[1]时静洁,袁雄军,邵辉,等.基于遗传算法对有机物热导率的预测研究[J].常州大学学报(自然科学版),2017,(01):86-92.[doi:doi:10.3969/j.issn.2095-0411.2017.01.015]
　SHI Jingjie,YUAN Xiongjun,SHAO Hui,et al.Prediction of the Thermal Conductivity of Organic Compounds Based on the Genetic Algorithm[J].Journal of Changzhou University(Natural Science Edition),2017,(01):86-92.[doi:doi:10.3969/j.issn.2095-0411.2017.01.015]
点击复制

基于遗传算法对有机物热导率的预测研究()
分享到：

常州大学学报(自然科学版)[ISSN:2095-0411/CN:32-1822/N]

卷:
期数:
2017年01期
页码:
86-92
栏目:
安全工程
出版日期:
2017-01-28

文章信息/Info

Title:
Prediction of the Thermal Conductivity of Organic Compounds Based on the Genetic Algorithm
作者:
时静洁; 袁雄军; 邵辉; 王凯全; 陈海群
常州大学 环境与安全工程学院,江苏 常州 213164
Author(s):
SHI Jingjie;  YUAN Xiongjun;  SHAO Hui;  WANG Kaiquan;  CHEN Haiqun
School of Environmental & Safety Engineering, Changzhou University, Changzhou 213164, China
关键词:
热导率;  遗传算法;  多元线性回归;  预测;  定量构效关系
Keywords:
thermal conductivity;  genetic algorithm;  multiplelinearregression;  prediction;  quantitativestructure-property relationship
分类号:
X 937
DOI:
doi:10.3969/j.issn.2095-0411.2017.01.015
文献标志码:
A
摘要:
根据定量构效关系(Quantitative Structure-Property Relationship,QSPR)原理,研究热导率与其分子结构间的内在定量关系。以178种有机化合物作为样本集,随机选择142种作为训练集,36种作为测试集,采用遗传算法(Genetic Algorithm,GA)进行变量选择,得到5个特征描述符作为模型的输入变量,结合多元线性回归(Multiple Linear Regression,MLR)方法建立了遗传-多元线性回归(GA-MLR)预测模型。研究结果表明:GA-MLR模型的训练集和测试集的复相关系数分别为0.808 0和0.742 2,其均方根误差分别为0.109 8和0.129 3,预测效果令人满意。随后采用残差分析图对样本集进行了残差分析,进一步验证模型在建立过程中未产生系统误差。采用“Y-随机性检验”方法对模型进行了研究,发现预测模型不存在“偶然相关”现象,具备较强的稳定性。该研究提供了一种有效预测有机化合物热导率的方法。
Abstract:
The quantitative relationship between the thermal conductivity and the molecular structure of the organic compound was investigated based on the QSPR principle. The datasets of 178 kinds of organic compounds were randomly divided into the train set(142)and the test one(36). GeneticAlgorithm(GA)was well adapted to the variable selection. As a result, five descriptors were screened out from a large pool of calculated descriptors as input parameters for the model. Coupled with these descriptors, Multiple Linear Regression(MLR)method was employed to build the GA-MLR model. In the model, the square correlation coefficient(R2)of the train set and the test one were 0.808 0 and 0.742 2, and the Root Mean Square Error(RMSE)were 0.109 8 and 0.129 3, respectively. The above results showed that the built modelis robust are very satisfying. Then, the sample was analyzed with the residual analysis as to further validate no systematic error in the process of the model. In addition, Y-randomization was applied to determine that there is no chance correlation in the model. It was seen that the established model had strong stability. This research provides a new and effective method for predicting the thermal conductivity of organic compounds.

参考文献/References:

