基于滚动MPCA的青霉素发酵过程的在线监控

• SYSTEM ENGINEERING • 上一篇下一篇

基于滚动MPCA的青霉素发酵过程的在线监控

汪志锋^a,b; 袁景淇^a,c

^a Department of Automatic Control, Shanghai Jiao Tong University, Shanghai 200030, China ^b Department of Automation, Shanghai Second Polytechnic University, Shanghai 201209, China ^c State Key Laboratory of Bioreactor Engineering, East China University of Science & Technology, Shanghai 200237, China

收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-02-28 发布日期:2007-02-28
通讯作者: 汪志锋

Online supervision of penicillin cultivations based on rolling MPCA

WANG Zhifeng^a,b; YUAN Jingqi^a,c

^a Department of Automatic Control, Shanghai Jiao Tong University, Shanghai 200030, China ^b Department of Automation, Shanghai Second Polytechnic University, Shanghai 201209, China ^c State Key Laboratory of Bioreactor Engineering, East China University of Science & Technology, Shanghai 200237, China

Received:1900-01-01 Revised:1900-01-01 Online:2007-02-28 Published:2007-02-28
Contact: WANG Zhifeng

摘要/Abstract

摘要： To reduce the variations of the production process in penicillin cultivations, a rolling multivariate statistical approach based on multiway principle component analysis (MPCA) is developed and used for fault diagnosis of penicillin cultivations. Using the moving data windows technique, the static MPCA is extended for use in dynamic process performance monitoring. The control chart is set up using the historical data collected from the past successful batches, thereby resulting in simplification of monitoring charts, easy tracking of the progress in each batch run, and monitoring the occurrence of the observable upsets. Data from the commercial-scale penicillin fer-mentation process are used to develop the rolling model. Using this method, faults are detected in real time and the corresponding measurements of these faults are directly made through inspection of a few simple plots (t-chart, SPE-chart, and T2-chart). Thus, the present methodology allows the process operator to actively monitor the data from several cultivations simultaneously.

关键词: multiway principle component analysis;fermentation;online supervision;fault diagnosis;rolling

Abstract: To reduce the variations of the production process in penicillin cultivations, a rolling multivariate statistical approach based on multiway principle component analysis (MPCA) is developed and used for fault diagnosis of penicillin cultivations. Using the moving data windows technique, the static MPCA is extended for use in dynamic process performance monitoring. The control chart is set up using the historical data collected from the past successful batches, thereby resulting in simplification of monitoring charts, easy tracking of the progress in each batch run, and monitoring the occurrence of the observable upsets. Data from the commercial-scale penicillin fer-mentation process are used to develop the rolling model. Using this method, faults are detected in real time and the corresponding measurements of these faults are directly made through inspection of a few simple plots (t-chart, SPE-chart, and T2-chart). Thus, the present methodology allows the process operator to actively monitor the data from several cultivations simultaneously.

Key words: multiway principle component analysis, fermentation, online supervision, fault diagnosis, rolling

汪志锋, 袁景淇. 基于滚动MPCA的青霉素发酵过程的在线监控[J]. , DOI: .

WANG ,Zhifeng, YUAN ,Jingqi. Online supervision of penicillin cultivations based on rolling MPCA[J]. , DOI: .

参考文献

1    Zhao, X.Q., Rong, G. “Blending scheduling under uncer-tainty based on particle swarm optimization algorithm”, Chin. J. Chem. Eng., 13(4), 535—541(2005).
2    Yoo, C.K., Lee, J.M., Vanrolleghem, P.A., Lee, I.B., “Online monitoring of batch processes using multiway independent component analysis”, Chemom. Intell. Lab. Syst., 71(2), 151—163(2004).
3    Chen, J.H., Liu, K.C., “Online batch process monitoring using dynamic PCA and dynamic PLS models”, Chemi. Eng. Sci., 57(1), 63—75(2002).
4    Lee, J.M., Yoo, C.K., Lee, I.B., “Fault detection of batch processes using multiway kernel principal component analysis”, Comput. Chem. Eng., 28(9), 1837—1847(2004).
5    Lopes, J.A., Menezes, J.C., “Multivariate monitoring of fermentation processes with nonlinear modelling meth-ods”, Anal. Chim. Acta, 515(1), 101—108(2004).
6    Lee, J.M., Yoo, C.K., Lee, I.B., “Enhanced process monitoring of fed-batch penicillin cultivation using time-varying and multivariate statistical analysis”, J. Biotechnol., 110(2), 119—136(2004).
7    Wold, S., “Exponentially weighted moving principal components analysis projections to latent structures”, Chemom. Intell. Lab. Syst., 23,149—161(1994).
8    Wachs, A., Lewin, D.R., “Improved PCA methods for process disturbance and failure identification”, AIChE J., 45, 1688—1700(1999).
9    Chen, J., Liao, C.M., Lin, F.R.J., Lu, M.J., “Principal component analysis based control charts with memory effect for process monitoring”, Ind. Eng. Chem. Res., 40,1516—1527(2001).
10    Lee, J.M., Yoo, C.K., Lee, I.B., “Online batch process monitoring using a consecutively updated multiway principal component analysis model”, Comput. Chem. Eng., 27, 1903—1912(2003).
11    Chen, G., McAvoy, T.J., “Predictive online monitoring of continuous processes”, J. Process Control, 8, 409—420(1998).
12    Wang, Z.F., Yuan, J.Q., Tan, J.D., “Batch process monitor-ing and fault detection based on and improved MPCA”, J. Shanghai Jiaotong Univ., 38(4), 555—558(2004).
13    Yuan, J.Q., Vanrolleghem, P.A., “Rolling learn-ing-prediction of product formation in bioprocesses”, J. Biotechnol., 69, 47—62(1999).
14    MacGregor, J.F., Jaeckle, C., KiParissides, C., Koutoudi, M., “Process monitoring and diagnosis by multiblock PLS methods”, AIChE J., 40(5), 826—838(1994).