论文信息 - Soft-sensing method based on modified ANN inversion and its application in erythromycin fermentation

Soft-sensing method based on modified ANN inversion and its application in erythromycin fermentation

In this paper, we modify the soft-sensing method based on ANN inversion. By using the non-state variables or the so-called function variables besides the state variables, the possibility in constructing the soft-sensing model will increase and the derivative order in soft-sensing model will be low. The simulation results verify that the soft-sensing method based on the modified ANN inversion is more accurate than the unmodified one.

Guohai Liu | Xianzhong Dai | Yuhan Ding

[1] José Ferrer,et al. A methodology for sequencing batch reactor identification with artificial neural networks: A case study , 2009, Comput. Chem. Eng..

[2] Tianyou Chai,et al. Adaptive moving window MPCA for online batch monitoring , 2004, 2004 5th Asian Control Conference (IEEE Cat. No.04EX904).

[3] A Chéruy,et al. Software sensors in bioprocess engineering , 1997 .

[4] D. Wilson,et al. Experiences implementing the extended Kalman filter on an industrial batch reactor , 1998 .

[5] R. Machado,et al. Soft-sensor Based on Artificial Neuronal Network for the Prediction of Physico-chemical Variables in Suspension Polymerization Reactions , 2011 .

[6] Xianzhong Dai,et al. "Assumed inherent sensor" inversion based ANN dynamic soft-sensing method and its application in erythromycin fermentation process , 2006, Comput. Chem. Eng..

[7] C. A. Kent,et al. A structured model for penicillin production on mixed substrates , 1998 .

[8] Bogdan Gabrys,et al. Data-driven Soft Sensors in the process industry , 2009, Comput. Chem. Eng..

[9] Gülnur Birol,et al. A modular simulation package for fed-batch fermentation: penicillin production , 2002 .

[10] B. De Baets,et al. Artificial neural network models of the rumen fermentation pattern in dairy cattle , 2008 .