Title | ||
---|---|---|
Data-driven prediction of the product formation in industrial 2-keto-l-gulonic acid fermentation |
Abstract | ||
---|---|---|
Mixed culture fermentation of Bacillus megaterium and Gluconobacter oxydans is widely used to produce 2-keto- l -gulonic acid (2-KGA), a key precursor for l -ascorbic acid synthesis. For such mixed cultivation, kinetic modelling is difficult because the interactions between the two strains are not well known yet. In this paper, data-driven prediction of the product formation is presented for the purpose of better process monitoring. A rolling learning-prediction approach based on neural networks is practiced to predict 2-KGA formation. Techniques associated with the approach, such as the data pretreatment and the rolling learning-prediction mechanism, are given in more detail. The validation results by using the data from commercial scale 2-KGA cultivation indicate that the prediction error is less than 5% in the later phase of fermentation and the reliable prediction time span is 8 h. The robustness of the prediction approach is further tested by adding extra noises to the process variables. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1016/j.compchemeng.2011.06.012 | Computers & Chemical Engineering |
Keywords | Field | DocType |
2-Keto-l-gulonic acid,Mixed culture,Neural networks,Product formation,Rolling learning-prediction | 2-keto-L-gulonic acid,Mathematical optimization,Mean squared prediction error,Data-driven,Biological system,Biochemistry,Ascorbic acid,Gluconobacter oxydans,Bacillus megaterium,Gulonic acid,Fermentation,Mathematics | Journal |
Volume | ISSN | Citations |
36 | 0098-1354 | 3 |
PageRank | References | Authors |
0.42 | 1 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lei Cui | 1 | 3 | 0.42 |
Ping Xie | 2 | 3 | 0.42 |
Junwei Sun | 3 | 205 | 8.68 |
Tong Yu | 4 | 3 | 0.42 |
Jing-Qi Yuan | 5 | 26 | 4.97 |