NonliNonlinear GPC with In-place Trained RLS-SVM Model for DOC Control in a Fed-batch Bioreactor*

Chinese Journal of Chemical Engineering ›› 2012, Vol. 20 ›› Issue (5): 988-994.

NonliNonlinear GPC with In-place Trained RLS-SVM Model for DOC Control in a Fed-batch Bioreactor^*

冯絮影, 于涛, 王建林

College of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China

收稿日期:2011-03-12 修回日期:2011-06-08 出版日期:2012-10-28 发布日期:2012-11-06
通讯作者: WANG Jianlin,E-mail:wangjl@mail.buct.edu.cn
基金资助:
Supported by the National Natural Science Foundation of China (20476007, 20676013)

NonliNonlinear GPC with In-place Trained RLS-SVM Model for DOC Control in a Fed-batch Bioreactor^*

FENG Xuying, YU Tao, WANG Jianlin

College of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China

Received:2011-03-12 Revised:2011-06-08 Online:2012-10-28 Published:2012-11-06
Supported by:
Supported by the National Natural Science Foundation of China (20476007, 20676013)

摘要/Abstract

摘要： In this study, Saccharomyces cerevisiae (baker's yeast) was produced in a fed-batch bioreactor at the optimal dissolved oxygen concentration (DOC) and growth medium temperature. However, it is very difficult to control the DOC using conventional controllers because of the poorly understood and constantly changing dynamics of the bioprocess. A generalized predictive controller (GPC) based on a nonlinear autoregressive integrated moving average exogenous (NARIMAX) model is presented to stabilize the DOC by manipulation of air flow rate. The NARIMAX model is built by an improved recursive least-squares support vector machine, which is trained by an in-place computation scheme and avoids the computation of the inverse of a large matrix and memory reallocation. The proposed nonlinear GPC algorithm requires little preliminary knowledge of the fermentation process, and directly obtains the nonlinear model in matrix form by using iterative multiple modeling instead of linearization at each sampling period. By application of an on-line bioreactor control, experimental results demonstrate the robustness, effectiveness and advantages of the new controller.

关键词: nonlinear generalized predictive controller, recursive least squares support vector machine, in-place computation, fed-batch bioreactor, dissolved oxygen concentration

Abstract: In this study, Saccharomyces cerevisiae (baker's yeast) was produced in a fed-batch bioreactor at the optimal dissolved oxygen concentration (DOC) and growth medium temperature. However, it is very difficult to control the DOC using conventional controllers because of the poorly understood and constantly changing dynamics of the bioprocess. A generalized predictive controller (GPC) based on a nonlinear autoregressive integrated moving average exogenous (NARIMAX) model is presented to stabilize the DOC by manipulation of air flow rate. The NARIMAX model is built by an improved recursive least-squares support vector machine, which is trained by an in-place computation scheme and avoids the computation of the inverse of a large matrix and memory reallocation. The proposed nonlinear GPC algorithm requires little preliminary knowledge of the fermentation process, and directly obtains the nonlinear model in matrix form by using iterative multiple modeling instead of linearization at each sampling period. By application of an on-line bioreactor control, experimental results demonstrate the robustness, effectiveness and advantages of the new controller.

Key words: nonlinear generalized predictive controller, recursive least squares support vector machine, in-place computation, fed-batch bioreactor, dissolved oxygen concentration

冯絮影, 于涛, 王建林. NonliNonlinear GPC with In-place Trained RLS-SVM Model for DOC Control in a Fed-batch Bioreactor^*[J]. Chinese Journal of Chemical Engineering, 2012, 20(5): 988-994.

FENG Xuying, YU Tao, WANG Jianlin. NonliNonlinear GPC with In-place Trained RLS-SVM Model for DOC Control in a Fed-batch Bioreactor^*[J]. Chin.J.Chem.Eng., 2012, 20(5): 988-994.

