| Title |
Masės perdavimo procesų bioreaktorių sistemose tyrimas / |
| Translation of Title |
Investigation of mass transfer processes in bioreactor systems. |
| Authors |
Baltaitis, Nerijus |
| Full Text |
|
| Pages |
70 |
| Keywords [eng] |
mixing ; aeration ; artificial neural network ; bioreactor ; Multilayer Perceptron |
| Abstract [eng] |
In this final master's project the mass transfer process in bioreactor systems is investigated. Using data stationary state method, for two real processes the values of the coefficient of mass transfer from gas to liquid phase (k_L a) are calculated. Artificial neural network models were developed in Matlab programming environment using NNSYSID and NNTOOL packages. With the help of black box models, the values of k_L a in a different mass transfer processes were identified. The comparison of artificial neural network forecasting quality was performed. The impact of the number of hidden layer neurons on the quality of forecasting was analyzed. The results show that the artificial neural network can be applied for the k_L a value assessment in the different fermentation systems. The created models can be used for model-based optimization of bioprocesses when an intensity of mass transfer processes is one of the factors limiting the performance of the process. |
| Dissertation Institution |
Kauno technologijos universitetas. |
| Type |
Master thesis |
| Language |
Lithuanian |
| Publication date |
2015 |
