基于基团拓扑的遗传神经网络工质临界温度预测

doi:10.11949/j.issn.0438-1157.20160289

摘要/Abstract

摘要：

用遗传神经网络预测工质的临界温度，网络的输入参数为分子基团和拓扑指数，输出参数为临界温度。所划分的16个分子基团涵盖了制冷、热泵及有机朗肯循环系统中的大部分工质，所选拓扑指数能够分辨工质中所有的同分异构体。通过遗传算法优化得到网络结构及初始参数后，由神经网络对工质临界温度进行预测，同时为了提高网络对临界温度预测的泛化能力，将200种工质划分成训练集、验证集及测试集。所得网络能够区分所有的同分异构体，且与实验值相比，各数据集临界温度的平均相对误差分别为1.18%、1.69%、1.28%，表明该网络对工质临界温度具有很好的预测能力。

关键词: 热力学性质, 临界温度, 工质, 分子基团, 拓扑指数, 遗传算法, 神经网络

Abstract:

A genetic neural network was presented to predict the critical temperature of refrigerants. The inputs of the network included molecular groups and a topological index, and the output was the critical temperature. 16 molecular groups divided can cover most of the refrigerants or working fluids in refrigeration, heat pump and Organic Rankine Cycle research. The chosen topological index was able to distinguish all refrigerant isomers. The critical temperatures of refrigerants were estimated by the neural network after obtaining the optimized network structure and initial parameters by genetic algorithm. At the same time, in order to improve network generalization ability of prediction, 200 data points were divided into three data sets including the training, validation, and test sets. The calculated results based on the developed network showed a good agreement with experimental data. The network can distinguish all refrigerant isomers and compared with the experimental data. The average absolute relative deviations for training, validation and test sets were 1.18%, 1.69% and 1.28%, respectively.

Key words: thermodynamics property, critical temperature, refrigerant, molecular groups, topological index, genetic algorithm, neural network

中图分类号:

TK123

苏文, 赵力, 邓帅. 基于基团拓扑的遗传神经网络工质临界温度预测[J]. 化工学报, 2016, 67(11): 4689-4695.

SU Wen, ZHAO Li, DENG Shuai. Prediction of refrigerant critical temperature with genetic neural network based on group topology[J]. CIESC Journal, 2016, 67(11): 4689-4695.

