Abstract:

In this paper, the self-organization neural network tree is presented to discriminate the amorphous state of trinary fluoride on the basis of some chemical bond parameters. And the computer intelligence expert system is built. The successful rate is high. The results indicates that the performance of the neural network method is good, and therefore it might be referred as an effective supplementary technique for the discrimination of amorphous state of compounds.

Key words: Fluoride, Amorphous state, Neural network