CIESC Journal ›› 2016, Vol. 67 ›› Issue (7): 3109-3117.DOI: 10.11949/j.issn.0438-1157.20151811

Previous Articles    

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

HE Fan, JIANG Juncheng, PAN Yong, NI Lei   

  1. Jiangsu Key Laboratory of Hazardous Chemicals Safety and Control, College of Safety Science and Engineering, Nanjing Tech University, Nanjing 210009, Jiangsu, China
  • Received:2015-12-02 Revised:2016-04-06 Online:2016-07-05 Published:2016-07-05
  • Supported by:

    supported by the National Natural Science Foundation of China (21436006, 21576136) and the Major Project of the Natural Science Foundation of Jiangsu Province (12KJA620001).

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

何凡, 蒋军成, 潘勇, 倪磊   

  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, 江苏 南京 210009
  • 通讯作者: 蒋军成
  • 基金资助:

    国家自然科学基金项目(21436006,21576136);江苏省自然科学基金重大项目(12KJA620001)。

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: