| 基于主元分析的传感器故障检测研究 |
| |
| 引用本文： | 高明亮.基于主元分析的传感器故障检测研究[J].科技广场,2012(3):132-134. |
| |
| 作者姓名： | 高明亮 |
| |
| 作者单位： | 沈阳工程学院自动控制工程系,辽宁沈阳,110136 |
| |
| 摘 要： | 基于主元分析(PCA)的故障诊断方法是故障诊断领域一个重要研究分支。本文首先介绍了主元分析的理论,然后深入研究了基于主元分析方法的传感器故障检测问题。该方法能够在对测量参数相关性分析的基础上,将传感器测量值所组成的测量空间分解为主元和残差两个子空间,通过传感器实际测量数据与正常数据矩阵在残差子空间投影的比较,对传感器的故障进行检测。最后进行具体仿真,仿真结果表明主元分析法对传感器具有很好的故障检测能力。
|
| 关 键 词： | 主元分析 故障检测 可检测性 传感器 |
Research on the Sensor Fault Detection based on Principal Component Analysis |
| |
| Gao Mingliang.Research on the Sensor Fault Detection based on Principal Component Analysis[J].Science Mosaic,2012(3):132-134. |
| |
| Authors: | Gao Mingliang |
| |
| Institution: | Gao Mingliang(Department of Automatic Control Engineering,Shenyang Institute of Engineering,Liaoning Shenyang 110136) |
| |
| Abstract: | Research of fault detection based-on principal component analysis(PCA)is one of the important branches in fault detection domain.This paper firstly introduces the theory of principal component analysis,and then specially studies the sensor fault detection based on principal component analysis in the control system.The method divides the measure space into two subspaces:principal component subspace and residual subspace(RS) based on the correlation analysis of measure data.It can detect sensor faults by comparing the projections in RS of actual sensors measurement and normal data matrix.In the end,the results show that the PCA approach has good performance in the fault detection of sensors,which are based on fault simulation. |
| |
| Keywords: | Principal Component Analysis Fault detection Fault detectability Sensor |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