[1]张苗, 刘幸娜, 陈阵, 等. 辐射强度对建筑典型外保温材料燃烧性能影响的试验研究[J]. 中国安全科学学报, 2013, 23(12): 42-47.
[2]漆政昆, 张和平, 黄冬梅, 等. 消防服用织物材料热湿舒适性综合评价[J]. 中国安全科学学报, 2012, 22(4): 133-138.
[3]娄江峰,张华,王瑞祥. 纳米冷冻机油热导率的实验研究[J]. 化工进展, 2015, 34(2): 495-499.
[4]杨晨, 高思云. 基于热传导反问题的各向异性材料热物性预测方法[J]. 化工学报, 2007, 58(6): 1378-1384.
[5]袁超,段斌,李岚,等. 热界面材料热导率和接触热阻的测试[J].化工学报, 2015, 66(S1): 349-353.
[6]彭国文, 肖方竹, 聂长明, 等. 液相链烷烃热导率与其结构定量关系[J]. 化工学报, 2011, 62(3): 604-610.
[7]WEI X H, WANG L Q. Synthesis and thermal conductivity of microfluidic copper nanofluids[J]. Particuology, 2010, 8(3): 262-271.
[8]RIDES M, MORIKAWA J, HALLDAHL L, et al. Intercomparison of thermal conductivity and thermal diffusivity methods for plastics[J]. Polymer Testing, 2009, 28(5): 480-489.
[9]COQUARD R, PANEL B. Adaptation of the FLASH method to the measurement of the thermal conductivity of liquids or pasty materials[J]. International Journal of Thermal Sciences, 2009, 48(4): 747-760.
[10]HUANGL H, LIUL S. Simultaneous determination of thermal conductivity and thermal diffusivity of food and agricultural materials using a transient plane-source method[J]. Journal of Food Engineering, 2009, 95(1): 179-195.
[11]NAGASAKA Y, NAGASHIMA A. Simultaneous measurement of the thermal conductivity and the thermal diffusivity of liquids by the transient hot-wire method[J]. Review of Science Instruments, 1981, 52(2): 229-232.
[12]许路加,胡明,杨海波,等.基于微结构参数建模的多孔硅绝热层热导率研究[J].物理学报, 2010, 59(12): 8794-8800.
[13]时静洁, 陈利平, 陈网桦, 等. 基于启发式方法和支持向量机方法预测有机物的热导率[J]. 物理化学学报, 2012, 28(12): 2790-2796.
[14]KAUFFMAN G, JURSP C. Prediction of surface tension, viscosity, and thermal conductivity for common organic solvents using quantitative structure-property relationships[J]. Journal of Chemical Information and Computer Science, 2001, 41(2): 408-418.
[15]TOROPOVA A, LESZCZYNSKA D, LESZCZYNSKI J. Predicting thermal conductivity of nanomaterials by correlation weighting technological attributes codes[J]. Materials Letters, 2007, 61(26): 4777-4780.
[16]蒋海燕, 施小斌, 杨小秋, 等. 基于BP神经网络的测井资料预测岩石热导率[J]. 测井技术, 2012, 36(3): 304-307.
[17]GHARAGHEIZI F, KASHKOULIP I, SATTARI M, et al. Development of a quantitative structure-liquid thermal conductivity relationship for pure chemical compounds[J]. Fluid Phase Equilibria, 2013,355: 52-80.
[18]时静洁, 陈利平, 石宁, 等. 基于遗传算法的支持向量机预测有机物自燃点的研究[J]. 中国安全科学学报, 2011, 21(7): 125-129.
[19]XIAO H, LEE L H. Simulation optimization using genetic algorithms with optimal computing budget allocation[J]. Simulation, 2014, 90(10): 1146-1157.
[20]ZHANGY X. An improved QSPR method based on support vector machine applying rational sample data selection and genetic algorithm-controlled training parameters optimization[J]. Chemometrics and Intelligent Laboratory Systems, 2014, 134: 34-46.
[21]XIA X H, SUN H W. Curve fitting based on genetic algorithms for quantitative resolution in overlapped fluorescence spectra[J]. Spectroscopy and Spectral Analysis, 2012, 32(8): 2157-2161.
[22]冯琳琳,张兆志,王新颖, 等. 取代芳烃对发光菌急性毒性的QSAR研究[J]. 常州大学学报(自然科学版), 2012, 24(4): 8-12.
[23]马沛生. 有机化合物实验物性数据手册——含碳、氢、氧、卤部分[M]. 北京: 化学工业出版社, 2006.
[24]HELGUERA A M, COMBES R D, GONZALEZ M P, et al.Applications of 2D descriptors in drug design: a DRAGON tale[J].Current Topics in Medicinal Chemistry, 2010, 8(18): 1628-1655.
[25]CUBILLAN N, MARRERO P Y, ARIZA R H, et al.Novel global and local 3D atom-based linear descriptors of the Minkowski distance matrix: theory, diversity-variability analysis and QSPR applications[J].Journal of Mathematical Chemistry, 2015, 53(9): 2028-2064.
[26]JOUYBAN A, SHAYANFAR A,GHAFOURIAN T, et al.Solubility prediction of pharmaceuticals in dioxane plus water mixtures at various temperatures: Effects of different descriptors and feature selection methods[J].Journalof MolecularLiouids, 2014, 195: 125-131.
[27]TEBBY C, MOMBELLI E, PANDARD P, et al. Exploring an ecotoxicity database with the OECD(Q)SAR Toolbox and DRAGON descriptors in order to prioritise testing on algae, daphnids, and fish[J]. Science of the Total Environment, 2011, 409(18): 3334-3343.
[28]BOROTA A, MRACEC M, GRUIA A, et al. A QSAR study using MTD method and dragon descriptors for a series of selective ligands of alpha C-2 adrenoceptor[J]. European Journal of Medicinal Chemistry, 2011, 46(3): 877-884.
[29]MELANIE M. An Introduction to genetic algorithms[M]. London: MIT Press, 1999.
[30]ROGERS D. Application of genetic function approximation to quantitative structure-activity relationships and quantitative structure-property relationships[J]. Journal of Chemical Information and Computer Sciences, 1994, 34(4): 854-866.
[31]STAVROU M, BARDOW A, GROSS J. Estimation of the binary interaction parameter Kij of the PC-SAFT Equation of State based on pure component parameters using a QSPR method[J]. Fluid Phase Equilibria, 2016, 416: 138-149.
[32]TROPSHA A, GRAMATICA P, GOMBAR V K. The importance of being earnest: validation is the absolute essential for successful application and interpretation of QSPR models[J]. QSAR & Combinatorial Science, 2003, 22(1): 69-77.
[33]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.
[34]CHIRICO N, GRAMATICA P. Real external predictivity of QSAR models. Part 2.new intercomparable thresholds for different validation criteria and the need for scatter plot inspection[J]. Journal of Chemical Information and Modeling, 2012, 52: 2044-2068.

