Prediction of auto-ignition temperatures for binary liquid mixtures based on electro-topological state indices

doi:10.11949/j.issn.0438-1157.20151811

Abstract

Abstract:

The auto-ignition temperature (AIT) values of 168 sets of binary flammable liquid mixtures composed of different components and volume ratios were measured by AITTA 551 auto-ignition temperature tester. The mixed electro-topological state indices (ETSI) values of different atom types were calculated. The modified particle swarm optimization (MPSO) algorithm with exponential decreasing inertia weight (EDIW) was applied to optimize the support vector machine (SVM) hyper-parameters and MPSO-SVM prediction model was established. The model was employed in research for predicting the AIT of mixtures according to the mixed ETSI values of different atom types. The results showed that it could effectively predict the AIT of binary liquid mixtures based on electro-topological state indices. The squared correlation coefficient (R²) and average absolute error (AAE) of MPSO-SVM model were 0.991 and 3.962 K, respectively. In terms of model generalization performance and prediction accuracy, the result of MPSO-SVM model was obviously superior to the results of multiple linear regression (MLR), grid search method (GSM-SVM), genetic algorithm (GA-SVM) and particle swarm optimization (PSO-SVM). This study provided an effective method to predict the AIT of binary liquid mixtures for engineering.

Key words: electro-topological state indices, binary mixture, algorithm, auto-ignition temperature, prediction

摘要：

利用AITTA551自燃温度测试仪，测得不同组分和配比下的28组168个二元可燃混合液体自燃温度（AIT）；基于电性拓扑状态指数（ETSI）理论，计算获得不同原子类型所对应的混合ETSI值；采用添加指数递减惯性权重的改进粒子群算法（MPSO）优化支持向量机（SVM）的超平面参数，建立根据原子类型混合ETSI值来预测混合物自燃温度的MPSO-SVM模型。结果表明，基于电性拓扑状态指数能够有效预测二元液体混合物自燃温度，MPSO-SVM模型的复相关系数R²为0.991，平均绝对误差AAE为3.962 K。MPSO-SVM模型的泛化性能和预测精度明显优于多元线性回归（MLR）、网格搜索法（GSM-SVM）、遗传算法（GA-SVM）、标准粒子群算法（PSO-SVM）模型。本研究为工程上提供了一种预测二元混合物自燃温度的有效途径。

关键词: 电性拓扑状态指数, 二元混合物, 算法, 自燃温度, 预测

CLC Number:

O621.2
X937

HE Fan, JIANG Juncheng, PAN Yong, NI Lei. Prediction of auto-ignition temperatures for binary liquid mixtures based on electro-topological state indices[J]. CIESC Journal, 2016, 67(7): 3109-3117.

何凡, 蒋军成, 潘勇, 倪磊. 基于电性拓扑状态指数的二元液体混合物自燃温度的预测[J]. 化工学报, 2016, 67(7): 3109-3117.

