基于人工蜂群算法优化的SVM管道风险评估
|
摘要
管道风险评估是管道风险管理的重要组成部分,其目的是通过对风险的调查和分析,识别可能导致管道事故的重要因素,使得管道风险管理更加科学化。为了对管道日常运行状态风险进行准确评估,提出了一种利用人工蜂群算法优化的支持向量机(Support Vector Machine,SVM)管道安全风险评估方法:建立管道风险评估模型,从工艺运行角度收集成品油管道、正反输原油管道、掺混输送原油管道的工艺运行特征,并形成样本特征集合。对这4种类型管道的特征集合进行试验验证,结果表明:在小样本情况下,采用基于人工蜂群算法优化的SVM管道风险评估方法正确率较高,并具有良好的普适性,能够根据管道实际运行状态给出正确的风险评估结果。(图3,表1,参21)
Pipeline risk assessment is one important part of pipeline risk management, and it is aimed at identifying the important factors that possibly lead to pipeline accidents by means of risk investigation and analysis to make the pipeline risk management more scientific. In this paper, an optimized SVM(Support Vector Machine) pipeline risk assessment method based on artificial bee colony algorithm was proposed in order to carry out accurate assessment on pipeline risks in the state of daily operation. In this method, the pipeline risk assessment model is established, the technological operation characteristics of products pipelines, forward/backward crude oil pipelines and mixed-transportation crude oil pipelines are collected from the viewpoint of technological operation, and the sample characteristic set is built up. Then, 4 types of pipeline characteristic sets were tested. It is indicated that in the case of small sample, the optimized SVM pipeline risk assessment method based on artificial bee colony algorithm has higher accuracy and good applicability, and it can provide the accurate risk assessment result according to the actual running state of pipelines.(3 Figures, 1 Table, 21 References)
Pipeline risk assessment is one important part of pipeline risk management, and it is aimed at identifying the important factors that possibly lead to pipeline accidents by means of risk investigation and analysis to make the pipeline risk management more scientific. In this paper, an optimized SVM(Support Vector Machine) pipeline risk assessment method based on artificial bee colony algorithm was proposed in order to carry out accurate assessment on pipeline risks in the state of daily operation. In this method, the pipeline risk assessment model is established, the technological operation characteristics of products pipelines, forward/backward crude oil pipelines and mixed-transportation crude oil pipelines are collected from the viewpoint of technological operation, and the sample characteristic set is built up. Then, 4 types of pipeline characteristic sets were tested. It is indicated that in the case of small sample, the optimized SVM pipeline risk assessment method based on artificial bee colony algorithm has higher accuracy and good applicability, and it can provide the accurate risk assessment result according to the actual running state of pipelines.(3 Figures, 1 Table, 21 References)
引文
[1]姜为夷.油气管道失效与风险评估[J].中国石油和化工标准与质量,2014,34(2):122-123.JIANG W Y.Pipeline failure and risk assessment[J].China Petroleum and Chemical Standard and Quality,2014,34(2):122-123.
[2]杜洋,姚广聚,姚鳞昱,等.风险评估法在川西集输管道的应用分析[J].天然气技术与经济,2017,11(2):55-57.DU Y,YAO G J,YAO L Y,et al.Application of risk assessment to gas gathering pipelines in Western Sichuan Gasfield[J].Natural Gas Technology and Economy,2017,11(2):55-57.
[3]邬蓉蓉,张炜.综合遗传优化支持向量机的变压器故障诊断模型[J].变压器,2018,55(11):40-44.WU R R,ZHANG W.Fault diagnosis model of power transformers based on GA optimization SVM[J].Transformer,2018,55(11):40-44.
[4]黄绪勇,刘洋,王艳涛.遗传算法优化支持向量机的输电线路雷击缺陷预测[J].现代工业经济和信息化,2017(20):9-10,30.HUANG X Y,LIU Y,WANG Y T.Lightning fault prediction of transmission line based on genetic algorithm optimized support vector machine[J].Modern Industrial Economy and Informationization,2017(20):9-10,30.
[5]赵新伟,张华,罗金恒.油气管道可接受风险准则研究[J].油气储运,2016,35(1):1-6.ZHAO X W,ZHANG H,LUO J H.Risk acceptance criteria for oil and gas pipelines[J].Oil&Gas Storage and Transportation,2016,35(1):1-6.
[6]帅健,单克.基于失效数据的油气管道定量风险评价方法[J].天然气工业,2018,38(9):125-138.SHUAI J,SHAN K.A quantitative risk assessment method for oil and gas pipelines based on failure data[J].Natural Gas Industry,2018,38(9):125-138.
[7]李亚芹.现役长输管道风险分析技术研究[J].化工设计通讯,2016,34(11):11-19.LI Y Q.Research on risk analysis technology of active long-distance pipeline[J].Chemical Engineering Design Communications,2016,34(11):11-19.
