQUEZ J C,CALEYO F,VALOR A,et al.Predictive model for pitting corrosion in buried oil and gas pipelines[J].Corrosion,2009,65(5):332-342.
[6]毕傲睿,骆正山,王小完,等.基于土壤腐蚀主成分的金属管道退化维纳过程研究[J].材料保护,2018,51(1):37-42.BI Ao-rui,LUO Zheng-shan,WANG Xiao-wan,et al.Wiener process of degradation of metal pipelines based on principal components of soil corrosion[J].Materials protection,2018,51(1):37-42.
[7]陈健飞,王孟,江文军,等.基于灰色关联度的埋地管道检测数据分析[J].表面技术,2017,46(4):264-269.CHEN Jian-fei,WANG Meng,JIANG Wen-jun,et al.Buried pipeline detection date analysis based on grey correlation[J].Surface technology,2017,46(4):264-269.
[8]张杰.基于主成分-聚类分析法的管道风险评价方法[J].油气储运,2014,33(2):139-143.ZHANG Jie.Pipeline risk assessment method based on principle component-clustering analysis[J].Oil&gas storage and transportation,2014,33(2):139-143.
[9]JAIN S,SANCHEZ A N,GUAN S,et al.Probabilistic assessment of external corrosion rates in buried oil and gas pipelines[C]//2015 International Corrosion Conference Series.Naperville:NACE,2015.
[10]李丽,李晓刚,邢士波,等.BP人工神经网络对国内典型地区碳钢土壤腐蚀的预测研究[J].腐蚀科学与防护技术,2013,25(5):372-376.LI Li,LI Xiao-gang,XING Shi-bo,et al.Research on soil corrosion rate prediction of carbon steel in typical Chinese cities based on BP artificial neural network[J].Corrosion science and protection technology,2013,25(5):372-376.
[11]MENG Q,MA X,ZHOU Y.Forecasting of coal seam gas content by using support vector regression based on particle swarm optimization[J].Journal of natural gas science&engineering,2014,21(21):71-78.
[12]贾义鹏,吕庆,尚岳全.基于粒子群算法和广义回归神经网络的岩爆预测[J].岩石力学与工程学报,2013,32(2):343-348.JIA Yi-peng,LV Qing,SHANG Yue-quan.Rock burst prediction using particle swarm optimization algorithm and general regression neural network[J].Chinese journal of rock mechanics and engineering,2013,32(2):343-348.
[13]WANG Hai-xian,HU Zi-lan.An unified EM algorithm for PCA and KPCA[J].Neurocomputing,2007,71(1):459-462.
[14]程砚秋,迟国泰.基于核主成分分析的生态评价模型及其应用研究[J].中国管理科学,2011,19(3):182-192.CHENG Yan-qiu,CHI Guo-tai.The ecosystem evaluation model based on kernel principle component analysis and its applications[J].Chinese journal of management science,2011,19(3):182-192.
[15]张钦礼,王兢,王新民.基于核主成分分析法与PSO-SVW的填充管道失效风险性分级评价模型[J].黄金科学技术,2017,25(3):70-76.ZHANG Qin-li,WANG Jing,WANG Xin-min.Failure risk assessment model of filling pipeline based on KPCA and PSO-SVW[J].Gold science and technology,2017,25(3):70-76.
[16]王晓丽,魏志兵,彭士涛,等.基于主成分分析法的液体管道泄漏后果综合评价模型[J].中国安全生产科学技术,2014,10(5):84-89.WANG Xiao-li,WEI Zhi-bing,PENG Shi-tao,et al.Comprehensive assessment model of liquid pipeline leakage consequences based on principle component analysis[J].Journal of safety science and technology,2014,10(5):84-89.
[17]WANG Shao-fu,ZHANG Jin-lei,ZHAO Shi-jun,et al.The generalized regression network and its application to predictive control[J].Microelectronics&computer,2009,26(6):32-35.
[18]林喆,兰生,张宇航.基于广义回归神经网络的油纸绝缘变压器的寿命预测[J].高压电器,2015,51(2):125-130.LIN Zhe,LAN Sheng,ZHANG Yu-hang.Life prediction of oil paper insulation of transformer based on GRNNneural network[J].High voltage apparatus,2015,51(2):125-130.
