二元系液相分层规律及会溶和偏晶温度的预报

SOME REGULARITIES OF MONOTECTIC BINARY ALLOY SYSTEMS AND PREDICTION OF CONSOLUTE TEMPERATURE AND MONOTECTIC EQUILIBRIUM TEMPERATURE

固相生成金属间化合物的液相分层二元系在Ｍｉｅｄｅｍａ的Δ—Δｎｗｓ１／３图中，分布在Δ＞１．３的区域，然而在该区域混杂有固相没有金属间化合物的液相分层二元系。为了消除这种混杂现象，应用扩展的Ｍｉｅｄｅｍａ合金元胞模型研究了金属液相分层二元系固相能否生成金属间化合物的规律。在由原子参数Δ与Δｎｗｓ１／３及ΔＺ张成的多维空间中，上述两类二元系各自分布在特定的区域。据此结果，以Δ，Δｎｗｓ１／３，ΔＺ，ＲＡ／ＲＢ作为人工神经网络的输入特征量，采用误差反向传递算法，利用经已知样本集训练的人工神经网络对上述二元系的会溶温度和偏晶温度进行预报。

In the Miedema's Δ  *—Δ n ws 1/3 figure, the representative points of monotectic binary alloy system with compound forming in solid state distribute in the region of Δ  *>1.3, however, in the same region that of without compound forming in solid state co distribute. In order to eliminate the mingled phenomenon, an extended Miedema's cellular model of alloys has been applied to study the regularities of whether two metals can combine into compound or not in solid state of monotectic binary alloy systems. In the multi dimensional space spanned by atomic parameters, Δ  *, Δ n ws 1/3 and Δ Z , the representative points of monotectic binary alloy systems with and without compound forming distribute in different regions separately. In addition, by using the error back propagation and four parameters, Δ  *, Δ n ws 1/3 , Δ Z and R A/ R B as the input features of an artificial neural network, the consolute temperature and monotectic equilibrium temperature of these monotectic binary alloy systems are predicted by the artificial neural network trained by known data of phase diagrams. The predicted results are in good agreement with the experimental ones.