کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
724077 | 892361 | 2007 | 6 صفحه PDF | دانلود رایگان |
An awareness of the likely future behaviour of a batch or fed-batch fermentation process is valuable information that can be exploited to improve product consistency and maximise profitability. For example, by making operational policy changes in a feedforward control sense, improved consistency can be facilitated, whilst prior knowledge of batch productivity, or the end time, can help determine the downstream processing configuration and upstream process scheduling. In this paper, forecasting methods based on multivariate batch statistical data analysis procedures are contrasted with case based reasoning (CBR). Two case studies are considered, fed-batch pharmaceutical fermentation and batch beer fermentation. It is demonstrated that following appropriate statistical pre-screening of the data, CBR is comparable to linear projection to latent structures (PLS) for the more straightforward forecasting problem whilst for the more complex problem, CBR is preferable.
Journal: IFAC Proceedings Volumes - Volume 40, Issue 4, 2007, Pages 145–150