论文部分内容阅读
应用原子参数-人工神经网络研究了MM′O3型的复氧化物的熔点与原子参数之间的关系,并利用已知样本集训练的人工神经网络对MM′O3型复氧化物的熔点用“留一法”进行了预报,预报结果与实测值符合较好,误差一般小于5%。研究结果表明,选择适当的原子参数-人工神经网络算法可以用于M2O3M′2O3系形成的MM′O3型复氧化物的熔点的预报。
The relationship between the melting point and the atomic parameters of MM’O3 type complex oxides was studied by means of the atomic parameter-artificial neural network. The melting point of the MM’O3 type complex oxide was estimated by using the artificial neural network trained by the known sample set. Leave a law "for the forecast, forecast results and measured values in good agreement, the error is generally less than 5%. The results show that the selection of an appropriate atomic parameter - artificial neural network algorithm can be used to predict the melting point of MM’O3 type complex oxide formed by M2O3M’2O3 system.