主成分分析在柴油机润滑油磨粒分析中的应用
|
摘要
针对船舶柴油机在用润滑油中的磨损监测问题,对某船队14台同型号柴油机在用润滑油进行监测,取得在用润滑油油样共计105个;利用油料发射光谱技术测量21种典型元素的含量,利用铁量仪和磁力方法测量铁磁性磨粒总量。从105个油样中选取铁磁性磨粒质量分数大于0的油样以及Fe元素质量分数大于平均值的油样共计18个。利用滤膜法分析18个油样的非铁磁性磨粒(大于10μm),统计了非铁磁性磨粒的最大尺寸和平均尺寸。采用主成分分析法对18个油样的发射光谱数据、PQ值、磁力值、非铁磁性磨粒的尺寸最大值和平均值进行分析。结果表明:主成分分析法可以综合多项磨粒监测参数对柴油机的磨损状态进行聚类。经滤膜图像分析验证,该聚类结果具有可靠性。
Aimed at the wear monitoring problem of marine diesel engine,the used oils of 14 sets of diesel engine of the same type used in a certain fleet were monitored,and 105 oil samples were obtained.The content of 21 typical elements was measured by atomic emission spectrometer.The total amount of ferromagnetic debris was measured by magnetic debris monitor and magnetic force measurement method.A total of 18 oil samples with ferromagnetic debris mass fraction greater than 0 and Fe element mass fraction greater than average were selected from 105 oil samples.The non-ferromagnetic debris(greater than 10 μm) from the 18 oil samples was analyzed by the filter membrane method,and the maximum size and average size of the non-ferromagnetic debris were counted.Principle component analysis(PCA) method was applied to analyze the spectral data,PQ value,magnetic force value,and the maximum size and average size of the non-ferromagnetic debris of the 18 oil samples.The results show that the PCA method can integrate the various debris monitoring characteristics to cluster the wear status of the diesel engine.The results of the membrane image analysis confirms that the clustering results are reliable.
Aimed at the wear monitoring problem of marine diesel engine,the used oils of 14 sets of diesel engine of the same type used in a certain fleet were monitored,and 105 oil samples were obtained.The content of 21 typical elements was measured by atomic emission spectrometer.The total amount of ferromagnetic debris was measured by magnetic debris monitor and magnetic force measurement method.A total of 18 oil samples with ferromagnetic debris mass fraction greater than 0 and Fe element mass fraction greater than average were selected from 105 oil samples.The non-ferromagnetic debris(greater than 10 μm) from the 18 oil samples was analyzed by the filter membrane method,and the maximum size and average size of the non-ferromagnetic debris were counted.Principle component analysis(PCA) method was applied to analyze the spectral data,PQ value,magnetic force value,and the maximum size and average size of the non-ferromagnetic debris of the 18 oil samples.The results show that the PCA method can integrate the various debris monitoring characteristics to cluster the wear status of the diesel engine.The results of the membrane image analysis confirms that the clustering results are reliable.
引文
[1]杨其明,严新平,贺石中.油液监测分析现场实用技术[M].北京:机械工业出版社,2006:1-10.
[2]TOMS L A,TOMS A M.Machinery oil analysis:methods,automation & benefits:a guide for maintenance managers,supervisors & technicians[M].3rd ed.New York:STLE,Park Ridge,Ill.,2008:1-20.
[3]萧汉梁.铁谱技术及其在机械监测诊断中的应用[M].北京:人民交通出版社,1993.
[4]Standardtest method for determination of wear metals and contaminants in used lubricating oils or used hydraulic fluids by rotating disc electrode atomic emission spectrometry:ASTM D6595-00[S].
[5]Standardtest method for multielement determination of used and unused lubricating oils and base oils by inductively coupled plasma atomic emission spectrometry (ICP-AES):ASTM D5158-13[S].
[6]王胜杰.基于磁力和电磁感应的金属磨粒监测方法的研究[D].武汉:海军工程大学,2015.
[7]王胜杰,孙云岭,田洪祥,等.一种基于磁力测量的油液铁磁性磨粒监测新方法[J].润滑与密封,2015,40(11):56-59.WANG S J,SUN Y L ,TIAN H X,et al.A new method to monitor ferrous debris in oil based on magnetic principle[J].Lubrication Engineering,2015,40(11):56-59.
[8]张奇,田洪祥,何伟,等.在用润滑油金属磨粒快速检测研究[J].设备管理与维修,2017(7):125-128.
