基于人工神经网络的放热规律的量化预测

doi:10.13229/j.cnki.jdxbgxb20170854

摘要/Abstract

摘要：

利用AVL-Fire建立了高压共轨柴油机燃烧系统仿真模型,通过台架试验验证仿真模型的基础上,分析了混合气浓度场和温度场动态分布特性并将燃烧过程划分为预混合和扩散燃烧分界点,提出燃烧始点、预混合燃烧速率、扩散燃烧速率及燃烧持续期等量化评价参数。建立了预测量化评价参数的人工神经网络(ANN)模型,预测分析发动机控制参数对放热规律评价参数的影响。研究结果表明:当采用“5-18-4”型神经网络结构模型并采用trainlm算法时,预测的鲁棒性、响应性和收敛精度均良好,所创建的ANN模型可以很好地预测放热规律。

关键词: 动力机械及工程, 人工神经网络, 控制参数, 放热规律, 量化评价参数, 量化预测

Abstract:

A combustion simulation model is built with AVL-Fire, and the dynamic distribution characteristics of the mixture concentration field and temperature field are analyzed by verification of the simulation results on test bench. The start point of combustion, premixed rate, diffusion rate and combustion duration are taken as the evaluation parameters. The effect of the control parameters on Heat Release Rate (HRR) at different stage is analyzed. An Artificial Neural Network (ANN) model is established for quantitative prediction of the evaluation parameters. The structure and of the ANN algorithm is confirmed. The effects of the injection parameters and intake parameters on the evaluation parameters are analyzed and predicted. The results show that, when the structure 5-18-4 ANN with trainlm algorithm are adopted, the robustness, responsiveness and convergence precision are good, indicating the ANN model is a powerful tool to predict HRR.

Key words: power machinery and engineering, artificial neural network(ANN), control parameter, heat release rate (HRR), quantitative evaluation parameter, quantitative prediction

中图分类号:

TK421

江涛,林学东,李德刚,杨淼,汤雪林. 基于人工神经网络的放热规律的量化预测[J]. 吉林大学学报(工学版), 2018, 48(6): 1747-1754.

JIANG Tao,LIN Xue-dong,LI De-gang,YANG Miao,TANG Xue-lin. Effect of control parameters on heat release rate with ANN method[J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(6): 1747-1754.

图/表 18

表1

表2

表3

图1

表4

图2

图3

图4

表5

表6

表7

表8

表9

图5

图6

图7

图8

图9

参考文献 15

[1]	Heywood J B . Internal Combustion Engine Funda-Mentals[M]. New York: McGraw-Hill, 1988.
[2]	Kim J, Jang J, Lee K , et al. Combustion and emissions characteristics of diesel and soybean biodiesel over wide ranges of intake pressure and oxygen concentration in a compression-ignition engine at a light-load condition[J]. Fuel, 2014,129:11-19. doi: 10.1016/j.fuel.2014.03.022
[3]	Li Xin-ling, Xu Zhen, Guan Chun , et al. Impact of exhaust gas recirculation (EGR) on soot reactivity from a diesel engine operating at high load[J]. Applied Thermal Engineering, 2014,68(1/2):100-106. doi: 10.1016/j.applthermaleng.2014.04.029
[4]	Wang Ying, Li Dong-chang, Lei Xiong , et al. Combustion and emission characteristics of a DME (dimethyl ether)-diesel dual fuel premixed charge compression ignition engine with EGR (exhaust gas recirculation)[J]. Energy, 2014,72(7):608-617. doi: 10.1016/j.energy.2014.05.086
[5]	Asad U, Zheng M . Fast heat release characterization of a diesel engine[J]. International Journal of Thermal Sciences, 2008,47(12):1688-1700. doi: 10.1016/j.ijthermalsci.2008.01.009
[6]	Taghavifar H, Mardani A, Mohebbi A , et al. Exhaust emissions prognostication for DI diesel group-hole injectors using a supervised artificial neural network approach[J]. Fuel, 2014,125:81-89. doi: 10.1016/j.fuel.2014.02.016
[7]	Taghavifar H, Mardani A, Mohebbi A , et al. Investigating the effect of combustion properties on the accumulated heat release of DI engines at rated EGR levels using the ANN approach[J]. Fuel, 2014,137:1-10. doi: 10.1016/j.fuel.2014.07.073
[8]	Rezaei J, Shahbakhti M, Bahri B , et al. Performance prediction of HCCI engines with oxygenated fuels using artificial neural networks[J]. Applied Energy, 2015,138:460-473. doi: 10.1016/j.apenergy.2014.10.088
[9]	Taghavifar H, Mardani A, Mohebbi A , et al. On the modeling of convective heat transfer coefficient of hydrogen fueled diesel engine as affected by combustion parameters using a coupled numerical-artificial neural network approach[J]. International Journal of Hydrogen Energy, 2015,40(12):4370-4381. doi: 10.1016/j.ijhydene.2015.01.140
[10]	Muralidharan K, Vasudevan D . Applications of artificial neural networks in prediction of performance, emission and combustion characteristics of variable compression ratio engine fuelled with waste cooking oil biodiesel[J]. J Braz Soc Mech Sci Eng, 2014,7(3):1-14. doi: 10.1007/s40430-014-0213-4
[11]	Mohammadhassani J, Dadvand A, Khalilarya S , et al. Prediction and reduction of diesel engine emissions using a combined ANN-ACO method[J]. Applied Soft Computing, 2015,34:139-150. doi: 10.1016/j.asoc.2015.04.059
[12]	Chen J, Randall R B . Improved automated diagnosis of misfire in internal combustion engines based on simulation models[J]. Mechanical Systems & Signal Processing, 2015,64- 65:58-83. doi: 10.1016/j.ymssp.2015.02.027
[13]	Dukowicz J K . Quasi-steady droplet change in the presence of convection[R]. Informal Report Los Alamos Scientific Laboratory, LA7997-MS, 1979.
[14]	Patankar S V. Numerical Heat and Mass Transfer and Fluid Flow[M]. New York: Hemisphere Publishing Corporation, 1980.
[15]	van der Vorst H A. Bi-CGSTAB: a fast and smoothly converging variant of Bi-CG for the solution of nonsymmetric linear systems[J]. SIAM J Sci Stat Comput, 1992,13:631-644. doi: 10.1137/0913035

