Conventional experimental design techniques are available to assist in the optimization of fermentation processes, but due to the nonlinearities in the bioprocess, they are limited in their effectiveness. This problem is further complicated with recombinant systems as a result of the additional complexities of the process. This article describes a general strategy using artificial neural networks as an alternative approach to fermentation process development laboratory are presented for the neural network based procedures. (c) 1994 John Wiley & Sons, Inc.

No abstract

No abstract

No abstract

upon Tyne, NE1 7RU, UK. This paper demonstrates how multivariante statistical data analysis procedures used as feature extraction methods can assist in the operation of an industrial fermentation process. The quality of the production fermenter seed and the subsequent forecasting of productivity are the two examples considered, with results presented from industrial plant. The feature extraction methodologies utilised are based around principal component analysis (PCA) and the extension to batch systems through the use of multi-way PCA.