中文摘要：

计算了44个烷基苯酚类化合物的组成、拓扑、几何、静电和量子化学等结构参数，运用启发式方法对这些结构参数进行筛选，得到了含3个变量的化合物的定量结构与色谱保留值的线性关系模型，同时以这3个变量作为支持向量机模型的输人变量建立非线性回归模型。两种方法的相关系数（R。）分别为0．98和0．92，相应的均方根误差分别是0．99和2．77。通过对两种模型的稳定性和预测能力的比较，发现线性模型能够更好地反映烷基苯酚的气相色谱保留值与其结构参数之间的定量关系。在已知烷基苯酚类化合物结构参数的情况下，线性回归模型更有助于它们的色谱分析。

英文摘要：

Alkylphenols are a group of permanent pollutants in the environment and could adversely disturb the human endocrine system. It is therefore important to effectively separate and measure the alkylphenols. To guide the chromatographic analysis of these compounds in pracrice, the development of quantitative relationship between the molecular structure and the retention time of alkylphenols becomes necessary. In this study, topological, constitutional, geometrical, electrostatic and quantum-chemical descriptors of 44 alkylphenols were calculated using a software, CODESSA, and these descriptors were pre-selected using the heuristic method. As a result, three-descriptor linear model （LM） was developed to describe the relationship between the molecular structure and the retention rime of alkylphenols. Meanwhile, the non-linear regression model was also developed based on support vector machine （SVM） using the same three descriptors. The correlation coefficient （R2 ） for the LM and SVM was 0.98 and 0.92, and the corresponding root-mean-square error was 0.99 and 2.77, respectively. By comparing the stability and prediction ability of the two models, it was found that the linear model was a better method for describing the quantitative relationship between the retention time of alkylphenols and the molecular structure. The results obtained suggested that the linear model could be applied for the chromatographic analysis of alkylphenols with known molecular structural parameters.