Internal Corrosion Risk Prediction of Submarine Pipeline Based on Kernel Principal Component Analysis
摘 要
采用核主成分分析(KPCA)算法,分别对高斯核支持向量机(SVM-rbf)、多项式核支持向量机(SVM-poly)、线性核支持向量机(SVM-linear)、人工神经网络(ANN)和随机森林(RFR)等算法进行优化,以网格搜索法进行参数寻优,对20条海底管道的最大腐蚀速率进行预测,以均方根误差(RMSE)、平均绝对误差(MAE)和平方相关系数(R2)作为评价指标对优化前后模型的预测效果进行评价。结果表明:优化后各模型的R2值显著提高,最高达0.987 7;KPCA能够降低特征维度,减少噪声干扰,提升模型预测性能;优化后的支持向量机算法对海底管道腐蚀速率预测的准确性较高,能够为海底油气田管道腐蚀的预警与防护提供参考。
Abstract
The kernel principal component analysis (KPCA) was used to optimize the algorithms such as gaussian kernel support vector machine (SVM-rbf), poly kernel support vector machine (SVM-poly), linear kernel support vector machine (SVM-linear), artificial neural network (ANN) and random forest (RFR). The maximum corrosion rate of 20 submarine pipelines was predicted by grid search method. The root mean square error (RMSE), mean absolute error (MAE) and squared correlation coefficient (R2) were used as evaluation indexes to evaluate the prediction effect of the model before and after optimization. The results showed that the R2 value of each model was significantly increased after optimization, and the maximum value was 0.987 7. KPCA could reduce both the feature dimension and the noise interference and improve the prediction performance of the model. The optimized support vector machine algorithm had high accuracy in predicting the corrosion rate of submarine pipelines, which could provide a reference for early warning and protection of submarine oil and gas pipeline corrosion.
中图分类号 TG174 DOI 10.11973/fsyfh-202303012
所属栏目 应用技术
基金项目 国家重点研发计划(2020YFB0704501)
收稿日期 2021/4/13
修改稿日期
网络出版日期
作者单位点击查看
引用该论文: JIA Haiyun,HU Lihua,LI Xiaqiao,QU Zhihao,WANG Zhu,CHANG Wei,ZHANG Lei. Internal Corrosion Risk Prediction of Submarine Pipeline Based on Kernel Principal Component Analysis[J]. Corrosion & Protection, 2023, 44(3): 82
共有人对该论文发表了看法,其中:
人认为该论文很差
人认为该论文较差
人认为该论文一般
人认为该论文较好
人认为该论文很好
参考文献
【1】曾维烁,江陵. 天然气管道运行中危害因素及管道完整性管理[J]. 中国石油石化,2017(2):21-22.
【2】李炳文,杨晶. 基于ABC-SVM算法的海底多相流热油管道腐蚀速率预测[J]. 工业加热,2020,49(2):47-49,55.
【3】徐安桃,李锡栋,周慧,等. 基于灰色补偿BP神经网络优化组合模型的车辆装备冷却系腐蚀预测[J]. 装备环境工程,2018,15(11):123-128.
【4】陈迪,廖柯熹,何国玺,等. 基于EWM-GRA的腐蚀主控因素分析与腐蚀模型建立[J]. 表面技术,2019,48(6):268-273.
【5】阎桂荣,董龙雷,宋利强. 一种提高飞行器结构天地力学环境地面试验有效性的方法及其应用[J]. 装备环境工程,2016,13(5):10-16.
【6】毕傲睿,骆正山,乔伟,等. 基于主成分和粒子群优化支持向量机的管道内腐蚀预测[J]. 表面技术,2018,47(9):133-140.
【7】宋丛威,张晓明. 基于PCA的解大型超定线性方程组快速算法及应用[J]. 智能计算机与应用,2019,9(4):91-95.
【8】CORTES C,VAPNIK V. Support-vector networks[J]. Machine Learning,1995,20(3):273-297.
【9】LIU Z L,GUO A X. Empirical-based support vector machine method for seismic assessment and simulation of reinforced concrete columns using historical cyclic tests[J]. Engineering Structures,2021,237:112141.
【10】LV Y J,WANG J W,WANG J L,et al. Steel corrosion prediction based on support vector machines[J]. Chaos,Solitons & Fractals,2020,136:109807.
【11】LEE L H,RAJKUMAR R,LO L H,et al. Oil and gas pipeline failure prediction system using long range ultrasonic transducers and Euclidean-Support Vector Machines classification approach[J]. Expert Systems With Applications,2013,40(6):1925-1934.
【12】李立刚,万勇,王宇,等. 基于支持向量机和磁记忆技术的管道缺陷深度的定量化反演研究[J]. 腐蚀与防护,2020,41(1):29-34,40.
【13】WU A,ZHU J H,YANG Y L,et al. Classification of corn kernels grades using image analysis and support vector machine[J]. Advances in Mechanical Engineering,2018,10(12):168781401881764.