参考文献

1 Furukawa,K.,Heinzle,E.,Dunn,I.J.,"Influence of oxygen on the growth of Saccharomyces cerevisiae in continuous culture",Biotechnol.Bioeng.,25 (10),2293-2317 (1983).
2 Lee,S.C.,Hwang,Y.B.,Chang,H.N.,Chang,Y.K.,"Adaptive control of dissolved oxygen concentration in a bioreactor",Biotechnol.Bioeng.,37 (7),597-607 (1991).
3 Sargantanis,I.O.,Karim,M.N.,"Adaptive pole placement control algorithm for DO-control in β-lactamase production",Biotechnol.Bioeng.,60 (1),1-9 (1998).
4 Liang,G.B.,Du,G.C.,Chen,J.,"A novel strategy of enhanced glutathione production in high cell density cultivation of Candida utilis-Cysteine addition combined with dissolved oxygen controlling",Enzyme Microb.Tech.,42,284-289 (2008).
5 Clarke,T.A.,Hesketh,T.,Seddon,T.,"Automatic control of dissolved oxygen tension via fermenter agitation speed",Biotechnol.Bioeng.,27 (10),1507-1511 (1985).
6 Ertunc,S.,Akay,B.,Boyacioglu,H.,Hapoglu,H.,"Self-tuning control of dissolved oxygen concentration in a batch bioreactor",Food Bioprod.Process.,87 (1),46-55 (2009).
7 Siegel,S.D.,Gaden,Jr.,E.L.,"Automatic control of dissolved oxygen levels in fermentations",Biotech.Bioeng.,4 (3),345-356 (1962).
8 Rodrigues,J.A.D.,Toledo,E.C.V.,Maciel Filho,R.,"A tuned approach of the predictive-adaptive GPC controller applied to a fed-batch bioreactor using complete factorial design",Comput.Chem.Eng.,26,1493-1500 (2002).
9 Diaz,C.,Dieu,P.,Feuillerat,C.,Lelong,P.,Salomé,M.,"Adaptive predictive control of dissolved oxygen concentration in a laboratoryscale bioreactor",J.Biotechnol.,43,21-32 (1995).
10 Diaz,C.,Dieu,P.,Feuillerat,C.,Lelong,P.,Salomé,M.,"Simultaneous adaptive predictive control of the partial pressures of dissolved oxygen (pO₂) and dissolved carbon dioxide (pCO₂) in a laboratoryscale bioreactor",J.Biotechnol.,52,135-150 (1996).
11 Bursali,N.,Akay,B.,Ertunc,S.,Hapoglu,H.,Alpbaz,M.,"New tuning method for generalized predictive control of the production of S.cerevisiae",Food Bioprod.Process.,79 (1),27-34 (2001).
12 Zulkeflee,S.A.,Aziz,N.,"Control implementation in bioprocess system: A review",In: Proceedings of 1st International Conference on Control,Instrumentation and Mechatronics Engineering (CIM'07),Othman,M.F.,ed.,Johor Bahru,Johor,Malaysia,798-804 (2007).
13 Bao,Z.J.,Pi,D.Y.,Sun,Y.X.,"Nonlinear model predictive control based on support vector machine with multi-kernel",Chin.J.Chem.Eng.,15 (5),691-697 (2007).
14 Gao,X.J.,Wang,P.,Qi,Y.S.,Zhang,Y.T.,Zhang,H.Q.,Yan,A.J.,"An optimal control strategy combining SVM with RGA for improving fermentation titer",Chin.J.Chem.Eng.,18 (1),95-101 (2010).
15 Suykens,J.A.K.,Vandewalle,J.,"Least squares support vector machine classifiers",Neural Process.Lett.,9 (3),293-300 (1999).
16 Liu,B.,Su,H.Y.,Chu,J.,"Predictive control algorithm based on least squares support vector machines",Control Decis.,19 (12),1439-1402 (2004).(in Chinese)
17 Li,L.J.,Su,H.Y.,Chu,J.,"Generalized predictive control with online least squares support vector machines",Acta Automatica Sin.,33 (11),1182-1188 (2007).
18 Clarke,D.W.,Mohtadi,C.,Tuffs,P.S.,"Generalized predictive control (Ⅰ) The basic algorithm",Automatica,23 (2),137-148 (1987).
19 Clarke,D.W.,Mohtadi,C.,Tuffs,P.S.,"Generalized predictive control (Ⅱ) Extensions and interpretations",Automatica,23 (2),149-160 (1987).
20 Vapnik,V.,"The nature of statistical learning theory",Springer-Verlay,New York (1995).
21 Tang,H.S.,Xue,S.T.,Chen,R.,Sato,T.,"Online weighted LS-SVM for hysteretic structural system identification",Eng.Struct.,28,1728-1735 (2006).Figure 3 Changes in DOC with time under KGPC regulation [with the set point of DOC of 40% (by volume)] Figure 4 Changes in AFR with time under KGPC regulation (corresponding to Fig.3) Figure 5 Changes in DOC with time under KGPC regulation (with the DOC set point changed at 32 h) Figure 6 Changes in AFR with time under KGPC regulation (with the DOC set point changed at 32 h)

NonliNonlinear GPC with In-place Trained RLS-SVM Model for DOC Control in a Fed-batch Bioreactor^*

NonliNonlinear GPC with In-place Trained RLS-SVM Model for DOC Control in a Fed-batch Bioreactor^*

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价