(559h) Development of a Deep Neural Network for the Prediction of Local Gas Holdup Profiles in Bubble Columns

Estimating local gas holdup profiles in bubble columns is key for their performance evaluation and optimization, as well as for design and scale-up tasks. However, there are important limitations in the accuracy and range of applicability of the available models in literature. A promising alternative for advancing the knowledge of the local holdup distributions in bubble columns is found in the application of Machine Learning techniques; nevertheless, up to these days there are no developed Neural Networks for the prediction of local gas holdups in bubble columns, and particularly radial profiles. In a great extent, the main drawback preventing the application of these techniques in previous years was the availability of a large enough databank of local gas holdup experimental measurements. Advances over the last decades in measurement techniques have allowed to have enough data reported in literature to gather a significative databank for these models’ development. In this work, a new databank containing 1252 experimental points was gathered and used for the development of a Deep Neural Network (DNN). The new DNN allowed a highly accurate prediction of the local gas holdup profiles, exhibiting a Mean Squared Error 0.001. Furthermore, the DNN allowed to estimate the single and multi-feature effects of the operation conditions, geometrical characteristics, and physical properties of the fluids, over the local gas holdup profiles