【14】BRERETON R G,LLOYD G R. Support vector machines for classification and regression[J]. The Analyst,2010,135(2):230-267.
【15】骆正山,宋莹莹,毕傲睿. 基于GRA-RFR的油气集输管道内腐蚀速率预测[J]. 材料保护,2020,53(3):95-100.
【16】曲志豪,唐德志,胡丽华,等. 基于优化随机森林的H2S腐蚀产物类型及腐蚀速率预测[J]. 表面技术,2020,49(3):42-49.
【17】支元杰. 大气环境下小样本金属材料腐蚀的数据驱动预测模型[D].北京:北京科技大学,2019.
【18】鲁庆. 基于数据挖掘的材料自然环境腐蚀预测研究[D].北京:北京科技大学,2015.
【19】SCORNET E. Random forests and kernel methods[J]. IEEE Transactions on Information Theory,2016,62(3):1485-1500.
【20】XU W Z,LI C B,CHOUNG J,et al. Corroded pipeline failure analysis using artificial neural network scheme[J]. Advances in Engineering Software,2017,112:255-266.
【21】SHI J B,WANG J H,MACDONALD D D. Prediction of crack growth rate in Type 304 stainless steel using artificial neural networks and the coupled environment fracture model[J]. Corrosion Science,2014,89:69-80.
【2】李炳文,杨晶. 基于ABC-SVM算法的海底多相流热油管道腐蚀速率预测[J]. 工业加热,2020,49(2):47-49,55.
【3】徐安桃,李锡栋,周慧,等. 基于灰色补偿BP神经网络优化组合模型的车辆装备冷却系腐蚀预测[J]. 装备环境工程,2018,15(11):123-128.
【4】陈迪,廖柯熹,何国玺,等. 基于EWM-GRA的腐蚀主控因素分析与腐蚀模型建立[J]. 表面技术,2019,48(6):268-273.
【5】阎桂荣,董龙雷,宋利强. 一种提高飞行器结构天地力学环境地面试验有效性的方法及其应用[J]. 装备环境工程,2016,13(5):10-16.
【6】毕傲睿,骆正山,乔伟,等. 基于主成分和粒子群优化支持向量机的管道内腐蚀预测[J]. 表面技术,2018,47(9):133-140.
【7】宋丛威,张晓明. 基于PCA的解大型超定线性方程组快速算法及应用[J]. 智能计算机与应用,2019,9(4):91-95.
【8】CORTES C,VAPNIK V. Support-vector networks[J]. Machine Learning,1995,20(3):273-297.
【9】LIU Z L,GUO A X. Empirical-based support vector machine method for seismic assessment and simulation of reinforced concrete columns using historical cyclic tests[J]. Engineering Structures,2021,237:112141.
【10】LV Y J,WANG J W,WANG J L,et al. Steel corrosion prediction based on support vector machines[J]. Chaos,Solitons & Fractals,2020,136:109807.
【11】LEE L H,RAJKUMAR R,LO L H,et al. Oil and gas pipeline failure prediction system using long range ultrasonic transducers and Euclidean-Support Vector Machines classification approach[J]. Expert Systems With Applications,2013,40(6):1925-1934.
【12】李立刚,万勇,王宇,等. 基于支持向量机和磁记忆技术的管道缺陷深度的定量化反演研究[J]. 腐蚀与防护,2020,41(1):29-34,40.
【13】WU A,ZHU J H,YANG Y L,et al. Classification of corn kernels grades using image analysis and support vector machine[J]. Advances in Mechanical Engineering,2018,10(12):168781401881764.
【14】BRERETON R G,LLOYD G R. Support vector machines for classification and regression[J]. The Analyst,2010,135(2):230-267.
【15】骆正山,宋莹莹,毕傲睿. 基于GRA-RFR的油气集输管道内腐蚀速率预测[J]. 材料保护,2020,53(3):95-100.
【16】曲志豪,唐德志,胡丽华,等. 基于优化随机森林的H2S腐蚀产物类型及腐蚀速率预测[J]. 表面技术,2020,49(3):42-49.
【17】支元杰. 大气环境下小样本金属材料腐蚀的数据驱动预测模型[D].北京:北京科技大学,2019.
【18】鲁庆. 基于数据挖掘的材料自然环境腐蚀预测研究[D].北京:北京科技大学,2015.
【19】SCORNET E. Random forests and kernel methods[J]. IEEE Transactions on Information Theory,2016,62(3):1485-1500.
【20】XU W Z,LI C B,CHOUNG J,et al. Corroded pipeline failure analysis using artificial neural network scheme[J]. Advances in Engineering Software,2017,112:255-266.
【21】SHI J B,WANG J H,MACDONALD D D. Prediction of crack growth rate in Type 304 stainless steel using artificial neural networks and the coupled environment fracture model[J]. Corrosion Science,2014,89:69-80.
相关信息