A Neural Network-Based Application to Identify Cubic Structures in Multi Component Crystalline Materials Using X-Ray Diffraction Data.

摘要

One of the crystalline materials structures is cubic. Anudexperimental study has been done about developing a scheme to identify the cubic structure types in single or multi component materials. This scheme is using fingerprints created from the calculation of quadratic Miller indices ratios and matches it with the ratio of the sin20 values from the diffracted data of material obtained by X-Ray Diffraction (XRD) method. These manual matching processes are complicated and sometimes are tedious because the diffracted data are complex and may have more thanudone fingerprint inside. This paper proposes an application of multi-layered back-propagation neural network in matching the fingerprints with the diffracted data of crystalline material to quickly and correctly identify its cubic structure component types.ud