建立一个用于预测和模拟玻璃形成合金的临界尺寸的人工神经网络模型;基于该人工神经网络模型优化设计一系列Zr-Al-Ni-Cu和Cu-Zr-Ti-Ni块体非晶合金的成分并对其临界尺寸进行预测。采用真空喷注法制备Zr-Al-Ni-Cu和Cu-Zr-Ti-Ni块体非晶合金试样。这些块体合金的非晶态结构采用X射线衍射法进行表征并确定这些合金的非晶形成的临界尺寸。结果表明,预测的临界尺寸与实验结果吻合较好,所建立的神经网络模型能可靠地设计非晶合金的成分和预测非晶合金的临界尺寸。 An artificial neural network model for predicting and simulating the critical size of the glass-forming alloy was established. Based on the artificial neural network model, a series of Zr-Al-Ni-Cu and Cu-Zr-Ti-Ni bulk amorphous alloys Composition and predict its critical size. Zr-Al-Ni-Cu and Cu-Zr-Ti-Ni bulk amorphous alloy samples were prepared by vacuum injection method. The amorphous structure of these bulk alloys was characterized by X-ray diffraction and the critical dimensions for the amorphous formation of these alloys were determined. The results show that the predicted critical dimension agrees well with the experimental results. The neural network model established can reliably design the composition of amorphous alloys and predict the critical size of amorphous alloys.