基于多变量统计对连铸结晶器过程的监测  

Monitoring of Continuous Casting Mould Process Based on Multivariate Statistics

作　　者：杨尚玉 王旭东[2] 姚曼[2] 李全育 

机构地区：[1]海洋工程股份有限公司海洋工程技术中心,天津300452 [2]大连理工大学材料科学与工程学院,辽宁大连116024

出　　处：《钢铁研究学报》2007年第10期59-62,共4页Journal of Iron and Steel Research

基　　金：教育部科技研究重点资助项目(03051)

摘　　要：尝试性地将基于主元分析的多变量统计方法应用于连铸结晶器过程的监测。介绍了该方法的原理及其建模步骤。基于板坯连铸结晶器实测数据,利用T2图、Q图进行故障检测,结合实测的结晶器摩擦力及其均方根图进行分析。仿真结果表明,多变量统计方法应用于连铸结晶器过程的监测是可行的。The authors try to use multivariate statistics method based on principal component analysis （PCA） to monitor continuous casting mould process. The principle and modeling process of this method are introduced. Based on the measured data of mould friction （MDF） in slab continuous casting process, the fault detection is performed by means of the T^2 and Q charts, and the MDF and its root-mean-square charts are used to analyze the condition of process. Simulation results show that the application of multivariate statistics method to monitor continuous casting mould process is feasible.

关 键 词：多变量统计 结晶器 主元分析 监测 

分 类 号：TF777[冶金工程—钢铁冶金]