Artificial neural network modeling of O₂ separation from air in a hollow fiber membrane module

Abstract

In this study artificial neural network (ANN) modeling of a hollow fiber membrane module for separation of oxygen from air was conducted. Feed rates, transmembrane pressure, membrane surface area, and membrane permeability for the present constituents in the feed were network input data. Output data were rate of permeate from the membrane, the amount of N 2 in the remaining flow, and the amount of O 2 in the permeate flow. Experimental

Transport Properties of Asymmetric Hollow Fiber Membrane Permeators for Practical Applications: Mathematical Modelling for Binary Gas Mixtures

“…Equations (24)(25) were obtained with the help of Equation (12) and an equation derived from the sum of Equations (12)(13). Equations (26) and (27) were derived from Equations (21) and (16) using dimensionless parameters, respectively. The value of y 0 is calculated from Equation (15), and K 1 and K 2 are defined as follows:…”

“…To solve the above ODEs (Equations (22)(23)(24)(25)(26)(27)), the following boundary conditions were used:…”

“…The differential equations were approximated by means of orthogonal polynomials and then the resulting system of non-linear algebraic equations was solved by the Brown method. Madaeni et al [27] accounted for the dependence of gas mixture viscosity on pressure and concentration following the Wilke method. [28] The method proposed by Chung et al [26,29] was used in the present study in order to consider the temperature dependence of gas viscosity: …”

“…In the present study, the pressure build-up in the lumen-side (permeate-side) of a hollow fiber membrane was calculated by applying the Hagen-Poiseuille equation to obtain a suitable equation (Equation (27)). At the end of model simulation, the Reynolds number (Re) is calculated for confirmation of the laminar flow assumption (Re must be less than 2100).…”

“…Furthermore, the values of DT along the fiber length are different. Permeate-side temperature was used in the differential Equation (27), SRK EOS, as well as in the equations proposed by Chung et al [29] and Jossi et al [30] to calculate permeate-side pure viscosities.…”