References 22

[1]	张宏哲, 王宁, 王亚琴, 等. 活化温度对活性炭自燃危险性的影响[J]. 化工学报, 2012, 63(11): 3730-3735. ZHANG H Z, WANG N, WANG Y Q, et al. Influence of activation temperature on spontaneous ignition behavior of activated carbon [J]. CIESC Journal, 2012, 63(11): 3730-3735.
[2]	YEONG S K, SUNG K L, JAE H K, et al. Prediction of autoignition temperatures (AITs) for hydrocarbons and compounds containing heteroatoms by the quantitative structure-property relationship [J]. Journal of the Chemical Society, Perkin Transactions 2, 2002, 12: 2087-2092.
[3]	PAN Y, JIANG J C, WANG R, et al. Advantages of support vector machine in QSPR studies for predicting auto-ignition temperatures of organic compounds [J]. Chemometrics and Intelligent Laboratory Systems, 2008, 92(2): 169-178.
[4]	PAN Y, JIANG J C, WANG R, et al. Predicting the auto-ignition temperatures of organic compounds from molecular structure using support vector machine [J]. Journal of Hazardous Materials, 2009, 164(2/3): 1242-1249.
[5]	TSAI F, CHEN C, LIAW H. A model for predicting the auto-ignition temperature using quantitative structure property relationship approach [J]. Procedia Engineering, 2012, 45: 512-517.
[6]	BAGHERI M, BORHANI T N G, ZAHEDI G. Estimation of flash point and auto-ignition temperature of organic sulfur chemicals [J]. Energy Conversion and Management, 2012, 58(6): 185-196.
[7]	KONG D, ECKHOFF R K, ALFERT F. Auto-ignition of CH4/air, C3H8/air, CH4/C3H8/air and CH4/CO2/air using a 1 L ignition bomb [J]. Journal of hazardous materials, 1995, 40(1): 69-84.
[8]	ROTA R, ZANOELO E F. Prediction of the auto-ignition hazard of industrial mixtures using detailed kinetic modeling [J]. Industrial and Engineering Chemistry Research, 2003, 42(13): 2940-2945.
[9]	NORMAN F, VAN DEN SCHOOR F, VERPLAETSEN F. Auto-ignition and upper explosion limit of rich propane-air mixtures at elevated pressures [J]. Journal of Hazardous Materials, 2006, 137(2): 666-671.
[10]	VAN DEN SCHOOR F, NORMAN F, VANDEBROEK L, et al. A numerical study of the influence of ammonia addition on the auto-ignition limits of methane/air mixtures [J]. Journal of Hazardous Materials, 2009, 164(2/3): 1164-1170.
[11]	American Institute of Chemical Engineers (AIChE). Design Institute for Physical Properties (DIPPR) [EB/OL]. [2014-09-11]. http://www.aiche.org/dippr/projects/801.
[12]	International Safety Intergovernmental Organization. International Chemical Safety Cards (ICSCs) [EB/OL]. [2010-03-11]. http://www.i-nchem. org/pages/icscs.html.
[13]	蒋军成, 潘勇. 有机化合物的分子结构与危险特性[M]. 北京: 科学出版社, 2011: 231-248. JIANG J C, PAN Y. The Molecular Structure and Dangerous Properties of Organic Compounds [M]. Beijing: Science Press, 2011: 231-248.
[14]	KIER L B, HALL L H. An electro-topological state index for atoms in molecules [J]. Pharmaceutical Research, 1990, 7(8): 801-807.
[15]	HALL L H, KIER L B. Electro-topological state indices for atom types: a novel combination of electro-topological and valencestate information [J]. Journal of Chemical Information and Computer Sciences, 1995, 35(6): 1039-1045.
[16]	安剑奇, 陈易斐, 吴敏. 基于改进支持向量机的高炉一氧化碳利用率预测方法[J]. 化工学报, 2015, 66(1): 206-214. AN J Q, CHEN Y F, WU M. A prediction method for carbon monoxide utilization ratio of blast furnace based on improved support vector regression [J]. CIESC Journal, 2015, 66(1): 206-214.
[17]	张晓南, 刘安心, 刘斌, 等. 基于优化PSO-SVM模型的软件可靠性预测[J]. 计算机应用, 2011, 31(7): 1761-1764, 1772. ZHANG X N, LIU A X, LIU B, et al. Software reliability prediction based on improved PSO-SVM model [J]. Journal of Computer Applications, 2011, 31(7): 1761-1764, 1772.
[18]	CHANG C C, LIN C J. LIBSVM: a library for support vector machines [J]. ACM Transactions on Intelligent Systems and Technology, 2011, 2(3): 389-396.
[19]	王梦寒, 李雁召, 夏知姿, 等. 基于Kriging模型与遗传算法结合的RHCM成型工艺参数优化[J]. 化工学报, 2014, 65(12): 5054-5060. WANG M H, LI Y Z, XIA Z Z, et al. Processing parameters optimization of rapid heat cycle molding based on Kriging meta-model and genetic algorithm [J]. CIESC Journal, 2014, 65(12): 5054-5060.
[20]	GRAMATICA P, PILUTTI P, PAPA E. Validated QSAR prediction of OH tropospheric degradation of VOCs: splitting into training_test sets and consensus modeling [J]. Journal of Chemical Information and Computer Sciences, 2004, 44(5): 1794-1802.
[21]	LIPNICK R L. Outliers: their origin and use in the classification of molecular mechanisms of toxicity [J]. Science of the Total Environment, 1991, 109: 131-153.
[22]	潘勇. 有机物定量结构燃爆特性相关性及预测模型研究[D]. 南京: 南京工业大学, 2009. PAN Y. Research on prediction models and quantitative relationships between the structures and flammability characteristics of organic compounds [D]. Nanjing: Nanjing University of Technology, 2009.