论文部分内容阅读
本文研究了MOCVD外延生长Ga1-xAlxAs1-ySby半导体薄膜的生长条件与外延层组成的关系,并用人工神经网络法总结有关气固平衡规律。结果表明,用气相组成,载气流量和生长温度等影响外延层组成的主要参数作为人工神经网络的输入,以固相Ga1-xAlxAs1-ySby中的Al和Sb的含量x、y作为输出,训练的人工神经网络可以预报固相组成x、y,得到满意结果。
In this paper, the relationship between the growth conditions of Ga1-xAlxAs1-ySby semiconductor films grown by MOCVD and the composition of epitaxial layers is studied. The laws of gas-solid equilibrium are summarized by artificial neural network. The results show that the main parameters affecting the composition of the epitaxial layer, such as the gas phase composition, the carrier gas flow rate and the growth temperature, are used as the input of the artificial neural network. The contents of Al and Sb in the solid-phase Ga1-xAlxAs1-ySby are output as the output The artificial neural network can predict the solid phase composition x, y, to obtain satisfactory results.