摘要
本文基于 PCA(Principal componentanalysis)理论对故障传感器进行重构。首先将数据分别投影于主元子空间和残差子空间 ,然后定义故障的方向向量 ;因为过程变量间具有的强相关性 。
This paper presents faulty sensor reconstruction based on PCA. Firstly, data is projected onto principal component sub space and residual sub space respectively, then fault direction vector is defined. Due to the strong related data, fault variable can be reconstructed along its own fault direction.
出处
《仪器仪表学报》
EI
CAS
CSCD
北大核心
2003年第z1期187-188,共2页
Chinese Journal of Scientific Instrument
