Analysis of sensor fault detection in chiller based on PCA method

HU Yunpeng; CHEN Huanxin; ZHOU Cheng; YANG Xiaoshuang; XU Rongji

doi:10.3969/j.issn.0438-1157.2012.z2.016

您当前的位置：

首页 >

文章列表页 >

Analysis of sensor fault detection in chiller based on PCA method

更新时间：2025-12-10

- Analysis of sensor fault detection in chiller based on PCA method
- CIESC Journal Issue S2, Pages: 85-88(2012)
- 作者机构：
  
  1. 华中科技大学环境科学与工程学院,湖北,武汉,430074
  2. 北京建筑工程学院供热供燃气通风及空调工程北京市重点实验室,北京,100044
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.0438-1157.2012.z2.016
  CLC： B65
- Online First：28 December 2012，
  
  Published：28 December 2012
- 稿件说明：
移动端阅览
HU Yunpeng, CHEN Huanxin, ZHOU Cheng, et al. Analysis of sensor fault detection in chiller based on PCA method[J]. CIESC Journal, 2012, (S2): 85-88.
DOI：

HU Yunpeng, CHEN Huanxin, ZHOU Cheng, et al. Analysis of sensor fault detection in chiller based on PCA method[J]. CIESC Journal, 2012, (S2): 85-88. DOI： 10.3969/j.issn.0438-1157.2012.z2.016.

摘要

冷水机组是一个高度非线性的复杂系统

其自控系统传感器故障会导致冷水机组的运行偏离正常状态和能耗浪费。采用冷水机组正常运行数据

通过多元统计方法中的主元分析法建立训练矩阵

利用平方预测误差进行故障分析工作。引入不同程度故障

分析主元分析法的检测效率。结果表明

主元分析法故障检测效果明显

但对于不同传感器的不同程度故障

故障检测的误判率存在一定的差异。

Abstract

Chiller is a highly nonlinear complex system.The sensor fault in the automation system of chiller will cause it to operate in unmoral situation and waste energy.Based on the principal component analysis(PCA)method

one of the analytical methods in multivariate statistics

the data in normal condition have been used to establish the train matrix.The square prediction error(SPE)has been used to analyze the sensor fault.The detection efficiency has been analyzed by the PCA method with introducing different level faults into the chiller.The result shows that PCA-based fault detection method works well

but the fault detection efficiencies of different sensors with different level faults are inconsistent.

关键词

Keywords

references

Views

405

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Fault detection using hierarchical variational Gaussian mixture model and principal polynomial analysis

Fault detection method based on state space-PCANet

DLNS-PCA-based fault detection for multimode batch process

Fault detection method based on minimum sufficient statistics pattern analysis

A process monitoring method based on informative principal component subspace reconstruction

Related Author

LI Yuan

YANG Dongsheng

ZHAO Liying

ZHANG Cheng

DONG Shun

LI Yiguo

SUN Shuanzhu

LIU Xichui

Related Institution

College of Information Engineering, Shenyang University of Chemical Technology

Department of Science, Shenyang University of Chemical Technology

School of Energy and Environment, Southeast University

Key Laboratory of Energy Thermal Conversion and Control of Ministry of Education, Southeast University

Jiangsu Frontier Electric Technology Company Limited

⁰