| Popis: |
The main and crucial fundamental thermodynamic properties are the enthalpy’s formation. It is know that the enthalpy of formation plays a keys role in energy balance calculation combustion properties, equilibrium constants of reactions and fuel characteristics of materials. Several methods have been carried out in calculation and estimating the enthalpy of formation, such a semi empirical model, Miedema model and density functional theory calculations. Currently, the datamining is the newly developed approach which attracts and increasing care of the material science researches. In the current paper, the one know datamining approach based on artificial neural network (predictive technique) has been proposed to estimate the enthalpy formation for several hydrides. An (3-13-1) architecture structure has been developed to predict the enthalpy of formation for rare-earth dihydrides CeH2, PrH2 and DyH2, Also, an (6-15-1) architecture of artificial neural network has been developed to estimate the enthalpy of formation, for the 39 ternary hydrides selected from different published works. The performance indices such a relative error, coefficient of determination and mean square error were used to control the performance of obtained results. The obtained results for enthalpy of formation for CeH2, PrH2 and DyH2 are basically consistent with the density functional theory and are in good agreement with experimental data. In other hand, the obtained results for 39 ternary hydrides are also in good agreement with experimental data available in the literature. |