[19]JIANG X Y,LI S.BAS:beet lean tennae search algorithm for optimization problems[J].Neural and evolutionary,2017,1710:10724.
[20]JIANG X Y,LI S.Beetle antennae search without parameter tuning(BAS-WPT)for multi-objective optimization[J].Neural and evolutionary,2017,1711:02395.
[21]王甜甜,刘强.基于BAS-BP模型的风暴潮灾害损失预测[J].海洋环境科学,2018,37(3):457-463.WANG Tian-tian,LIU Qiang.The assessment of storm surge disaster loss based on BAS-BP model[J].Marine environmental science,2018,37(3):457-463.
[22]任帅,张琪,王东.基于主分量法的管道腐蚀评价-以川气东送管道为例[J].油气储运,2015,34(5):519-523.REN Shuai,ZHANG Qi,WANG Dong.Pipeline corrosivity assessment based on principal component analysis-take the Sichuan-east gas transmission pipeline as an example[J].Oil&gas storage and transportation,2015,34(5):519-523.
[23]骆正山,毕傲睿,王小完.基于PCA-SVM的高含硫油气混输管道腐蚀预测[J].中国安全科学学报,2016,26(2):85-90.LUO Zheng-shan,BI Ao-rui,WANG Xiao-wan.Corrosion prediction of high sulfur gas-oil mixed transmission pipelines based on PCA-SVM[J].China safety science journal,2016,26(2):85-90.
[2]李斌,邢希金,张鑫,等.酸性环境下溶解氧对低合金管材点蚀的影响[J].表面技术,2017,46(3):246-252.LI Bin,XING Xi-jin,ZHANG Xin,et al.Effects of dissolved oxygen on pitting of low alloy tubes in acidic environment[J].Surface technology,2017,46(3):246-252.
[3]李兆玲,杨任继,陈浩.氯离子和直流电流密度对X65钢的腐蚀研究[J].表面技术,2017,46(8):254-258.LI Zhao-ling,YANG Ren-ji,CHEN Hao.Corrosion of X65steel under influence of Cl-and direct current density[J].Surface technology,2017,46(8):254-258.
[4]谭才渊,殷启帅,杨进,等.渤海某油田L80油管腐蚀机理研究[J].表面技术,2017,46(3):236-245.TAN Cai-yuan,YIN Qi-shuai,YANG Jin,et al.Corrosion mechanism of L80 tubing in a Bohai oilfield[J].Surface technology,2017,46(3):236-245.
[5]VELAZQUEZ J C,CALEYO F,VALOR A,et al.Predictive model for pitting corrosion in buried oil and gas pipelines[J].Corrosion,2009,65(5):332-342.
[6]毕傲睿,骆正山,王小完,等.基于土壤腐蚀主成分的金属管道退化维纳过程研究[J].材料保护,2018,51(1):37-42.BI Ao-rui,LUO Zheng-shan,WANG Xiao-wan,et al.Wiener process of degradation of metal pipelines based on principal components of soil corrosion[J].Materials protection,2018,51(1):37-42.
[7]陈健飞,王孟,江文军,等.基于灰色关联度的埋地管道检测数据分析[J].表面技术,2017,46(4):264-269.CHEN Jian-fei,WANG Meng,JIANG Wen-jun,et al.Buried pipeline detection date analysis based on grey correlation[J].Surface technology,2017,46(4):264-269.
[8]张杰.基于主成分-聚类分析法的管道风险评价方法[J].油气储运,2014,33(2):139-143.ZHANG Jie.Pipeline risk assessment method based on principle component-clustering analysis[J].Oil&gas storage and transportation,2014,33(2):139-143.
[9]JAIN S,SANCHEZ A N,GUAN S,et al.Probabilistic assessment of external corrosion rates in buried oil and gas pipelines[C]//2015 International Corrosion Conference Series.Naperville:NACE,2015.
