论文信息 - NEURAL NETWORKS IN LYSINE FERMENTATION

NEURAL NETWORKS IN LYSINE FERMENTATION

Abstract Conventional modeling, state estimation, multi-step ahead prediction, and control of bioprocesses is often difficult owing to the uncertainties involved. Back-propagation multi-layer neural network models were constructed to overcome such problems. Neural networks were programmed in MS-Visual C++ for Windows and implemented in a personal computer with an 80486/66 MHz processor. State estimation and multi-step ahead prediction of consumed sugar and produced lysine in a industrial scale bioprocess were successfully demonstrated.

Pekka Linko | S. Linko | Y.-H. Zhu

[1] P Linko,et al. Uncertainties, Fuzzy Reasoning, and Expert Systems in Bioengineering , 1988, Annals of the New York Academy of Sciences.

[2] P. Linko,et al. Neural control of fed-batch baker's yeast fermentation , 1994 .

[3] Maureen Caudill. Expert networks , 1990 .

[4] Pekka Linko,et al. Artificial intelligence in bioprocess modelling, estimation and control , 1994 .

[5] Pekka Linko,et al. Neural network modelling for real-time variable estimation and prediction in the control of glucoamylase fermentation , 1992 .

[6] T. Eerikäinen,et al. Neural networks in extrusion process identification and control , 1994 .

[7] Josiah C. Hoskins,et al. Artificial neural network models for knowledge representation in chemical engineering , 1990 .

[8] A. J. Morris,et al. Towards improved penicillin fermentation via artificial neural networks , 1992 .

[9] Rimvydas Simutis,et al. Fuzzy-aided neural network for real-time state estimation and process prediction in the alcohol formation step of production-scale beer brewing , 1993 .

[10] Pekka Linko,et al. Neural Networks in Enzymology , 1996 .