[8]宿兰花.基于模糊理论的管道失效模式诊断模型与方法研究[D].北京:北京石油大学(北京),2010:11-12.SU L H.Research on pipeline failure mode diagnosis and method based on fuzzy theory[D].Beijing:China University of Petroleum(Beijing),2010:11-12.
[9]刘春波,王鲜芳,潘丰.基于蚁群优化算法的支持向量机参数选择及仿真[J].中南大学学报(自然科学版),2008,39(6):1309-1313.LIU C B,WANG X F,PAN F.Parameters selection and stimulation of support vector machines based on ant colony optimization algorithm[J].Journal of Central South University(Science and Technology),2008,39(6):1309-1313.
[10]路志英,李艳英,陆洁.粒子群算法优化RBF-SVM沙尘暴预报模型参数[J].天津大学学报,2008,41(4):413-418.LU Z Y,LI Y Y,LU J.Parameter optimization of RBF-SVMsand-dust storm forecasting model based on PSO[J].Journal of Tianjin University,2008,41(4):413-418.
[11]蒋波涛,WESLEYH J,赵福宇.蚁群优化最小二乘支持向量机在测量数据拟合中的应用[J].核动力工程,2018,39(6):156-160.JIANG B T,WESLEYH J,ZHAO F Y.Application of ant colony optimization least squares support vector machine in measurement data fitting[J].Nuclear Power Engineering,2018,39(6):156-160.
[12]徐飞,徐卫亚,王珂.基于蚁群优化最小二乘支持向量机模型的边坡稳定性分析[J].工程地质学报,2009,17(2):253-257.XU F,XU W Y,WANG K.Slope stability analysis using least square support vector machine optimized with ant colony algorithm[J].Journal of Engineering Geology,2009,17(2):253-257.
[13]吴景龙,杨淑霞,刘承水.基于遗传算法优化参数的支持向量机短期负荷预测方法[J].中南大学学报(自然科学版),2009,40(1):180-184.WU J L,YANG S X,LIU C S.Parameter selection for support vector machines based on genetic algorithms to short-term power load forecasting[J].Journal of Central South University(Science and Technology),2009,40(1):180-184.
[14]高扬,李旭,董明,等.增强性人工蜂群算法及在多阀值图像分割中的应用[J].中南大学学报,2018,25(1):107-120.GAO Y,LI X,DONG M,et al.An enhanced artificial bee colony optimizer and its application to multi-level threshold image segmentation[J].Journal of Central South University,2018,25(1):107-120.
[15]丁世飞,齐丙娟,谭红艳.支持向量机理论与算法研究综述[J].电子科技大学学报,2011,40(1):2-10.DING S F,QI B J,TAN H Y.An overview on theory and algorithm of support vector machines[J].Journal of University of Science and Technology of China,2011,40(1):2-10.
[16]WANG H L,HUANG Y W,DING H F.Application of support vector machine and quantum genetic algorithm in infrared target recognition[C].San Diego:International Conference on Image Processing and Pattern Recognition in Industrial Engineering,2010:35-40.
[17]LI W H,LIU W.Gear incipient fault diagnosis using graph theory and transductive support vector machine[J].Journal of Mechanical Engineering,2010,46(23):82-88.
[18]CRISTIANINI N,SHAWE-TAYOR J.支持向量机导论[M].北京:电子工业出版社,2004:344-365.CRISTIANINI N,SHAWE-TAYOR J.Support vector machines introduction[M].Beijing:Publishing House of Electronics Industry,2004:344-365.
[19]ROJAS M,PLAZA A.Comparison of support vector machinebased processing chains for hyper-spectral image classification[C].San Diego:Conference on Satellite Data Compression,Communications and Processing VI,2010:781-786.
[20]KARABOGA D,BASTURK B.A powerful and efficient algorithm for numerical function optimization:Artificial bee colony(ABC)algorithm[J].Journal of Global Optimization,2007,39(3):459-471.
[21]KARABOGA D,BASTURK B.A comparative study of artificial bee colony algorithm[J].Applied Mathematics and Computation,2009,214(1):108-132.
[2]杜洋,姚广聚,姚鳞昱,等.风险评估法在川西集输管道的应用分析[J].天然气技术与经济,2017,11(2):55-57.DU Y,YAO G J,YAO L Y,et al.Application of risk assessment to gas gathering pipelines in Western Sichuan Gasfield[J].Natural Gas Technology and Economy,2017,11(2):55-57.
[3]邬蓉蓉,张炜.综合遗传优化支持向量机的变压器故障诊断模型[J].变压器,2018,55(11):40-44.WU R R,ZHANG W.Fault diagnosis model of power transformers based on GA optimization SVM[J].Transformer,2018,55(11):40-44.
[4]黄绪勇,刘洋,王艳涛.遗传算法优化支持向量机的输电线路雷击缺陷预测[J].现代工业经济和信息化,2017(20):9-10,30.HUANG X Y,LIU Y,WANG Y T.Lightning fault prediction of transmission line based on genetic algorithm optimized support vector machine[J].Modern Industrial Economy and Informationization,2017(20):9-10,30.