相关文章 15

[1]	孙正, 黄钰期, 俞小莉. 径向滑动轴承润滑油膜流动-传热过程仿真[J]. 吉林大学学报(工学版), 2018, 48(3): 744-751.
[2]	刘忠长, 孙士杰, 田径, 徐瑞辰, 汪泊舟. 瞬态工况下喷油参数对柴油机排放及燃烧特性的影响[J]. 吉林大学学报(工学版), 2014, 44(6): 1639-1646.
[3]	包堂堂, 胡宗杰, 胡俊超, 阮逸平, 邓俊, 吴志军. 基于超声雾化的柴油/汽油混合燃料液滴群燃烧特性[J]. 吉林大学学报(工学版), 2013, 43(04): 903-908.
[4]	于秀敏,谭兴闻,马君,李国良,董伟,齐万强,崔峰云. 缸内直喷汽油机起动控制[J]. 吉林大学学报(工学版), 2011, 41(6): 1554-1558.
[5]	贾志新, 张宏斌, 郗安民. 利用神经网络扩充数控机床可靠性数据[J]. 吉林大学学报(工学版), 2011, 41(02): 403-0407.
[6]	高印寒, 孙强, 丛玉良, 池俊成, 唐荣江. 基于神经网络的非稳态噪声品质的评价方法[J]. 吉林大学学报(工学版), 2010, 40(增刊): 110-0114.
[7]	刘成材,高青,马纯强,金英爱,李玥. 发动机可变组分进气系统的膜气体分离特性[J]. 吉林大学学报(工学版), 2010, 40(03): 625-0629.
[8]	殷涌光,丁筠. 基于计算机视觉的食品中大肠杆菌快速定量检测[J]. 吉林大学学报(工学版), 2009, 39(增刊2): 344-0348.
[9]	周立军, 王殿海, 李卫青. 人工神经网络及粒子群优化算法在跟驰模型中的应用[J]. 吉林大学学报(工学版), 2009, 39(04): 896-899.
[10]	刘发发，谷艳华，彭亚平，李华，郭英男 . 乙醇均质压燃燃烧的化学反应动力学模拟[J]. 吉林大学学报(工学版), 2009, 39(01): 21-26.
[11]	李鸿雁，刘宪亮，鲍新华 . 学习率有限监督调整方法[J]. 吉林大学学报(工学版), 2007, 37(04): 846-850.
[12]	杨忠振，崔丛 . 基于神经网络的道路交通污染物浓度预测[J]. 吉林大学学报(工学版), 2007, 37(03): 705-0708.
[13]	董恩增，陈增强，袁著祉 . 基于神经网络PID控制器的混沌系统控制与同步[J]. 吉林大学学报(工学版), 2007, 37(03): 646-0650.
[14]	程平，张海涛，高岩，李俊锋，王洪艳 . ANN在聚丙烯酸酯乳液性质预测中的应用 [J]. 吉林大学学报(工学版), 2007, 37(02): 362-0366.
[15]	王庆年，金启前，初亮，王伟华. 传动系参数和控制参数对并联混合动力轿车性能的影响[J]. 吉林大学学报(工学版), 2005, 35(03): 243-248.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

参数	变化范围
喷射压力/MPa	120, 140,160
喷射时刻/°CA	-7,-9,-11
喷射比例/mg	0:40,2:38,4:36
VNT开度/%	30,40,50
EGR率/%	20,30,40

项目	单位	技术参数
缸数	缸	4
缸径	mm	83
冲程	mm	92
压缩比	-	17.3
排量	L	1.991
标定功率/转速	kW/(r·min^-1)	100/3600
最大转矩/转速	N·m/(r·min^-1)	310/2200~2800
共轨系统	-	BOSCH二代共轨系统
喷油器	-	Bosch CR 12
喷孔数×喷孔直径	孔数×mm	7×0.131

仪器设备	型号
电涡流测功机	CW260
油耗仪	FCMM-2
气缸压力传感器	Kistler6056A31U20
电荷放大器	Kistler5018A0001
燃烧分析仪	DS9100

项目	数值
头部温度/K	420
活塞温度/K	473
缸内温度/K	420
初始压力/MPa	0.1
初始温度/K	330
TKE/( m²?s^-2)	70.78
TLS/m	0.00307
初次破碎模型	DDM
二次破碎模型	KH-RT
液滴扩散模型	Hug-Gosman
碰壁模型	walljet1
蒸发模型	Dukowicz
燃烧模型	ECFM-3Z

参数	喷射压力/MPa
参数	120	140	160
燃烧始点/°CA	0.3	0.3	0.3
预混合燃烧速率/[J·(°CA)^-1]	2.83	3.19	4.28
扩散燃烧速率/[J·(°CA)^-1]	3.19	1.91	1.48
燃烧持续期/°CA	35.75	31.07	25.07