相似文献/References:

[1]刘付喜,钱苏翔,曹 坚.基于遗传算法的BP神经网络在声音智能监控中应用[J].常州大学学报(自然科学版),2012,(03):70.
　LIU Fu-xi,QIAN Su-xiang,CAO Jian.Application of Optimized BP Neural Network Based on Genetic Algorithm in Intelligent Sound Monitoring[J].Journal of Changzhou University(Natural Science Edition),2012,(01):70.
[2]冯琳琳,张兆志,王新颖,等.取代芳烃对发光菌急性毒性的QSAR研究[J].常州大学学报(自然科学版),2012,(04):8.
　FENG Lin-lin,ZHANG Zhao-zhi,WANG Xin-ying,et al.QSAR Study on Acute Toxicity of Substituted Aromatic Compounds to Photobacterium Phosphoreum[J].Journal of Changzhou University(Natural Science Edition),2012,(01):8.
[3]刘 东,周祖德.基于多代理系统的车间动态调度模型设计[J].常州大学学报(自然科学版),2008,(01):59.
　LIU D ong,ZH OU Zu- de.Model Design of Dynamic Workshop Scheduling Based on Multi- Agent System[J].Journal of Changzhou University(Natural Science Edition),2008,(01):59.
[4]葛安杰,屠懿,彭剑.基于机器学习的含缺陷PE管道承载能力研究[J].常州大学学报(自然科学版),2022,34(06):34.[doi:10.3969/j.issn.2095-0411.2022.06.005]
　GE Anjie,TU Yi,PENG Jian.Study on the Carrying Capacity of the PE Pipeline with Defects Based on Machine Learning[J].Journal of Changzhou University(Natural Science Edition),2022,34(01):34.[doi:10.3969/j.issn.2095-0411.2022.06.005]

备注/Memo

备注/Memo:
收稿日期:2016-05-10。
基金项目:常州大学科研启动基金(ZMF15020112); 常州市科技支撑计划项目(社会发展)(CE20155025); 建筑消防工程技术公安部重点实验室开放课题(KFKT2014MS02)。
作者简介:时静洁(1987—),女,江苏常州人,博士,讲师。通讯联系人:陈海群(1970—),E-mail:shijingjie@cczu.edu.cn
更新日期/Last Update: 2017-02-10