DOI: 10.1615/ICHMT.2009.CONV
ISBN Print: 978-1-56700-261-4
ISSN Online: 2642-3499
ISSN Flash Drive: 2642-3502
MODELLING AND SIMULATION OF MASS TRANSFER IN AN ANISOTROPIC MEDIUM
ABSTRACT
The artificial neural network (ANN) approach is generic technique for mapping non-linear relationships between inputs and outputs without knowing the details of these relationships. In this paper, an application of the ANN has been presented for the calculation of mass transfer in anisotropic porous medium (radial diffusion in wood). The kinetics of desorption of the impregnate solute were measured indirectly by the conductimetric method. In first step, the kinetics of desorption of the impregnate solvent in wood is modeled where the equation of mass is solved using Laplace transforms and the modelling includes simplifying assumptions and suitable initial and boundary conditions, this modelling allows the determination of the apparent diffusivity. An ANN was trained, using eleven parameters as inputs to estimate the apparent diffusivity and efficiency of mass transfer in wood. Also, this paper presents an optimisation methodology that enabled the neural network to deal with different geometry of wood. The mean absolute error in apparent diffusivity, predicted by ANN, was approximately 0.52 %, thus proving that the developed ANN model is a reliable approach with powerful predictive capacity towards the estimation of apparent diffusivity.