(中國科學院上海冶金研究所， 上海 200050;
*北京師范大學， 北京 100081)
摘 要: 用rMe, rMe', rX, xMe和xMe'等原子參數(shù)作為人工神經(jīng)網(wǎng)絡的輸入， 203個可信的Me-Me'-X體系的三元化合物的形成情況作為輸出，研究了Me-Me'-X系三元化合物的形成規(guī)律，這里r是離子半徑，x是電負性， Me代表一價金屬， Me'代表二價金屬，X代表鹵族元素。利用所得規(guī)律預報了M-Eu-I（M=Li，Na， K， Rb和Cs）系三元碘化物的形成情況， 應用差熱分析和粉末X射線法測定了它們的相圖，預報結果和實驗測定結果的對比是令人滿意的。
關鍵字: 三元化合物 相圖 計算機預報 人工神經(jīng)網(wǎng)絡
（Shanghai Institute of Metallurgy, Chinese Academy of Sciences, Shanghai 200050, P. R. China;
* Beijing Normal University, Beijing 100081, P. R. China）
Abstract:Using the atomic parameters of rMe, rMe', rX, xMe and xMe as the inputs, the regularity of formation of ternary complex halides of MeMe'-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.
Key words: ternary compound phase diagram computer prediction artificial neural network
