化工学报 ›› 2020, Vol. 71 ›› Issue (7): 3191-3200.doi: 10.11949/0438-1157.20191453

• 过程系统工程 • 上一篇    下一篇

基于SHPSO-GA-BP的成品汽油调和中加氢汽油组分辛烷值的预测

李炜1,2,3(),王晓明1,2,3(),蒋栋年1,2,3,李亚洁1,2,3,梁成龙4   

  1. 1.兰州理工大学电气工程与信息工程学院,甘肃 兰州 730050
    2.甘肃省工业过程先进控制重点实验室,甘肃 兰州 730050
    3.兰州理工大学电气与控制工程国家级实验教学示范中心,甘肃 兰州 730050
    4.中国石化兰州石化分公司油品储运厂,甘肃 兰州 730060
  • 收稿日期:2019-11-30 修回日期:2020-02-29 出版日期:2020-07-05 发布日期:2020-05-09
  • 通讯作者: 王晓明 E-mail:liwei@lut.cn;wangxiaoming19951@163.com
  • 作者简介:李炜(1963—),女,博导,教授,liwei@lut.cn
  • 基金资助:
    国家自然科学基金项目(61763027)

Prediction of octane number of finished gasoline blend based on SHPSO-GA-BP

Wei LI1,2,3(),Xiaoming WANG1,2,3(),Dongnian JIANG1,2,3,Yajie LI1,2,3,Chenglong LIANG4   

  1. 1.College of Electrical and Information Engineering, Lanzhou University of Technology, Lanzhou 730050, Gansu, China
    2.Key Laboratory of Gansu Advanced Control for Industrial Processes, Lanzhou 730050, Gansu, China
    3.National Demonstration Center for Experimental Electrical and Control Engineering Education, Lanzhou University of Technology, Lanzhou 730050, Gansu, China
    4.Oil Storage and Transportation Plant, Petrochina Lanzhou Petrochemical Company, Lanzhou 730060, Gansu, China
  • Received:2019-11-30 Revised:2020-02-29 Online:2020-07-05 Published:2020-05-09
  • Contact: Xiaoming WANG E-mail:liwei@lut.cn;wangxiaoming19951@163.com

摘要:

针对成品汽油调和配方建模中加氢汽油组分辛烷值难以实时获取,考虑遗传算法(genetic algorithm,GA)、粒子群算法(particle swarm optimization,PSO)优化反向传播(back propagation,BP)网络存在的问题,提出了一种串行混合粒子群遗传算法(serial hybrid PSO-GA,SHPSO-GA)优化BP网络,并用于辛烷值的预测建模。该方法首先将PSO算法的输出依据适应度值分为优劣2个种群,弃劣留优;然后对留优种群再进行GA的交叉变异操作,进一步优化种群,经过每一代PSO和GA的交替优化,并将最优种群用于BP网络参数优化;最后基于该方法和工业历史数据,建立了加氢汽油组分辛烷值的预测模型,仿真结果表明,较传统BP,以及改进的GA-BP、PSO-BP、PSO-GA-BP等方法,SHPSO-GA-BP由于将PSO与GA进行更优的深度融合,具有更好的预测性能,可以用于辛烷值的预测。

关键词: 辛烷值, 预测, 神经网络, 遗传算法, 粒子群算法, SHPSO-GA-BP神经网络, 优化

Abstract:

In the production of finished gasoline,octane number as the key indicators of quality of finished product gasoline and foundation of formula model,it is import to accurate measuring its content. However, due to the existing measurement technology and the constraints of complex conditions, it is difficult to obtain the component data effectively. Considering the problems of genetic algorithm (GA), particle swarm optimization (PSO), and optimizing back propagation (BP) network, a serial hybrid particle swarm genetic algorithm (serial hybrid PSO-GA, SHPSO-GA) is proposed to optimize the BP network, and it is used to predict and model the octane number. In this method, the output of PSO algorithm is divided into two populations according to the fitness value, and the bad ones are discarded and the good ones are retained. Then the optimized population was further optimized by GA crossover and mutation, the optimal population was applied to BP network parameter optimization. Finally, based on the method and the industrial historical data, a prediction model of octane number of hydrogenated gasoline was established. The simulation results showed that, compared with the traditional BP, GA-BP, PSO-BP, PSO-GA-BP and other methods, SHPSO-GA-BP had better prediction performance due to the deeper integration of PSO and GA, it could be used for octane number prediction.

