基于核主元分析的蒸汽管网数据的显著误差检测研究  

Research on Data Calibration of Steam Pipe Network Based on KPCA and KALMAN Filtering

作　　者：吴泽浩 罗先喜[1] Wu Ze-hao;Luo Xian-xi(Jiangxi Province Engineering Research Center of New Energy Technology and Equipment,East China University of Technology,Jiangxi Nanchang 330013)

机构地区：[1]江西省新能源工艺及装备工程技术研究中心东华理工大学

出　　处：《电子质量》2019年第10期23-26,共4页Electronics Quality

摘　　要：工业生产中蒸汽能源的回收和利用的效果一直不高,与发达国家相比还有很大差距,造成这些的主要原因在于蒸汽管网的数据测量不完整、精度低以及一致性不明显。针对以上问题,以蒸汽管网的温度数据检测为例,在传统的数据校正方法上采用改进型的主元分析法-核主元分析法进行管网数据的显著误差检测,通过现场采集的管网温度数据进行仿真分析,有效地验证了核主元分析法对蒸汽管网显著误差检测的准确性与一致性的极大提升。The effect of recovery and utilization of steam energy in industrial production has not been high,and there is still a big gap compared with developed countries.The main reason for these is that the steam pipe network data measurement is incomplete,the precision is low and the consistency is not obvious.In view of the above problems,taking the data detection of the temperature of the steam pipe network as an example,the improved principal component analysis method-nuclear principal component analysis method is used to detect the significant error of the pipe network data in the traditional data correction method.The simulation analysis of the pipe network temperature data effectively verified the accuracy and consistency of the nuclear principal component analysis method for the significant error detection of the steam pipe network.

关 键 词：蒸汽管网 数据校正 核主元分析法 仿真分析 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置]