An artificial neural network (ANN) model was used to predict the weight loss of MgO-C composites at different temperatures and graphite contents. The general idea of ANN modelling was presented and after that the empirical weight loss data were used for both model verification and assessment of the oxidation rate predictions. The model was proved to have an astounding power in predicting kinetic parameters of the oxidation process. Graphite oxidation was, for example, found to be controlled by alternative diffusion steps. Plotting the Arrhenius law curves for graphite oxidation indicated a distinguishable slope change at a critical temperature which was related to the graphite content. This temperature indicated alternative diffusion mechanisms: (1) pore diffusion with higher activation energy (about 30-200kJmole−1) due to CO saturation at temperatures higher than the critical temperature and (2) pore diffusion at temperatures lower than the critical temperature with activation energies of about 20-30kJ/mol.

Oxygen Diffusion Mechanism in MgO-C Composites - an Artificial Neural Network Approach. A.Nemati, E.Nemati: Modelling and Simulation in Materials Science and Engineering, 2012, 20[1], 015016