A process singular value recognition based recursive PCA approach to mode-transition process monitoring

doi:10.3969/j.issn.0438-1157.2012.09.044

Abstract

Abstract: Conventional PCA method is susceptible to intractable difficulties to monitor a process experiencing mode transitions.In this context,this paper presents a modified recursive PCA approach which combines on-line process singular value recognition algorithms and contributes to mode transition process monitoring.Specifically,an enabling algorithm of process singular value recognition is proposed,which accounts for accurately identifying ongoing mode transition of a process before launching recursive PCA algorithms to monitor the transition phases.TE process is employed as a case study,which demonstrates the benefits of the contribution.

Key words: multi-mode process, monitoring, singular value recognition, recursive PCA

摘要： 常规的PCA方法难于对发生模式变化的过程参数进行监控,为此,本文提出了一种基于奇异值识别递归PCA技术,用于解决多模式切换过程的监控问题。首先建立了在线奇异值识别算法,通过识别奇异值的变化可以准确判断过程发生模式切换的时间,然后采用递归PCA对过程的模式切换过渡阶段进行监控。将TE过程用于实例研究,验证了所提出方法的有效性。

关键词: 多模式过程, 监控, 奇异值识别, 递归PCA

CLC Number:

TP277

WANG Qian, LI Hongguang. A process singular value recognition based recursive PCA approach to mode-transition process monitoring[J]. CIESC Journal, 2012, 63(9): 2948-2952.

王倩, 李宏光. 基于奇异值识别的模式切换过程递归PCA监控[J]. 化工学报, 2012, 63(9): 2948-2952.

References 15

[1]	Zhang Xinrong(张新荣).Researches on continuous process performance monitoring and fault diagnosis based on PCA.Wuxi:Jiangnan University,2008
[2]	Guo Ming(郭明).Researches on performance monitoring and fault diagnosis for process industry based on data-driven technique.Hangzhou:Zhejiang University,2004
[3]	Young-Hak Lee,Kwang Gi Min,Chonghun Han,et al. Process improvement methodology based on multivariate statistical analysis methods[J].Control Engineering Practice,2004,12:945-961
[4]	Liu Shaobo(刘少波).Study of monitoring and fault diagnosis in industrial process based on the theory of multivariate statistics.Harbin:Harbin University of Science and Technology,2008
[5]	Yang Peiwu(杨沛武).Study of multivariate statistical method based on probabilistic PCA on the process monitoring.Wuxi:Jiangnan University,2008
[6]	Xu Yongmao(徐用懋),Zhao Shijian(赵仕健).Multivariate statistical process monitoring and safe operating [J].Computers and Applied Chemistry(计算机与应用化学),2007,24(4):475-478
[7]	Yu Jianbo.Hidden Markov models combining local and global information for nonlinear and multimodal process monitoring[J].Journal of Process Control,2010,20:344-359
[8]	Mohammad H,Fazel Z,Adel A.A general fuzzy-statistical clustering approach for estimating the time of change in variable sampling control charts[J].Information Sciences,2010,180:3033-3044
[9]	Mauricio M,Andrés F,Pablo G,Miryan C,Gabriel H.A robust clustering method for detection of abnormal situations in a process with multiple steady-state operation modes[J].Computers and Chemical Engineering,2010,34:223-231
[10]	Dae-Hee Hwang,Chonghun Han.Real-time monitoring for a process with multiple operating modes[J].Control Engineering Practice,1999,7:891-902
[11]	Jyh-Cheng Jeng.Adaptive process monitoring using efficient recursive PCA and moving window PCA algorithms [J].Journal of the Taiwan Institute of Chemical Engineers,2010,41(4):475-481
[12]	Pearson K.On lines and planes of closest fit to systems of points in space[J].Edinburgh and Duhlin Philosophical Magazine and Journal of Science,1901,6(2):572-575
[13]	Manabu K,Koji N,Shinji H,Iori H,Hiromu O,Ramon S,Bhavik B.Comparison of statistical process monitoring methods:application to the Eastman challenge problem[J].Computers and Chemical Engineering,2000,24:175-181
[14]	Jiang Haotian(蒋浩天),Duan Jianmin(段建民).Fault Detection and Diagnosis in Industrial Systems(工业系统的故障检测与诊断)[M].Beijing:China Machine Press,2003:98-107
[15]	Zhao Zhonggai(赵忠盖).Some studies on statistical process monitoring based on PCA.Wuxi:Jiangnan University,2007