Key words: octane number, prediction, neural network, genetic algorithm, particle swarm optimization, PSO-GA-BP neural network, optimization

中图分类号: 

  • TP 273

图1

SHPSO-GA-BP算法基本流程"

图2

四种网络适应度曲线(终止代数=50)"

图3

几种方法预测结果"

表1

几种方法性能比较"

方法MSESAD训练时间/s

PED

δ=0.05)

PED

δ=0.15)

BP0.028914.892010.0914.95%67.29%
GA-BP0.025213.6423644.3631.78%69.16%
PSO-BP0.023912.2688630.2533.64%67.29%
PSO-GA-BP0.019411.3015415.2630.84%76.64%
SHPSO-GA-BP0.018610.8781380.1135.51%78.50%
1 仇爱波, 周如金, 邱松山, 等. 汽油组分及汽油辛烷值预测方法研究进展[J]. 天然气化工(C1化学与化工), 2014, 39(2): 62-66.
Qiu A B, Zhou R J, Qiu S S, et al. Review of octane number prediction methods for gasoline components and gasoline[J]. Natural Gas Chemical Industry (C1 Chemistry and Chemical Industry), 2014, 39(2): 62-66.
2 Perdih A, Perdih F. Chemical interpretation of octane number[J]. Acta Chimica Slovenica, 2006, 53(3): 306-315.
3 Nikolaou N, Papadopoulos C E, Gaglias I A, et al. A new non-linear calculation method of isomerisation gasoline research octane number based on gas chromatographic data[J]. Fuel, 2004, 83(4): 517-523.
4 王宁, 温浩, 许志宏, 等. 一种用拓扑指数和基团组成预测烷烃辛烷值的方法[J]. 石油学报(石油加工), 1998, (3): 70-76.
Wang N, Wen H, Xu Z H, et al. A new prediction method for antiknock of alkanes with topological indices and group composition[J]. Acta Petrolei Sinica (Petroleum Processing Section), 1998, (3): 70-76.
5 Albahri T A. Structural group contribution method for predicting the octane number of pure hydrocarbon liquids[J]. Industrial & Engineering Chemistry Research, 2003, 42(3): 657-662.
6 Al-Fahemi J H, Albis N A, Gad E A M. QSPR models for octane number prediction[J]. Journal of Theoretical Chemistry, 2014, 2014: 1-6.
7 Jeong H I, Lee H, Jeon J H, et al. Determination of research octane number using NIR spectral data and ridge regression[J]. Bulletin of The Korean Chemical Society, 2001, 22(1): 37-42.
8 Kardamakis A A, Pasadakis N. Autoregressive modeling of near-IR spectra and MLR to predict RON values of gasolines[J]. Fuel, 2010, 89(1): 158-161.
9 Kelly J J, Barlow C H, Jinguji T M, et al. Prediction of gasoline octane numbers from near-infrared spectral features in the range 660-1215 nm[J]. Analytical Chemistry, 1989, 61(4): 313-320.
10 Alghouti M A, Aldegs Y S, Amer M W, et al. Determination of motor gasoline adulteration using FTIR spectroscopy and multivariate calibration[J]. Talanta, 2008, 76(5): 1105-1112.
11 Mendes G, Aleme H G, Barbeira P J, et al. Determination of octane numbers in gasoline by distillation curves and partial least squares regression[J]. Fuel, 2012, 97: 131-136.
12 王拓, 戴连奎, 马万武. 拉曼光谱结合后向间隔偏最小二乘法用于调和汽油辛烷值定量分析[J]. 分析化学, 2018, 46(4): 623-629.
Wang T, Dai L K, Ma W W. Quantitative analysis of blended gasoline octane number using raman spectroscopy with backward interval partial least squares method[J]. Chinese Journal of Analytical Chemistry, 2018, 46(4): 623-629.
13 蒋书波, 林锦国, 程明霄, 等. 基于拉曼技术的汽油辛烷值测定系统设计[J]. 化工学报, 2011, 62(8): 2188-2194.
Jiang S B, Lin J G, Cheng M X, et al. System design of gasoline octane number detection based on Raman technology[J]. CIESC Journal, 2011, 62(8): 2188-2194.
14 Murty B S N, Rao R N. Global optimization for prediction of blend composition of gasolines of desired octane number and properties[J]. Fuel Processing Technology, 2004, 85(14): 1595-1602.
15 Pasadakis N, Gaganis V, Foteinopoulos C, et al. Octane number prediction for gasoline blends[J]. Fuel Processing Technology, 2006, 87(6): 505-509.
16 Abduljameel A G, van Oudenhoven V, Emwas A, et al. Predicting octane number using nuclear magnetic resonance spectroscopy and artificial neural networks[J]. Energy & Fuels, 2018, 32(5): 6309-6329.
17 钟英竹. 汽油调合优化神经网络模型的研究[J]. 石油炼制与化工, 2013, 44(5): 71-75.
Zhong Y Z. Study on neural network model for gasoline blending optimization[J]. Petroleum Processing and Petrochemicals, 2013, 44(5): 71-75.
18 Zhou X W, Yuan J, Yang B L. Prediction of octane number for clean gasoline obtained from secondary reactions based on back-propagation neural network[J]. Journal of Xian Jiaotong University, 2010, 44(12): 82-86.
19 Wang W, Li Z, Zhang Q, et al. On-line optimization model design of gasoline blending system under parametric uncertainty[J]. Control & Automation, 2007, 24(7): 1-5.
20 韩仲志,万剑华,刘康炜.基于近红外光谱的汽油辛烷值预测与模型优化[J].分析试验室, 2015, 34(11): 1268-1271.
Han Z Z, Wan J H, Liu K W. Model optimization in prediction of gas octane value by NIR[J]. Chinese Journal of Analysis Laboratory, 2015, 34(11): 1268-1271.
21 Ding S F, Xu L, Su C Y, et al. Using genetic algorithms to optimize artificial neural networks[J]. Journal of Convergence Information Technology, 2010, 5(8): 54-62.
22 Ling Y, Chai C, Hou W, et al. A new method for nuclear accident source term inversion based on GA-BPNN algorithm[J]. Neural Network World, 2019, 29(2): 71-82.
