二元互溶可燃混合液体闪点预测模型研究  

Prediction model for the flash point of the binary mutually mixed flammable liquid

作　　者：宋晓亚[1] 潘勇[1] 蒋军成[1] 徐迅[1] SONG Xiao-ya PAN Yong JIANG Jun-cheng XU Xun(Jiangsu Key Laboratory of Hazardous Chemicals Safety and Control, College of Safety Science and Engineering, Nanjing Tech University, Nanjing 210009, China)

机构地区：[1]南京工业大学安全科学与工程学院江苏省危险化学品本质安全与控制技术重点实验室,南京210009

出　　处：《安全与环境学报》2016年第6期133-140,共8页Journal of Safety and Environment

基　　金：国家自然科学基金项目(21436006;21576136);江苏省高校自然科学基金重大项目(12KJA620001)

摘　　要：基于定量结构-性质相关性(QSPR)原理,开展二元互溶可燃混合液体闪点与其结构信息间的内在定量关系(M-QSPR)研究。以332个不同组成和配比的二元互溶可燃混合液体闪点试验数据作为研究样本,根据体系中各纯组分的结构信息,计算相应的混合物描述符(SiRMS,Simplex Representation of Molecular Structure),应用遗传-多元线性回归(GA-MLR)算法从中优化筛选出一组与该体系闪点最密切相关的原子碎片参数作为输入参数,分别采用多元线性回归(MLR)和支持向量机(SVM)算法建立理论预测模型,并将其与文献已有模型进行比较。结果表明,MLR和SVM对测试集样本的平均绝对误差(AAE)分别为4.142 K、1.551 K,均方根误差(RMSE)分别为4.911 K、2.220 K,决定系数(R^2)分别为0.818、0.962。研究表明,影响二元混合液体闪点的主要SiRMS结构因素是■和■,并且随体系中■、■、■四原子碎片增多,闪点升高;随体系中■、■、■四原子碎片增多,闪点降低。同时,与内部交互作用和分子间非加和作用相比,分子间的可加和作用对该体系闪点的影响更为显著;与原子的局部电荷相比,原子类型对该体系闪点的影响更为显著。The paper is aimed at introducing a prediction model for the flash point of the binary miscible mixed flammable liquid in an inherently quantitative relation between the flash points and the structure of the binary miscible combustible liquid （M - QSPR） based on the quantitative structure ＆ characteristic relation （QSPR） system. In the given paper, we have settled the flash points of the experimental data of 332 mixed binary miscible flammable liquids in different components and proportions as our study samples. And, then, we have worked out the corresponding simplex representation of molecular structure （SiRMS） parame- ters of the mixtures in accordance with the molecular structure of each component. And, next, we have managed to screen out a set of atom fragments parameters that contribute to the flash points of the binary miscible liquid mixtures with the Genetic Algorithm combined with multiple linear regression （GA - MLR）. And, consequently, we have established the selected parameters as in- put parameters, and built up the theoretical prediction models by comparing the aforementioned models with those proposed in the previous literatures as the Multiple Linear Regression （MLR） and Support Vector Machine （SVM） methods. The results of our ex- perimental study have shown that the average absolute deviation （ AAE）, the root mean square error （RMSE）, the squared corre- lation coefficient （R2） of the testing set by MLR turn to be equal to4. 142K, 4. 911K, 0. 818, respectively. The AAE, RMSE, R2 of the testing sets by SVM stand for 1. 551 K, 2. 220 K, 0. 962, respectively. And, finally, it has been made easier to explain the main structural features and their effects on the flash points of the said liquid mixtures by clarifying the mechanism of the system. Thus, it would be easier to clarify the main SiRMS structural features affecting the flash points of binary miscible flammable liquid mixtures. At the same time, it can also be found that, the more the contents of are, the

关 键 词：安全工程 混合物定量结构-性质相关性研究 二元互溶 混合液体 闪点 原子碎片 

分 类 号：X931[环境科学与工程—安全科学]