Artificial intelligence-based prediction of crossflow microfiltration with a graphical user interface

The neural network model is used to estimate the permeate flux during the crossflow microfiltration process of aqueous solutions containing guar and xanthan gums at temperatures of 25°C and 40°C. For the simulations, membrane type, solution composition, filtration time, temperature, transmembrane pressure, and flow velocity were used as input variables. The model, developed in Python using the TensorFlow library, achieved an average percentage error of 2.71% for the training dataset and 5.79% for the test dataset. In addition, a graphical user interface (GUI) was developed using the Glade library, allowing users to easily and efficiently obtain permeate flux values.