基于KPCA和SVM的工艺管道腐蚀速率预测
|
摘要
为解决有限样本数据下工艺管道中腐蚀速率难以估算的问题,提出一种基于核主成分分析(KPCA)和支持向量机(SVM)的腐蚀速率预测的方法。采用核主成分分析方法有效融合多种腐蚀影响因素,剔除核主成分分析结果中贡献率低的主元变量,将贡献率大的主元变量作为输入,腐蚀速率作为输出,建立了支持向量机模型,并预测了管道腐蚀速率。采用工艺管道实际工程数据检验KPCA-SVM模型预测腐蚀速率的效果,结果表明,基于核主成分分析和支持向量机方法的管道腐蚀速率预测误差较小,能够获得准确的预测结果。
In order to estimate the corrosion rate of process pipeline under limited condition data,a method based on kernel principal component analysis(KPCA)and support vector machine(SVM)was proposed.The kernel principal component analysis method was used to effectively integrate the factors that affect the corrosion rate of pipeline.The kernel components with low contribution rate were discarded.The principal components with higher contribution rate were taken as input variables of the support vector machine,and the corrosion rate was taken as output.The support vector machine model was established to predict the corrosion rate of pipelines.The prediction model was verified by engineering data of process pipelines.The results show that prediction error of the method based on kernel principal component analysis and support vector machine was low,and accurate prediction data could be obtained.
In order to estimate the corrosion rate of process pipeline under limited condition data,a method based on kernel principal component analysis(KPCA)and support vector machine(SVM)was proposed.The kernel principal component analysis method was used to effectively integrate the factors that affect the corrosion rate of pipeline.The kernel components with low contribution rate were discarded.The principal components with higher contribution rate were taken as input variables of the support vector machine,and the corrosion rate was taken as output.The support vector machine model was established to predict the corrosion rate of pipelines.The prediction model was verified by engineering data of process pipelines.The results show that prediction error of the method based on kernel principal component analysis and support vector machine was low,and accurate prediction data could be obtained.
引文
[1]刘志亮.常减压车间工艺管线腐蚀寿命评估与缺陷模拟[D].北京:中国石油大学,2011.
[2]喻西崇,赵金洲,邬亚玲,等.利用灰色理论预测注水管道腐蚀速率的变化趋势[J].腐蚀与防护,2003,24(2):51-54.
[3]张镇,刘晓东,李著信,等.基于灰色组合模型的管道腐蚀速率预测[J].中国腐蚀与防护学报,2008,24(3):173-176.
[4]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.
[5]肖健华,吴今培.基于核的特征提取技术及应用研究[J].计算机工程,2002,28(10):36-38.
[6]徐晔,杜文莉,钱锋.基于核主元分析和最小二乘支持向量机的软测量建模[J].系统仿真学报,2007,19(17):3873-3875.
[7] NELLO C,JOHN S T.An introduction to support vector machines and other kernel-based learning methods[M].李国正,等译,支持向量机导论.北京:电子工业出版社,2004:5-6.
[8] LIU H,LIU D,ZHENG G,et al.Research on natural gas short-term load forecasting based on support vector regression[J].Chinese Journal of Chemical Engineering,2004,12(5):732-736.
[9] LIU J C,WANG H T,YUAN Z G.Forecast model for inner corrosion rate of oil pipeline based on PSO-SVM[J].International Journal of Simulation and ProcessModelling,2012,7(1):74-80.
[10]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.
[2]喻西崇,赵金洲,邬亚玲,等.利用灰色理论预测注水管道腐蚀速率的变化趋势[J].腐蚀与防护,2003,24(2):51-54.
[3]张镇,刘晓东,李著信,等.基于灰色组合模型的管道腐蚀速率预测[J].中国腐蚀与防护学报,2008,24(3):173-176.
[4]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.
[5]肖健华,吴今培.基于核的特征提取技术及应用研究[J].计算机工程,2002,28(10):36-38.
[6]徐晔,杜文莉,钱锋.基于核主元分析和最小二乘支持向量机的软测量建模[J].系统仿真学报,2007,19(17):3873-3875.
[7] NELLO C,JOHN S T.An introduction to support vector machines and other kernel-based learning methods[M].李国正,等译,支持向量机导论.北京:电子工业出版社,2004:5-6.
[8] LIU H,LIU D,ZHENG G,et al.Research on natural gas short-term load forecasting based on support vector regression[J].Chinese Journal of Chemical Engineering,2004,12(5):732-736.
[9] LIU J C,WANG H T,YUAN Z G.Forecast model for inner corrosion rate of oil pipeline based on PSO-SVM[J].International Journal of Simulation and ProcessModelling,2012,7(1):74-80.
[10]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.