Online prediction for contamination of chlortetracycline fermentation based on Dezert–Smarandache theory

doi:10.1016/j.cjche.2014.06.043

Chinese Journal of Chemical Engineering ›› 2015, Vol. 23 ›› Issue (6): 1009-1016.DOI: 10.1016/j.cjche.2014.06.043

Online prediction for contamination of chlortetracycline fermentation based on Dezert–Smarandache theory

Jianwen Yang, Xiangguang Chen, Huaiping Jin

School of Chemical Engineering and Environment, Beijing Institute of Technology, Beijing 100081, China

收稿日期:2014-05-04 修回日期:2014-06-30 出版日期:2015-06-28 发布日期:2015-07-09
通讯作者: Xiangguang Chen

Online prediction for contamination of chlortetracycline fermentation based on Dezert–Smarandache theory

Jianwen Yang, Xiangguang Chen, Huaiping Jin

School of Chemical Engineering and Environment, Beijing Institute of Technology, Beijing 100081, China

Received:2014-05-04 Revised:2014-06-30 Online:2015-06-28 Published:2015-07-09
Contact: Xiangguang Chen

摘要/Abstract

摘要： Fermentative production of chlortetracycline is a complex fed-batch bioprocess. It generally takes over 90 h for cultivation and is often contaminated by undesired microorganisms. Once the fermentation system is contaminated to certain extent, the product quality and yieldwill be seriously affected, leading to a substantial economic loss. Using information fusion based on the Dezer–Smarandache theory, self-recursive wavelet neural network and unscented kalman filter, a novel method for online prediction of contamination is developed. All state variables of culture process involving easy-to-measure and difficult-to-measure variables commonly obtained with soft-sensors present their contamination symptoms. By extracting and fusing latent information fromthe changing trend of each variable, integral and accurate prediction results for contamination can be achieved. Thismakes preventive and correctivemeasures be taken promptly. The field experimental results showthat themethod can be used to detect the contamination in time, reducing production loss and enhancing economic efficiency.

关键词: Chlortetracycline fermentation, Online prediction of contamination, Dezert&ndash, Smarandache theory, Self-recursive wavelet neural network, Unscented kalman filter

Abstract: Fermentative production of chlortetracycline is a complex fed-batch bioprocess. It generally takes over 90 h for cultivation and is often contaminated by undesired microorganisms. Once the fermentation system is contaminated to certain extent, the product quality and yieldwill be seriously affected, leading to a substantial economic loss. Using information fusion based on the Dezer-Smarandache theory, self-recursive wavelet neural network and unscented kalman filter, a novel method for online prediction of contamination is developed. All state variables of culture process involving easy-to-measure and difficult-to-measure variables commonly obtained with soft-sensors present their contamination symptoms. By extracting and fusing latent information fromthe changing trend of each variable, integral and accurate prediction results for contamination can be achieved. Thismakes preventive and correctivemeasures be taken promptly. The field experimental results showthat themethod can be used to detect the contamination in time, reducing production loss and enhancing economic efficiency.

Key words: Chlortetracycline fermentation, Online prediction of contamination, Dezert&ndash, Smarandache theory, Self-recursive wavelet neural network, Unscented kalman filter

Jianwen Yang, Xiangguang Chen, Huaiping Jin. Online prediction for contamination of chlortetracycline fermentation based on Dezert–Smarandache theory[J]. Chinese Journal of Chemical Engineering, 2015, 23(6): 1009-1016.

Jianwen Yang, Xiangguang Chen, Huaiping Jin. Online prediction for contamination of chlortetracycline fermentation based on Dezert–Smarandache theory[J]. Chin.J.Chem.Eng., 2015, 23(6): 1009-1016.

参考文献

[1] Z. Hoš?álek, Relationship between the carbohydrate metabolism of Streptomyces aureofaciens and the biosynthesis of chlortetracycline, Folia Microbiol. 9 (2) (1964) 78-88.

[2] A.O. Onadipe, Prediction of microbial contamination in cell culture using a laser scanning system, BioPharm 14 (2001) 38-40.

[3] L. Jimenez, Light up the life in microbial contamination, Pharm. Formul. Qual. (August/September 2001) 54-55.

[4] I. Elmroth, A. Fox, O. Holst, L. Larsson, Prediction of bacterial contamination in cultures of eukaryotic cell by gas chromatography-mass spectrometry, Biotechnol. Bioeng. 42 (1993) 421-429.