[9]刘东风,孙怡,周新聪,等.主成分分析在舰船液压系统监测中的应用研究[J].武汉理工大学学报(交通科学与工程版),2003,27(5):639-642.LIU D F,SUN Y,ZHOU X C,et al.The application of principal component analysis to the monitoring data for on-board hydraulic system[J].Journal of Wuhan University of Technology(Transportation Science & Engineering),2003,27(5):639-642.
[10]王永杰,白艳萍.基于主成分分析的 PSO-BP 算法在 GDP 和 CPI 预测中的应用[J].重庆理工大学学报(自然科学),2017(4):150-154.WANG Y J,BAI Y P.Application of PSO-BP algorithm based on principal component analysis in prediction of GDP and CPI[J].Journal of Chongqing University of Technology(Natural Science),2017(4):150-154.
[11]刘韬,田洪祥,郭文勇.主成分分析在某型柴油机光谱数据分析中的应用[J].光谱学与光谱分析,2010,30(3):779-782.LIU T,TIAN H X,GUO W Y.Application of PCA to diesel engine oil spectrometric analysis[J].Spectroscopy and Spectral Analysis,2010,30(3):779-782.
[12]乔晓君,田洪祥.系统聚类法与主成分分析法在润滑油聚类分析中的应用[J].润滑与密封,2013,38(5):99-103.QIAO X J,TIAN H X.Application of system clustering method and principle component analysis method in clustering analysis of lubricating oil[J].Lubrication Engineering,2013,38(5):99-103.
[2]TOMS L A,TOMS A M.Machinery oil analysis:methods,automation & benefits:a guide for maintenance managers,supervisors & technicians[M].3rd ed.New York:STLE,Park Ridge,Ill.,2008:1-20.
[3]萧汉梁.铁谱技术及其在机械监测诊断中的应用[M].北京:人民交通出版社,1993.
[4]Standardtest method for determination of wear metals and contaminants in used lubricating oils or used hydraulic fluids by rotating disc electrode atomic emission spectrometry:ASTM D6595-00[S].
[5]Standardtest method for multielement determination of used and unused lubricating oils and base oils by inductively coupled plasma atomic emission spectrometry (ICP-AES):ASTM D5158-13[S].
[6]王胜杰.基于磁力和电磁感应的金属磨粒监测方法的研究[D].武汉:海军工程大学,2015.
[7]王胜杰,孙云岭,田洪祥,等.一种基于磁力测量的油液铁磁性磨粒监测新方法[J].润滑与密封,2015,40(11):56-59.WANG S J,SUN Y L ,TIAN H X,et al.A new method to monitor ferrous debris in oil based on magnetic principle[J].Lubrication Engineering,2015,40(11):56-59.
[8]张奇,田洪祥,何伟,等.在用润滑油金属磨粒快速检测研究[J].设备管理与维修,2017(7):125-128.
[9]刘东风,孙怡,周新聪,等.主成分分析在舰船液压系统监测中的应用研究[J].武汉理工大学学报(交通科学与工程版),2003,27(5):639-642.LIU D F,SUN Y,ZHOU X C,et al.The application of principal component analysis to the monitoring data for on-board hydraulic system[J].Journal of Wuhan University of Technology(Transportation Science & Engineering),2003,27(5):639-642.
[10]王永杰,白艳萍.基于主成分分析的 PSO-BP 算法在 GDP 和 CPI 预测中的应用[J].重庆理工大学学报(自然科学),2017(4):150-154.WANG Y J,BAI Y P.Application of PSO-BP algorithm based on principal component analysis in prediction of GDP and CPI[J].Journal of Chongqing University of Technology(Natural Science),2017(4):150-154.
[11]刘韬,田洪祥,郭文勇.主成分分析在某型柴油机光谱数据分析中的应用[J].光谱学与光谱分析,2010,30(3):779-782.LIU T,TIAN H X,GUO W Y.Application of PCA to diesel engine oil spectrometric analysis[J].Spectroscopy and Spectral Analysis,2010,30(3):779-782.
[12]乔晓君,田洪祥.系统聚类法与主成分分析法在润滑油聚类分析中的应用[J].润滑与密封,2013,38(5):99-103.QIAO X J,TIAN H X.Application of system clustering method and principle component analysis method in clustering analysis of lubricating oil[J].Lubrication Engineering,2013,38(5):99-103.
© 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 |