(中國科學(xué)院上海冶金研究所，上海 200050)
摘 要: 應(yīng)用原子參數(shù)-人工神經(jīng)網(wǎng)絡(luò)研究了MM'O3型的復(fù)氧化物的熔點與原子參數(shù)之間的關(guān)系，并利用已知樣本集訓(xùn)練的人工神經(jīng)網(wǎng)絡(luò)對MM'O3型復(fù)氧化物的熔點用“留一法”進行了預(yù)報，預(yù)報結(jié)果與實測值符合較好，誤差一般小于5%。研究結(jié)果表明，選擇適當(dāng)?shù)脑訁?shù)-人工神經(jīng)網(wǎng)絡(luò)算法可以用于M2O3-M'2O3系形成的MM'O3型復(fù)氧化物的熔點的預(yù)報。
關(guān)鍵字: 氧化物系 相圖計算 復(fù)氧化物
（Shanghai Institute of Metallurgy, Chinese Academy of Sciences, Shanghai200050, P. R. China）
Abstract:ANN-atomic parameter method was used in investigating the regularity of the melting point of MM'O3 type intermediate compounds. A method for the prediction of the melting points of MM'O3 type intermediate compounds was proposed. And three atomic parameters of constituent elements, ionic radii Ri, electronegativity X, covalent radii Rc and the known melting points data of MM'O3-type compounds were used to find a mathematical model for the melting point prediction, with ANN as the method of computation. The predicted results agree well with the experimental ones.
Key words: oxide system calculation of phase diagram complex oxide
