A fermentation process monitoring method based on kernel independent component analysis

ZHU YuanChun; YU Tao; WANG JianLin; ZHAO LiQiang

Journal of Beijing University of Chemical Technology ›› 2014, Vol. 41 ›› Issue (2) : 81-86.

PDF(1184 KB)
Welcome to Journal of Beijing University of Chemical Technology, Today is February 21, 2025
Email Alert  RSS
PDF(1184 KB)
Journal of Beijing University of Chemical Technology ›› 2014, Vol. 41 ›› Issue (2) : 81-86.
生物技术和环境工程

A fermentation process monitoring method based on kernel independent component analysis

  • ZHU YuanChun; YU Tao; WANG JianLin; ZHAO LiQiang
Author information +
History +

Abstract

A fermentation process monitoring method based on kernel independent component analysis (KICA) is proposed, and the method is combined with the characteristics of batch process data with a new indicator being used. The indicator effectively extracts information about the deviation between independent components at each moment and their mean in the intermittent process, which overcomes the effects of disturbance more effectively than traditional indicators. The results of penicillin fermentation detection experiments show that fermentation process monitoring based on KICA with the new index is very effective. This method has a greater ability to detect small faults than traditional methods and a low false alarm rate, as well as giving improved accuracy during the monitoring process.

Cite this article

Download Citations
ZHU YuanChun; YU Tao; WANG JianLin; ZHAO LiQiang. A fermentation process monitoring method based on kernel independent component analysis[J]. Journal of Beijing University of Chemical Technology, 2014, 41(2): 81-86

References

[1] 郭明, 谢磊, 王树青. 基于模型的多尺度间歇过程性能监控[J]. 系统工程理论与实践, 2004(1): 97-102. Guo M, Xie L, Wang S Q. Intermittent process performance monitoring based on the model of multi scale [J]. Journal of Engineering System Theory and Practice, 2004(1): 97-102. (in Chinese)[2] 齐咏生, 王普, 高学金, 等. 改进MKPCA方法及其在发酵过程监控中的应用[J]. 仪器仪表学报, 2009, 30(12): 2531-2538. 
Qi Y S, Wang P, Gao X J, et al. The improved MKPCA method and its application in the fermentation process monitoring [J]. Chinese Journal of Scientific Instrument, 2009, 30(12): 2531-2538. (in Chinese)
[3] 刘世成, 王海清, 李平. 基于多向核主元分析的青霉素生产过程在线监测[J]. 浙江大学学报: 工学版, 2007, 41(2): 202-207. 
Liu S C, Wang H Q, Li P. The penicillin production process on line monitoring based on kernel principal component analysis[J]. Journal of Zhejiang University: Engineering Science, 2007, 41(2): 202-207. (in Chinese)
[4] Zhang Y W, Hu Z Y. Multivariate process monitoring and analysis based on multi scale KPLS[J]. Chemical Engineering Research and Design, 2011, 89: 2667-2678. 
[5] Yang J, Gao X M, Zhang D, et al. Kernel ICA: An alternative formulation and its application to face recognition[J]. Pattern Recognition, 2005, 38(10): 1784-1787. 
[6] Tian X M, Zhang X L, Deng X G, et al. Multiway kernel independent component analysis based on feature samples for batch process monitoring[J]. Neurocomputing, 2009, 72(7/8/9): 1584-1596. 
[7] 王丽, 侍洪波. 基于核独立元分析的间歇过程在线监控[J]. 化工学报, 2010, 61(5): 1183-1189. 
Wang L, Si H B. Online batch process monitoring based 〖JP3〗on kernel ICA[J]. CIESC Journal, 2010, 61(5): 1183-1189. (in Chinese)
[8] Chiu S H, Lu C P, Wu D C, et al. A histogram based data reducing algorithm for the fixed point independent component analysis[J]. Pattern Recognition Letters, 2008, 29(3): 370-376. 
[9] 钟蕾, 刘飞. 基于独立元分析的数据重构方法及应用[J]. 系统仿真学报, 2007, 19(17): 4090-4092. 
Zhong L, Liu F. Data reconstruction and application based on independent component analysis[J]. Journal of System Simulation, 2007, 19(17): 4090-4092. (in Chinese)
[10]Wang L, Shi H B. Multivariate statistical process monitoring using an improved independent component analysis[J]. Chemical Engineering Research and Design, 2010, 88: 403-414. 
[11]Birol G, ndey C, inar A. A modular simulation package for fed-batch fermentation: penicillin production [J]. Computers and Chemical Engineering, 2002, 26(11): 1553-1565.
PDF(1184 KB)

1571

Accesses

0

Citation

Detail

Sections
Recommended

/