23 Outanoute M, Lachhab A, Selmani A, et al. Particle swarm optimization of BP-ANN based soft sensor for greenhouse climate[J]. Journal of Electronic Commerce in Organizations, 2018, 16(1): 72-81.
24 Mohsen A, Mahyar K A, Ebrahimi W M. An accurate PSO-GA based neural network to model growth of carbon nanotubes[J]. Journal of Nanomaterials, 2017, 2017: 1-6.
25 Semero Y K, Zhang J, Zheng D, et al. A GA-PSO hybrid algorithm based neural network modeling technique for short-term wind power forecasting[J]. Distributed Generation & Alternative Energy Journal, 2018, 33(4): 26-43.
26 Esmin A A A, Lambert-Torres G, Alvarenga G B. Hybrid evolutionary algorithm based on PSO and GA mutation[C]// 6th International Conference on Hybrid Itelligent Systems, and 4th Conference on Neuro-Computing and Evolving Intelligence (HIS-NCEI 2006); Rio de Janeiro, Brazil. 2006: 231-234.
27 Du S, Li W, Cao K, et al. A learning algorithm of artificial neural network based on GA - PSO[C]// 2006 6th World Congress on Intelligent Control and Automation, Dalian, 2006: 3633-3637.
28 Bhattacharjee K, Pant M. Hybrid particle swarm optimization-genetic algorithm trained multi-layer perceptron for classification of human glioma from molecular brain neoplasia data[J]. Cognitive Systems Research, 2019, 58: 173-194.
29 Li G, Zhao F, Guo C, et al. Parallel hybrid PSO-GA algorithm and its application to layout design[C]//International Conference on Natural Computation, 2006: 749-758.
30 Robinson J T, Sinton S, Rahmatsamii Y, et al. swarm Particle, algorithm genetic, and their hybrids: optimization of a profiled corrugated horn antenna[C]// IEEE Antennas and Propagation Society International Symposium (IEEE Cat. No.02CH37313), San Antonio, TX, USA, 2002: 314-317.
31 Utkarsh A, Kantha A S, Praveen J, et al. Hybrid GA-PSO trained functional link artificial neural network based channel equalizer[C]// International Conference on Signal Processing & Integrated Networks. IEEE, 2015: 285-290.
32 Garg H. A hybrid PSO-GA algorithm for constrained optimization problems[J]. Applied Mathematics and Computation, 2016, 274: 292-305.
33 Anand A, Suganthi L. Hybrid GA-PSO optimization of artificial neural network for forecasting electricity demand[J]. Energies, 2018, 11(4): 728-755.
34 Yang X M, Yuan J Y, Mao H N, et al. A modified particle swarm optimizer with dynamic adaptation[J]. Applied Mathematics and Computation, 2007, 189(2): 1205-1213.
35 Ratnaweera A, Halgamuge S K, Watson H C, et al. Self-organizing hierarchical particle swarm optimizer with time-varying acceleration coefficients[J]. IEEE Transactions on Evolutionary Computation, 2004, 8(3): 240-255.
36 高浩, 冷文浩, 须文波. 一种全局收敛PSO算法及其收敛分析[J]. 控制与决策, 2009, 24(2): 196-201.
Gao H, Len W H, Xu W B. A global convergence algorithm of particle swarm optimization and its convergence analysis[J]. Control and Decision, 2009, 24(2): 196-201.
[1] 张行, 庞丽萍, 王莹. 某型运输机飞行状态下冷凝器风道性能[J]. 化工学报, 2020, 71(S1): 166-171.
[2] 汪宁, 张学军, 赵阳, 甘智华, 张春伟, 余萌. 基于斯特林制冷机的文物恒湿展柜设计及实验研究[J]. 化工学报, 2020, 71(S1): 179-186.
[3] 毛海涛, 王璐, 许志颖, 解万翠, 都健, 张磊. 基于分子表面电荷密度分布与机器学习的混合物设计方法研究[J]. 化工学报, 2020, 71(S1): 282-292.
[4] 方黄峰, 刘瑶瑶, 张文彪. 基于LSTM神经网络的流化床干燥器内生物质颗粒湿度预测[J]. 化工学报, 2020, 71(S1): 307-314.
[5] 张庭玮, 李斌, 翟晓强. 基于理论的传热结构拓扑优化[J]. 化工学报, 2020, 71(S1): 31-37.
[6] 阿嵘, 庞丽萍, 杨东升, 齐玢. 高速飞行器机载综合热管理系统设计与优化[J]. 化工学报, 2020, 71(S1): 315-321.
[7] 徐刚, 庞丽萍. 特种车辆舱室送风系统布局仿真优化[J]. 化工学报, 2020, 71(S1): 335-340.
[8] 周月, 张鹤林, 程定斌, 尹俊成. 典型空气循环制冷系统仿真研究[J]. 化工学报, 2020, 71(S1): 341-345.
[9] 刘秀峰, 张诗, 周志杰, 郑浩, 王成泽, 时红远, 李梦杰. 换热器结构优化与换热性能评价指标研究[J]. 化工学报, 2020, 71(S1): 98-105.
[10] 邓睿渠,汪林正,张睿智,罗永浩. 基于粒子群算法的生活垃圾高热值成分热解动力学特性研究[J]. 化工学报, 2020, 71(7): 3238-3246.
[11] 周红标,张钰,柏小颖,刘保连,赵环宇. 基于自适应模糊神经网络的非线性系统模型预测控制[J]. 化工学报, 2020, 71(7): 3201-3212.
[12] 高学金, 刘腾飞, 徐子东, 高慧慧, 于涌川. 基于循环自动编码器的间歇过程故障监测[J]. 化工学报, 2020, 71(7): 3172-3179.
[13] 陈威,于梅红,赵红霞. 优化控制R744多喷射器双温超市制冷系统[J]. 化工学报, 2020, 71(7): 3266-3277.
[14] 霍二福, 李迎春, 杨帅, 冯明, 程伟琴, 王柏楠, 魏新军. 环己醇精馏残液催化加氢分离二环己基醚工艺研究[J]. 化工学报, 2020, 71(7): 3132-3139.
[15] 黄桂冬, 张凇源, 葛众, 解志勇, 相华江, 鄢银连, 袁志鹏. 基于内置换热器有机闪蒸循环的热性能研究[J]. 化工学报, 2020, 71(7): 3080-3090.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 赵迎宪, 危凤, 虞影. Inhibition of Coke Formation in Cracking of 2-Methylpentane on USHY by Addition of Steam[J]. CIESC Journal, 2008, 16(5): 726 -732 .
[2] 谢鹏程, 李锋祥, 丁玉梅, 阎华, 关昌峰, 杨卫民. Experimental Study of Heat Transfer Enhancement and Friction Loss Induced by Inserted Rotor-assembled Strand(I) Water[J]. CIESC Journal, 2008, 16(6): 849 -855 .
[3] 范文元, 马友光, 李小磊, 李怀志. Study on the Flow Field around Two Parallel Moving Bubbles and Interaction Between Bubbles Rising in CMC Solutions by PIV[J]. CIESC Journal, 2009, 17(6): 904 -913 .
[4] 周红艺;徐新华;汪大翚.