[5] B.A. Plantz, J. Anderen, L.A. Smith, M.M. Meagher, V.L. Schlegel, Prediction of nonhost viable contamination in Pichia pastoris culture and fermentation broth, J. Ind. Microbiol. Biotechnol. 30 (2003) 643-650.

[6] J.R. Swartz, N. McFarland, Genetic approaches to the prediction of contaminants in Escherichia coli fermentations, Biotechnol. Prog. 14 (1998) 88-91.

[7] R. Van Beurden, R. Mackintosh, New developments in rapid microbiology using immunoassays, Food Agric. Immunol. 6 (1994) 209-214.

[8] O. Xu, Y. Fu, H. Su, et al., A selective moving window partial least squares method and its application in process modeling, Chin. J. Chem. Eng. 22 (7) (2014) 799-804.

[9] C.Q. Cheryl, H. Juergen, Processmonitoring and parameter estimation via unscented kalman filtering, J. Loss Prev. Process Ind. 22 (2009) 703-709.

[10] G. Yang, X. Li, Y. Qian, A real-time updated model predictive control strategy for batch processes based on state estimation, Chin. J. Chem. Eng. 22 (3) (2014) 318-329.

[11] J. Wang, L. Zhao, T. YU, On-line estimation in fed-batch fermentation process using state space model and unscented kalman filter, Chin. J. Chem. Eng. 18 (2) (2010) 258-264.

[12] Y.W. Zhang, Z.Y. Hu, On-line batch process monitoring using hierarchical kernel partial least squares, Chem. Eng. Res. Des. 89 (2011) 2078-2084.

[13] W.W. Dong, Y. Yao, F.R. Gao, Phase analysis and identification method for multiple batch process with partitioning multi-way principal component, Chin. J. Chem. Eng. 20 (6) (2012) 1121-1127.

[14] J. Mori, J. Yu, Quality relevant nonlinear batch process performance monitoring using a kernel based multiway non-gaussian latent subspace, J. Process Control 24 (2014) 57-71.

[15] X. Zhao, W.W. Yan, H.H. Shao, Nonlinear statistical process monitoring and fault diagnosis based on kernel fisher discriminant analysis, J. Chem. Ind. Eng. 58 (4) (2007) 951-956 (in Chinese).

[16] X.D. Li, X.H. Huang, J. Dezert, L. Duan, M.Wang, A successful application of DSmT in sonar grid map building and comparison with DST-based approach, Int. J. Innov. Comput. Inf. Control 3 (3) (2007) 539-549.

[17] A. Tchamova, T. Semerdjive, J. Dezert, Estimation of target behavior tendencies using DSmT, Prco. Of Fusion 2003, Cairns, Australia, July 8-11, 2003.

[18] S. Corgne, L. Hubert-Moy, J. Dezert, J. Mercier, Land cover change prediction with a new theory of plausible and paradoxical reasoning, Proc. Of Fusion 2003 Conf., Cairns, Australiz, July 8-11, 2003.

[19] F. Smarandache, J. Dezert, Information fusion based on new proportional conflict redistribution rules, Proceedings of Fusion 2005 Conf., Philadelphia, July 26-29, 2005.

[20] J.Y. Sung, H.C. Yoon, B.P. Jin, Generalized Predictive Control Based on Self-recurrent Wavelet Neural Network for Stable Path Tracking ofMobile Robots: Adaptive Learning Rates Approach, IEEE Transactions on Circuits and System—I: Regular Papers, 53(6), 2006, pp. 1381-1394.

[21] K. Xiong, H.Y. Zhang, C.W. Chan, Performance evaluation of UKF-based nonlinear filtering, Automatica 42 (2006) 261-270.

[22] J.W. Yang, X.G. Chen, H.P. Jin, L. WU, Study on the industrial chlortetracycline fermentation feed rate adjustment method based on soft sensor, Chin. J. Sci. Instrum. 35 (2) (2014) 468-474.

Online prediction for contamination of chlortetracycline fermentation based on Dezert–Smarandache theory

Online prediction for contamination of chlortetracycline fermentation based on Dezert–Smarandache theory

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

本文评价

[1]	Wentao Cang, Huizhong Yang. Estimation of catalytic activity using an unscented Kalman filtering in condensation reaction[J]. Chinese Journal of Chemical Engineering, 2015, 23(12): 1965-1969.
[2]	王建林, 赵利强, 于涛. On-line Estimation in Fed-batch Fermentation Process Using State Space Model and Unscented Kalman Filter[J]. , 2010, 18(2): 258-264.