[5]赵新伟,张华,罗金恒.油气管道可接受风险准则研究[J].油气储运,2016,35(1):1-6.ZHAO X W,ZHANG H,LUO J H.Risk acceptance criteria for oil and gas pipelines[J].Oil&Gas Storage and Transportation,2016,35(1):1-6.
[6]帅健,单克.基于失效数据的油气管道定量风险评价方法[J].天然气工业,2018,38(9):125-138.SHUAI J,SHAN K.A quantitative risk assessment method for oil and gas pipelines based on failure data[J].Natural Gas Industry,2018,38(9):125-138.
[7]李亚芹.现役长输管道风险分析技术研究[J].化工设计通讯,2016,34(11):11-19.LI Y Q.Research on risk analysis technology of active long-distance pipeline[J].Chemical Engineering Design Communications,2016,34(11):11-19.
[8]宿兰花.基于模糊理论的管道失效模式诊断模型与方法研究[D].北京:北京石油大学(北京),2010:11-12.SU L H.Research on pipeline failure mode diagnosis and method based on fuzzy theory[D].Beijing:China University of Petroleum(Beijing),2010:11-12.
[9]刘春波,王鲜芳,潘丰.基于蚁群优化算法的支持向量机参数选择及仿真[J].中南大学学报(自然科学版),2008,39(6):1309-1313.LIU C B,WANG X F,PAN F.Parameters selection and stimulation of support vector machines based on ant colony optimization algorithm[J].Journal of Central South University(Science and Technology),2008,39(6):1309-1313.
[10]路志英,李艳英,陆洁.粒子群算法优化RBF-SVM沙尘暴预报模型参数[J].天津大学学报,2008,41(4):413-418.LU Z Y,LI Y Y,LU J.Parameter optimization of RBF-SVMsand-dust storm forecasting model based on PSO[J].Journal of Tianjin University,2008,41(4):413-418.
[11]蒋波涛,WESLEYH J,赵福宇.蚁群优化最小二乘支持向量机在测量数据拟合中的应用[J].核动力工程,2018,39(6):156-160.JIANG B T,WESLEYH J,ZHAO F Y.Application of ant colony optimization least squares support vector machine in measurement data fitting[J].Nuclear Power Engineering,2018,39(6):156-160.
[12]徐飞,徐卫亚,王珂.基于蚁群优化最小二乘支持向量机模型的边坡稳定性分析[J].工程地质学报,2009,17(2):253-257.XU F,XU W Y,WANG K.Slope stability analysis using least square support vector machine optimized with ant colony algorithm[J].Journal of Engineering Geology,2009,17(2):253-257.
[13]吴景龙,杨淑霞,刘承水.基于遗传算法优化参数的支持向量机短期负荷预测方法[J].中南大学学报(自然科学版),2009,40(1):180-184.WU J L,YANG S X,LIU C S.Parameter selection for support vector machines based on genetic algorithms to short-term power load forecasting[J].Journal of Central South University(Science and Technology),2009,40(1):180-184.
[14]高扬,李旭,董明,等.增强性人工蜂群算法及在多阀值图像分割中的应用[J].中南大学学报,2018,25(1):107-120.GAO Y,LI X,DONG M,et al.An enhanced artificial bee colony optimizer and its application to multi-level threshold image segmentation[J].Journal of Central South University,2018,25(1):107-120.
[15]丁世飞,齐丙娟,谭红艳.支持向量机理论与算法研究综述[J].电子科技大学学报,2011,40(1):2-10.DING S F,QI B J,TAN H Y.An overview on theory and algorithm of support vector machines[J].Journal of University of Science and Technology of China,2011,40(1):2-10.
[16]WANG H L,HUANG Y W,DING H F.Application of support vector machine and quantum genetic algorithm in infrared target recognition[C].San Diego:International Conference on Image Processing and Pattern Recognition in Industrial Engineering,2010:35-40.
[17]LI W H,LIU W.Gear incipient fault diagnosis using graph theory and transductive support vector machine[J].Journal of Mechanical Engineering,2010,46(23):82-88.
[18]CRISTIANINI N,SHAWE-TAYOR J.支持向量机导论[M].北京:电子工业出版社,2004:344-365.CRISTIANINI N,SHAWE-TAYOR J.Support vector machines introduction[M].Beijing:Publishing House of Electronics Industry,2004:344-365.
[19]ROJAS M,PLAZA A.Comparison of support vector machinebased processing chains for hyper-spectral image classification[C].San Diego:Conference on Satellite Data Compression,Communications and Processing VI,2010:781-786.
[20]KARABOGA D,BASTURK B.A powerful and efficient algorithm for numerical function optimization:Artificial bee colony(ABC)algorithm[J].Journal of Global Optimization,2007,39(3):459-471.
[21]KARABOGA D,BASTURK B.A comparative study of artificial bee colony algorithm[J].Applied Mathematics and Computation,2009,214(1):108-132.
© 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 |