论文信息 - Incorporation of Raw Material Quality Information on Fermentation Estimation Models

Incorporation of Raw Material Quality Information on Fermentation Estimation Models

Abstract This paper investigates the influence of the quality of complex raw materials in a fermentation process by developing data-based models (using Multiway Partial Least Squares) for final productivity estimation in an industrial antibiotic production operated by Eli Liliy. Near infrared (NIR) spectroscopy measurements of a selected raw material are available. Wavelets are used to compress the NIR spectra for use in the models, while still retaining the main information about the raw material.

[1] D. Kell,et al. Variable selection in wavelet regression models , 1998 .

[2] Desire L. Massart,et al. Noise suppression and signal compression using the wavelet packet transform , 1997 .

[3] Ward,et al. Fermentation seed quality analysis with self-organising neural networks , 1999, Biotechnology and bioengineering.

[4] A. J. Morris,et al. Multivariate Statistical Process Control in Batch Process Monitoring , 1996 .

[5] S. Wold,et al. PLS regression on wavelet compressed NIR spectra , 1998 .

[6] D. Kirwan,et al. Correlation of Fermentation Yield with Yeast Extract Composition as Characterized by Near‐Infrared Spectroscopy , 1998, Biotechnology progress.

[7] S. Wold,et al. Multi‐way principal components‐and PLS‐analysis , 1987 .

[8] Junbin Gao,et al. A review on applications of wavelet transform techniques in chemical analysis: 1989–1997 , 1998 .

[9] Jarka Glassey,et al. An assessment of seed quality and its influence on productivity estimation in an industrial antibiotic fermentation. , 2002, Biotechnology and bioengineering.

[10] Alexander Kai-man Leung,et al. Application of wavelet transform in infrared spectrometry: spectral compression and library search , 1998 .

[11] D. Kell,et al. An introduction to wavelet transforms for chemometricians: A time-frequency approach , 1997 .