应用原子类型AI指数预测烃类燃烧热

Predicting the Combustion Heat of Hydrocarbon by Using Atom-type AI Indices

以基于Xu指数的原子类型AI指数作为分子结构描述符,表征了80个液态烃的分子结构特征,并分别结合人工神经网络和多元线性回归方法,对这80种液态烃的燃烧热进行定量结构-性质相关性建模和预测研究。结果表明,基于Xu指数的原子类型AI指数能很好地表征烃类物质的分子结构特征。所建的最佳预测模型为基于Xu指数的原子类型AI指数多元线性回归模型,模型复相关系数为0.999,对测试集的平均预测相对误差为0.637%,模型预测值与实验值的一致性令人满意。

Xu index based atom-type AI indices is used to describe the structures of 80 liquid hydrocarbon molecules,and quantitative structure-property relationship models are developed to predict the heat of combustion of these 80 liquid hydrocarbon by using the artificial neural network and the multilinear regression approach,respectively.The results show that the characteristic of hydrocarbon molecular structures can be well described by Xu index based atom-type AI indices.The best model is obtained by combination of atom-type AI indices and multi-linear regression,whose correlation coefficient and average relative errors between the predicted and experimental values for the testing set is 0.999 and 0.637% respectively.The predicted values of the models are in good agreement with the experimental data.