节点文献
利用神经网络推算二元混合物体系的过量
EVALUATION OF EXCESS MOLAR ENTHALPIES OF BINARY SYSTEMS USING NEURAL NETWORKS
【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%。
【Abstract】 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%.
【关键词】 二元分子体系;
过量焓;
神经网络;
【Key words】 Binary molecular system; Excess molar enthalpy; Neural network;
【Key words】 Binary molecular system; Excess molar enthalpy; Neural network;
- 【文献出处】 计算机与应用化学 ,COMPUTERS AND APPLIED CHEMISTRY , 编辑部邮箱 ,1998年04期
- 【分类号】O189.3,O642.1
- 【被引频次】3
- 【下载频次】16