A datamining approach to classify, select and predict the formation enthalpy for intermetallic compound hydrides

In this paper, two techniques of datamining tools were adopted, a principal component analysis (PCA) and artificial neural network (ANN). A PCA to classify, select and identify several combinations between transition element A and B (B = Ti, Zr, Hf, Sc, Y, La and Th) and ANN to predict OH for ternary hydrides. Based on the datasets selected from different works, a principal component analysis (PCA) has been applied to select, classify and identify around 76 possible combinations between transition metal elements A and B. The results showed that the clustering of combinations A-B are significantly influenced by the atomic parameters of element A, such atomic radius (RA), Pauling's electronegativity NA) and atomic electron density (ZA/Ri). From 76 combinations, 55 systems which have 3CA > 1.5, ZA/Ri>1.28 and RA < 1.46 A are categorized as group 1. On the other hand, 21 systems which have xi, < 1.5, ZA/R3A < 1.28, and RA > 1.46 A are categorized as group 2. From the first group, 46 different combinations are identified and have a negative AH, within 18 well-known promising binary alloys of hydrogen storage. An (6-15-1) architecture of artificial neural network (ANN) has been developed to estimate the Ali for the other ternary hydrides selected from different published works. The performance indices such as relative error, coefficient of determination (R2) and mean square error (MSE) were used to control the performance of obtained results. In addition to this, the tH obtained from ANN model were compared with those experimental data and theoretical results available in the literature. (C) 2018 Hydrogen Energy Publications LLC. Published by Elsevier Ltd. All rights reserved.