[10]李丽,李晓刚,邢士波,等.BP人工神经网络对国内典型地区碳钢土壤腐蚀的预测研究[J].腐蚀科学与防护技术,2013,25(5):372-376.LI Li,LI Xiao-gang,XING Shi-bo,et al.Research on soil corrosion rate prediction of carbon steel in typical Chinese cities based on BP artificial neural network[J].Corrosion science and protection technology,2013,25(5):372-376.
[11]MENG Q,MA X,ZHOU Y.Forecasting of coal seam gas content by using support vector regression based on particle swarm optimization[J].Journal of natural gas science&engineering,2014,21(21):71-78.
[12]贾义鹏,吕庆,尚岳全.基于粒子群算法和广义回归神经网络的岩爆预测[J].岩石力学与工程学报,2013,32(2):343-348.JIA Yi-peng,LV Qing,SHANG Yue-quan.Rock burst prediction using particle swarm optimization algorithm and general regression neural network[J].Chinese journal of rock mechanics and engineering,2013,32(2):343-348.
[13]WANG Hai-xian,HU Zi-lan.An unified EM algorithm for PCA and KPCA[J].Neurocomputing,2007,71(1):459-462.
[14]程砚秋,迟国泰.基于核主成分分析的生态评价模型及其应用研究[J].中国管理科学,2011,19(3):182-192.CHENG Yan-qiu,CHI Guo-tai.The ecosystem evaluation model based on kernel principle component analysis and its applications[J].Chinese journal of management science,2011,19(3):182-192.
[15]张钦礼,王兢,王新民.基于核主成分分析法与PSO-SVW的填充管道失效风险性分级评价模型[J].黄金科学技术,2017,25(3):70-76.ZHANG Qin-li,WANG Jing,WANG Xin-min.Failure risk assessment model of filling pipeline based on KPCA and PSO-SVW[J].Gold science and technology,2017,25(3):70-76.
[16]王晓丽,魏志兵,彭士涛,等.基于主成分分析法的液体管道泄漏后果综合评价模型[J].中国安全生产科学技术,2014,10(5):84-89.WANG Xiao-li,WEI Zhi-bing,PENG Shi-tao,et al.Comprehensive assessment model of liquid pipeline leakage consequences based on principle component analysis[J].Journal of safety science and technology,2014,10(5):84-89.
[17]WANG Shao-fu,ZHANG Jin-lei,ZHAO Shi-jun,et al.The generalized regression network and its application to predictive control[J].Microelectronics&computer,2009,26(6):32-35.
[18]林喆,兰生,张宇航.基于广义回归神经网络的油纸绝缘变压器的寿命预测[J].高压电器,2015,51(2):125-130.LIN Zhe,LAN Sheng,ZHANG Yu-hang.Life prediction of oil paper insulation of transformer based on GRNNneural network[J].High voltage apparatus,2015,51(2):125-130.
[19]JIANG X Y,LI S.BAS:beet lean tennae search algorithm for optimization problems[J].Neural and evolutionary,2017,1710:10724.
[20]JIANG X Y,LI S.Beetle antennae search without parameter tuning(BAS-WPT)for multi-objective optimization[J].Neural and evolutionary,2017,1711:02395.
[21]王甜甜,刘强.基于BAS-BP模型的风暴潮灾害损失预测[J].海洋环境科学,2018,37(3):457-463.WANG Tian-tian,LIU Qiang.The assessment of storm surge disaster loss based on BAS-BP model[J].Marine environmental science,2018,37(3):457-463.
[22]任帅,张琪,王东.基于主分量法的管道腐蚀评价-以川气东送管道为例[J].油气储运,2015,34(5):519-523.REN Shuai,ZHANG Qi,WANG Dong.Pipeline corrosivity assessment based on principal component analysis-take the Sichuan-east gas transmission pipeline as an example[J].Oil&gas storage and transportation,2015,34(5):519-523.
[23]骆正山,毕傲睿,王小完.基于PCA-SVM的高含硫油气混输管道腐蚀预测[J].中国安全科学学报,2016,26(2):85-90.LUO Zheng-shan,BI Ao-rui,WANG Xiao-wan.Corrosion prediction of high sulfur gas-oil mixed transmission pipelines based on PCA-SVM[J].China safety science journal,2016,26(2):85-90.