Me-Me′-X系三元化合物形成规律的人工神经网络

ARTIFICIAL NEURAL NETWORK APPLIED TO REGULARITY OF FORMATION OF TERNARY COMPOUNDS IN Me Me′ X SYSTEMS

用ｒＭｅ，ｒＭｅ′，ｒＸ，ｘＭｅ和ｘＭｅ′等原子参数作为人工神经网络的输入，２０３个可信的ＭｅＭｅ′Ｘ体系的三元化合物的形成情况作为输出，研究了ＭｅＭｅ′Ｘ系三元化合物的形成规律，这里ｒ是离子半径，ｘ是电负性，Ｍｅ代表一价金属，Ｍｅ′代表二价金属，Ｘ代表卤族元素。利用所得规律预报了ＭＥｕＩ（Ｍ＝Ｌｉ，Ｎａ，Ｋ，Ｒｂ和Ｃｓ）系三元碘化物的形成情况，应用差热分析和粉末Ｘ射线法测定了它们的相图。

Using the atomic parameters of r Me , r Me′ , r X, x Me and x Me′ as the inputs, the regularity of formation of ternary complex halides of Me Me′ X halides systems has been investigated by artificial neural networks(ANNs). Where, r is the radius of the ion, x is the electronegativity of element, Me is the mono valent metal, Me′ is di valent metal, X represents the F, Cl, Br or I. The regularity was found by training the ANNs with 203 known samples (such as Ag Ca Cl system and K Mg Cl system etc.). The formation of ternary complex iodides in M Eu I systems (where M represents Li, Na, K, Rb or Cs) was predicted by this trained ANNs. The predicted results are completely in agreement with the experimental facts.