1097-0290/asset/BIT_left.gif?v=1&s=5f6054ce9ff7b0421e44e8e4e33966356f37b71c)
Fermentation seed quality analysis with self-organising neural networks
Article first published online: 26 MAR 2000
DOI: 10.1002/(SICI)1097-0290(19990705)64:1<82::AID-BIT9>3.0.CO;2-5
Copyright © 1999 John Wiley & Sons, Inc.
1097-0290/asset/cover.gif?v=1&s=169bf64713ffd27abfe496301dbedc7070f98e92 "Biotechnology and Bioengineering")
Additional Information
How to Cite
Ignova, M., Montague, G. A., Ward, A. C. and Glassey, J. (1999), Fermentation seed quality analysis with self-organising neural networks. Biotechnol. Bioeng., 64: 82–91. doi: 10.1002/(SICI)1097-0290(19990705)64:1<82::AID-BIT9>3.0.CO;2-5
Publication History
- Issue published online: 26 MAR 2000
- Article first published online: 26 MAR 2000
- Manuscript Accepted: 30 NOV 1998
- Manuscript Received: 19 MAY 1998
- Abstract
- References
- Cited By
Keywords:
- Kohonen SOM;
- batch processes;
- fault detection;
- fermentation
Abstract
Industrial fermentation processes operate under well defined operating conditions to attempt to minimise production variability. Variability occurs for many reasons but a long held belief is that variation in the state of the seed is highly influential. In this paper a seed stage (a batch process) of an industrial antibiotic fermentation is considered and the performance of the main production fermentations is correlated with the quality of the seed using an unsupervised Kohonen self-organising feature map (SOM). It is shown that using only seed information poor performance in the final stage fermentations can be predicted. Data from industrial penicillin G fermenters is used to demonstrate the procedure. © 1999 John Wiley & Sons, Inc. Biotechnol Bioeng 64: 82–91, 1999.