中文摘要：

基于定量结构-性质相关性（quantitative structure-property relationship,QSPR）原理,研究了烃类物质爆炸下限与其分子结构间的内在定量关系。根据分子结构计算用于反映分子各种结构信息的结构参数,应用遗传算法从大量结构参数中优化筛选出与爆炸下限最密切相关的一组结构参数作为分子描述符,分别采用支持向量机方法和多元线性回归方法对分子描述符数据与爆炸下限数据之间的内在定量关系进行模拟,建立了根据分子结构预测烃类物质爆炸下限的数学模型。对模型性能进行内部及外部验证,结果表明,2种模型爆炸下限的预测值与实验值均符合良好,在实验误差允许范围之内。支持向量机模型预测体积分数平均绝对误差为0.036%,均方根误差为0.046%,优于多元线性回归和已有方法所得结果。该方法的提出为工程上提供了一种预测烃类物质爆炸下限的新方法。

英文摘要：

The quantitative relationships between the lower flammability limits （LFL） and the molecular structures of hydrocarbon compounds were investigated based on the quantitative structure-property relationship （QSPR） studies. Various structure parameters were calculated to describe the structure characteristics of the molecules based on their structures. A set of structure parameters which have significant contribution to the LFL were chosen as the molecular descriptors by employing the variable selection method of genetic algorithm （GA）. Both the multiple linear regression （MLR） and support vector machine （SVM） were employed to model the possible quantitative relationship existed between these selected descriptors and LFL,respectively,and the corresponding prediction models for the LFL of hydrocarbons based on the molecular structures were constructed. The models were tested by internal and external validations. The results showed that,for both models,the predicted LFL values agreed well with the experimental ones,and the predicted errors were within the range of the experimental error of LFL measurements. The mean absolute error and the root mean square error for the test set of SVM model were 0.036% and 0.046%,respectively,which were better than those of the MLR model and previous models. This paper provides a new method for predicting LFL of hydrocarbons for engineering.