摘要
以第一组分的摩尔分数和第二组分分子中碳原子数目的差异来表证二元分子体系，利用具有三层拓扑结构的神经网络模型，推算了２８个体系的过量焓，其中内插１６个体系，外推１２个体系，所有体系的相对误差均在５％左右，最大相对误差为７．６８％，最小相对误差为２．２９％。
In this paper, binary molecular systems were represented by the mole fraction of the first component and the number of carbon atmos in the second component, three-layered neural networks trained with backpropagation algorithm were employed to evaluate the excess molar enthalpies of 28 binary systems, of which 16 binary systems were calculated by interpolation and 12 binary systems were calculated by extrapolation. For all the systems, the mean relative error was calculated and the value of it was around 5% , the maximum was 7.68% and the minimum was 2.29%.
出处
《计算机与应用化学》
CAS
CSCD
1998年第4期255-256,共2页
Computers and Applied Chemistry
关键词
二元分子体系
过量焓
神经网络
混合物
Binary molecular system, Excess molar enthalpy, Neural network
