Search

Coaxial bioreactors are known for effectively dispersing gas inside non-Newtonian fluids. However, due to their design complexity, many aspects of their design and function, including the relationship between hydrodynamics and bioreactor efficiency, remain unexplored. Nowadays, various numerical models, such as computational fluid dynamics (CFD) and artificial intelligence models, provide exceptional opportunities to investigate the performance of coaxial bioreactors. For the first time, this study applied various machine learning models, both classifiers and regressors, to predict the torque generated by a coaxial bioreactor. In this regard, 500 CFD simulations at different aeration rates, central impeller speeds, anchor impeller speeds, and rotating modes were conducted. The results obtained from the CFD simulations were used to train and test the machine learning models. Careful feature scaling and k-fold cross-validation were performed to enhance all models' performance and prevent overfitting. A key finding of the study was the importance of selecting the right features for the model. It turns out that just by knowing the speed of the central impeller and the torque generated by the coaxial bioreactor, the rotating mode can be labelled with perfect accuracy using k-nearest neighbors (kNN) or support vector machine models. Moreover, regression models, including multi-layer perceptron, kNN, and random forest, were examined to predict the torque of the coaxial impellers. The results showed that the random forest model outperformed all other models. Finally, the feature importance analysis indicated that the rotating mode was the most significant parameter in determining the torque value. [ABSTRACT FROM AUTHOR]

Aerated stirred vessels are commonly employed to enhance gas dispersion. However, the associated high energy consumption is a challenging feature, particularly when dealing with complex non‐Newtonian fluids. Coaxial mixers comprising a central impeller and a close‐clearance impeller have emerged as an energy‐efficient alternative that effectively intensifies gas dispersion. Hence, the objective of this study is to investigate the effect of aeration and agitation on the gas dispersion effectiveness of a coaxial mixer containing a yield‐pseudoplastic fluid. An anchor‐pitched blade turbine was employed to disperse air into a 1 wt.% xanthan gum solution, and the analysis primarily focused on characterizing the gas holdup and fluid flow behaviour. Gas holdup data were obtained experimentally using electrical resistance tomography (ERT), while computational fluid dynamics (CFD) simulations provided a detailed analysis of fluid flow patterns within the coaxial mixer. The rotational speed of the impeller exhibited a non‐monotonic effect on the gas holdup, and a significant influence of the interaction between variables was identified. For instance, the experimental data showed that the aeration effect varied with the anchor speed. Nevertheless, the variables' interaction effect was explained by the change in flow pattern observed numerically. Furthermore, the CFD results demonstrated that high gas holdup does not necessarily indicate intensified mixing. Therefore, combining experimental data and numerical simulations enables a more accurate characterization of mixing performance. These findings contribute to the understanding and improvement of mixing performance in such a complex system, which is crucial for designing efficient operations. [ABSTRACT FROM AUTHOR]