Pd/Fe双金属对水中m-二氯苯的催化脱氯

[J]. CIESC Journal, 2004, 55(11): 1912 -1915 .
[5] 陆乃宸,李光福,陆云质,赵绪检. 丙烯与乙苯氢化过氧化物环氧化反应的动力学 [J]. CIESC Journal, 1980, 31(4): 365 -374 .
[6] 刘伟伟;卢春喜;范怡平;施晓萌;徐春明.

气固流化床中双组分混合颗粒的流态化特性

[J]. CIESC Journal, 2008, 59(8): 1971 -1978 .
[7] 徐振林,汪绍昆,田维民,时钧. 色谱斜率法测过量自由焓模型参数 [J]. CIESC Journal, 1985, 36(2): 141 -150 .
[8] 佘远斌, 罗振华, 宋旭锋, 段立丽, 恽悦, 张天慧. 金属卟啉仿生催化氧化邻硝基甲苯绿色合成邻硝基苯甲醛 [J]. 化工学报, 2007, 58(11): 2782 -2786 .
[9] 左恒;王贻明;张杰. 电场强化铜矿排土场氧气传质 [J]. CIESC Journal, 2007, 58(12): 3001 -3005 .
[10] 王绍亭,陈树章,徐平. 充液填料塔液相轴向混合的研究 [J]. CIESC Journal, 1985, 36(4): 475 -484 .