[1]司风琪,周建新,仇晓智,等.基于APCA的电站热力过程故障传感器自适应检测方法[J].东南大学学报(自然科学版),2009,39(2):282-286.[doi:10.3969/j.issn.1001-0505.2009.02.018]
 Si Fengqi,Zhou Jianxin,Qiu Xiaozhi,et al.Adaptive detection method of sensor failures based on APCA for the thermodynamic system in power plant[J].Journal of Southeast University (Natural Science Edition),2009,39(2):282-286.[doi:10.3969/j.issn.1001-0505.2009.02.018]
点击复制

基于APCA的电站热力过程故障传感器自适应检测方法()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
39
期数:
2009年第2期
页码:
282-286
栏目:
自动化
出版日期:
2009-03-20

文章信息/Info

Title:
Adaptive detection method of sensor failures based on APCA for the thermodynamic system in power plant
作者:
司风琪 周建新 仇晓智 徐治皋
东南大学能源与环境学院, 南京 210096
Author(s):
Si Fengqi Zhou Jianxin Qiu Xiaozhi Xu Zhigao
School of Energy and Environment,Southeast University,Nanjing 210096, China
关键词:
电站 热力系统 主元分析 传感器 故障检测
Keywords:
power plant thermodynamic system principal component analysis sensor fault detection
分类号:
TP206.3
DOI:
10.3969/j.issn.1001-0505.2009.02.018
摘要:
为自动适应电站热力过程的连续变化,提出了基于APCA的电站热力过程传感器故障诊断方法,通过模型参数的自动更新,使模型及时反映当前的系统状态,从而连续可靠运行.对PCA重构残差进行研究,在对电站实际测量数据可靠性分析的基础上提出了参数自适应预估计方法,利用预估计值来替代故障数据,以抑制残差污染,提高重构参数的准确性.利用电厂实际测量参数进行了算例分析,表明所提算法能很快适应系统状态变化,并给出正确的检测结果,即使在系统同时存在多个传感器故障时,通过对不良数据的检验,也能够获得准确的重构数据.
Abstract:
Based on the adaptive principal component analysis(APCA)model, an adaptive detection method of sensor failures is proposed to improve the performance of the monitoring of thermodynamic system in power plant. The model can be adaptively updated to reflect the process change. A pre-estimate model is also developed based on the analysis of data reliability in power plant to replace the bad data from the failed sensors, by which the phenomenon of residual contamination can be restricted and the correct reconstruction result can be achieved. The case study shows the validity of model’s adaptive updating to adapt to the changed process and the better performance of data validation even if there are several failed sensors existed at the same time.

参考文献/References:

[1] 司风琪.电站性能在线监测中的数据检验和热力系统模型研究[D].南京:东南大学能源与环境学院,2001.
[2] Bakshi B R.Multiscale PCA with application to multivariate statistical process monitoring[J]. AIChE Journal,1998,44(7):1596-1610.
[3] Ku W,Storer R H,Georgakis C.Disturbance detection and isolation by dynamic principal component analysis[J].Chemometrics and Intelligent Laboratory Systems,1995,30(1):179-196.
[4] Wold S.Exponentially weighted moving principal component analysis and projection to latent structures[J].Chemometrics and Intelligent Laboratory Systems,1994,23(1):149-161.
[5] Tien D X,Lim K W,Jun L.Comparative study of PCA approaches in process monitoring and fault detection[C] //The 30th Annual Conference of the IEEE Industrial Electronics Society.Busan,South Korea,2004:2594-2599.
[6] 牛征,刘吉臻,牛玉广.动态多主元模型故障检测方法在变工况过程中的应用[J].动力工程,2005,25(4):554-558,598.
  Niu Zheng,Liu Jizhen,Niu Yuguang.Fault detection under varying load conditions based on dynamic multi-principal component models[J]. Power Engineering,2005,25(4):554-558,598.(in Chinese)
[7] 司风琪,洪军,徐治皋.基于向量投影的数据检验PCA方法[J].中国电机工程学报,2002,22(10):157-160.
  Si Fengqi,Hong Jun,Xu Zhigao.Data validation method based on PCA with vector projection[J]. Proceedings of the CSEE,2002,22(10):157-160.(in Chinese)
[8] Li Weihua,Yue H H,Valle-Cervantes S,et al.Recursive PCA for adaptive process monitoring[J].Journal of Process Control,2000,10(5):471-486.
[9] 王海清,宋执环,王慧.PCA过程监测方法的故障检测行为分析[J].化工学报,2002,53(3):297-301.
  Wang Haiqing,Song Zhihuan,Wang Hui.Fault detection behavior anaylysis of PCA-based process monitoring approach[J].Journal of Chemical Industry and Engineering,2002,53(3):297-301.(in Chinese)
[10] Fuat D,Jose A R,Ahmet P.A strategy for detection and isolation of sensor failures and process upsets[J]. Chemometrics and Intelligent Laboratory Systems,2001,55(1):109-123.
[11] Gertler J,Li Weihua,Huang Yunbing,et al.Isolation enhanced principal component analysis[J]. AIChE Journal,1999,45(2):323-334.

备注/Memo

备注/Memo:
作者简介: 司风琪(1973—),男,博士,副教授,fqsi@seu.edu.cn.
引文格式: 司风琪,周建新,仇晓智,等.基于APCA的电站热力过程故障传感器自适应检测方法[J].东南大学学报:自然科学版,2009,39(2):282-286.
更新日期/Last Update: 2009-03-20