Porosity Prediction of Hollow Fiber Membrane Incorporating Neural Network and Digital Image Processing

摘要

The porosity of Hollow Fiber Membrane (HFM) is one of the main factors to evaluate the membrane performance in a special application. The study aims to introduce a novel and convenient method to calculate the overall porosity of the membrane. The artificial neural network (ANN) with a radial basis function (RBF) scheme was used to analyze the qualitative information of the outer surface of HFM based on the results obtained through a Field Emission Scanning Electron Microscope (FESEM) images. An image processing computer program was then developed to measure the HFM surface porosity from the FESEM images. The calculated overall porosity of the HFM was compared with the mathematical model. It was found that there is no significant difference in terms of results for both methods, thereby confirming the applicability of ANN for assessing the membrane porosity. This work presents a useful framework to evaluate the overall porosity of HFM considering different dope compositions and spinning conditions.