参考文献 30

[1]	侯虞钧. 化学工程手册[M]. 北京:化学工业出版社, 1986. HOU Y J. Chemical Engineering Handbook[M]. Beijing:Chemical Industry Press, 1986.
[2]	CALM J, HOURAHAN G. Physical, safety and environmental data for current and alternative refrigerants[C]//Proceedings of 23rd International Congress of Refrigeration (ICR2011). Prague, Czech Republic, 2011.
[3]	SAMUDRA A, SAHINIDIS N. Design of secondary refrigerants.A combined optimization enumeration approach[C]//Proceedings of AIChE Annual Meeting, Philadelphia, 2009.
[4]	POLING B.E, PRAUSNITZ J M, CONNELL J P. The Properties of Gases and Liquids[M]. 5th ed. New York:McGraw-Hill, 2004.
[5]	王小艳, 司继林, 张达, 等. 纯物质临界参数估算方法的研究进展[J]. 化工进展, 2012, 31(9):1871-1877. WANG X Y, SI J L, ZHANG D, et al. Research progress of estimation methods for critical parameters of pure substances[J]. Chem. Ind. Eng. Prog., 2012, 31(9):1871-1877.
[6]	夏力, 李忠杰, 项曙光. 估算有机物正常沸点的元素和化学键贡献法[J]. 化工进展, 2007, 26(1):138-144. XIA L, LI Z J, XIANG S G. A new method based on elements and chemical bonds for estimating normal boiling point of organic compounds[J]. Chem. Ind. Eng. Prog., 2007, 26(1):138-144.
[7]	周永昌, 赵锁奇, 许志明, 等. 预测复杂高沸点重质油馏分平均沸点的基团贡献法[J]. 化工学报, 2004, 55(8):1224-1229. ZHOU Y C, ZHAO S Q, XU Z M, et al. New group contribution method for estimating average boiling point of heavy oil fractions[J]. Journal of Chemical Industry and Engineering(China), 2004, 55(8):1224-1229.
[8]	陈福明. 基团溶解度参数及有机物汽化热的估算[J]. 化工学报, 1991, 42(3):328-333. CHEN F M. Estimation of the group solubility parameter and the latent heat for organic compounds[J]. Journal of Chemical Industry and Engineering(China), 1991, 42(3):328-333.
[9]	JOBACK K G, REID R C. Estimation of pure-component properties from group-contributions[J]. Chemical Engineering Communications, 1987, 57(1-6):233-243.
[10]	CONSTANTINOU L, GANI R. New group contribution method for estimating properties of pure compounds[J]. AIChE Journal, 1994, 40(10):1697-1709.
[11]	MARRERO J, PARDILLO E. Estimation of pure compound properties using group-interaction contributions[J]. AIChE Journal, 1999, 45(3):615-621.
[12]	许文. 估算有机物基础物性的三基团参数关联式[J]. 化工学报, 1992, 43(2):222-229. XU W. Estimation of three group parameters for correlating basic physical properties of organic compounds[J]. Journal of Chemical Industry and Engineering(China), 1992, 43(2):222-229.
[13]	马沛生, 王加宁, 李平. 基团法估算临界参数的改进[J]. 高校化学工程学报, 1996, 10(4):15-18. MA P S, WANG J N, LI P. Improvement of group contribution method for estimation of critical parameters[J]. Journal of Chemical Engineering of Chinese Universities, 1996, 10(4):15-18.
[14]	WANG Q, MA P, JIA Q, et al. Position group contribution method for the prediction of critical temperatures of organic compounds[J]. Journal of Chemical & Engineering Data, 2008, 53(5):1103-1109.
[15]	许禄, 胡昌玉. 化学中的人工神经网络法[J]. 化学进展, 2000, 17(1):18-31. XU L, HU C Y. Artificial neural networks in chemistry[J]. Progress in Chemistry, 2000, 17(1):18-31.
[16]	张维涛, 于雁武. 基团贡献人工神经网络集成法估算有机物物性研究进展[J].中国胶粘剂, 2015, 24(4):46-48. ZHANG W T, YU Y W. Research progress of group contribution method integrated with artificial neural network for estimating the properties of organic compounds[J]. China Adhesives, 2015, 24(4):46-48.
[17]	彭黔荣, 杨敏, 石炎福, 等. 基于混合遗传算法的人工神经网络模型及其对有机化合物熔点的预测[J]. 化工学报, 2005, 56(10):1922-1927. PENG Q R, YANG M, SHI Y F, et al. Artificial neural network based on hybrid genetic algorithm and prediction of melting points of organic compounds[J]. Journal of Chemical Industry and Engineering(China), 2005, 56(10):1922-1927.
[18]	张向东, 赵立群, 张国义. 人工神经网络法预测有机物基础物[J]. 化工学报, 1995, 46(1):66-74. ZHANG X D, ZHAO L Q, ZHANG G Y. An artificial neural network for predicting the basic physical properties of organic compounds[J]. Journal of Chemical Industry and Engineering(China), 1995, 46(1):66-74.
[19]	旷戈, 赵素英, 赵之山, 等. 人工神经网络基团贡献法估算纯有机物的临界参数[J]. 计算机与应用化学, 2001, 18(4):396-9. KUANG G, ZHAO S Y, ZHAO Z S, et al. Prediction of critical properties for organic compound by group-contribution artificial neural network method[J]. Computers and Applied Chemistry, 2001, 18(4):396-399.
[20]	刘春艳, 凌建春, 寇林元, 等. GA-BP神经网络与BP神经网络性能比较[J]. 中国卫生统计, 2013, 30(2):173-6. LIU C Y, LING J C, KOU L Y, et al. Performance comparison between GA-BP neural network and BP neural network[J]. Chinese Journal of Health Statistics, 2013, 30(2):173-176.
[21]	MIDGLEY T, HENNEAL, MCNARY R R. Heat transfer and refrigeration:US 2104882[P]. 1938-01-11.
[22]	李素芳, 陈腊生. 分子设计的发展与应用[J]. 化学世界, 2005, 46(9):574-575. LI S F, CHEN L S. Development and application of molecular design[J]. Chemical World, 2005, 46(9):574-575.
[23]	KHETIB Y, LARKECHE O, MENIAI A, et al. Group contribution concept for computer-aided design of working fluids for refrigeration machines[J]. Chemical Engineering & Technology, 2013, 36(11):1924-1934.
[24]	GUO M, XU L, HU C Y, et al. Study on structure-activity relationship of organic compounds-applications of a new highly discriminating topological index[J]. Match, 1997, 14(35):185-197.
[25]	许禄, 胡昌玉, 许志宏. 应用化学图论[M]. 北京:科学出版社, 2000. XU L, HU C Y, XU Z H. Apply Chemistry Graph Theory[M]. Beijing:Science Press, 2000.
[26]	NIELSEN R. Theory of the back propagation neural network[J]. Neural Networks, 1988, 1(1):65-93.
[27]	HOLAND J H. Adaptation in Natural and Artificial Systems[M]. Ann Arbor:The University of Michigan Press, 1975.
[28]	孙娓娓. BP神经网络的算法改进及应用研究[D]. 重庆:重庆大学, 2009. SUN W W. Study on improved algorithm and application of BP neural network[D]. Chongqing:Chongqing University, 2009.
[29]	赵寿玲. BP神经网络结构优化方法的研究及应用[D]. 苏州:苏州大学, 2010. ZHAO S L. Researches and application on the structure optimization of the BP neural networks[D]. Suzhou:Soochow University, 2010.
[30]	MOOSAVI M, SEDGHAMIZ E, ABARESHI M. Liquid density prediction of five different classes of refrigerant systems (HCFCs, HFCs, HFEs, PFAs and PFAAs) using the artificial neural network-group contribution method[J]. International Journal of Refrigeration, 2014, 48:188-200.