دانلود رایگان مقاله انگلیسی شناسایی ساختار کریستالی سه بعدی با استفاده از شبکه های عصبی فازی - اشپرینگر 2017

Abstract

The problem of recognizing nano-scale images of lattice projections comes down to identification of crystal lattice structure. The paper considers two types of fuzzy neural networks that can be used for tackling the problem at hand: the Takagi-Sugeno-Kang model and Mamdani-Zadeh model (the latter being a modification of the Wang-Mendel fuzzy neural network). We offer a threestage neural network learning process. In the first two stages crystal lattices are grouped in non-overlapping classes, and lattices belonging to overlapping classes are recognized at the third stage. In the research, we thoroughly investigate the applicability of the neural net models to structure identification of 3D crystal lattices.

CONCLUSIONS

We have offered a three-stage learning technique for neural networks. Crystal lattices are divided into non-overlapping classes in the first two stages. Crystal lattices belonging to overlapping classes are recognized at the last stage. The investigation showed that the Mamdani-Zadeh neural net is particularly sensitive to the size of the learning sample and it is necessary to use no less than 1000 lattices of each lattice system type to ensure efficient work. As compared with parametric identification methods, the use of neural nets makes it possible to decrease the 3D structure identification failure rate for four couples of lattice systems considerably (as much as 2 to 13 times). The research results allow us to draw a conclusion that fuzzy neural networks are an efficient tool in recognition of crystal lattice types using Bravais cells parameters.