Research on FT fuel engine characteristics using neural network

WU Tao; ZHANG Wugao; PENG Haiyong; ZHANG Haibo; MIAO Xuelong

doi:10.12299/jsues.22-0140

Volume 37 Issue 1

Mar. 2023

Turn off MathJax

Article Contents

Article Navigation > Journal of Shanghai University of Engineering Science > 2023 > 37(1): 68-75

WU Tao, ZHANG Wugao, PENG Haiyong, ZHANG Haibo, MIAO Xuelong. Research on FT fuel engine characteristics using neural network[J]. Journal of Shanghai University of Engineering Science, 2023, 37(1): 68-75. doi: 10.12299/jsues.22-0140

Citation:

WU Tao, ZHANG Wugao, PENG Haiyong, ZHANG Haibo, MIAO Xuelong. Research on FT fuel engine characteristics using neural network[J]. Journal of Shanghai University of Engineering Science, 2023, 37(1): 68-75. doi: 10.12299/jsues.22-0140

Citation:

PDF( 1117 KB)

Research on FT fuel engine characteristics using neural network

doi: 10.12299/jsues.22-0140

1.
School of Mechanical and Automotive Engineering, Shanghai University of Engineering Science, Shanghai 201620, China
2.
Key Laboratory for Power Machinery and Engineering of Ministry of Education, Shanghai Jiao Tong University, Shanghai 200240, China

Received Date: 2022-05-09
Publish Date: 2023-03-31

Abstract

Abstract

Based on the strong nonlinear approximation and self-learning ability of Back Propagation (BP) neural network, a three-layer network model was designed, and the engine bench test data were collected as the samples to train and verify the model. The engine speed, torque, fuel supply advance angle and the characteristic parameters of the fuel mixture of Fischer-Tropsch gas-to-liquid (GTL) and diesel, such as cetane number, sulfur content and aromatic hydrocarbon content, were taken as inputs. The BP neural network model was established to predict the characteristics of GTL engine. The results show that the model can predict the power, fuel consumption, exhaust temperature, HC, CO, CO₂, NO_x and soot emission of GTL engine at the same time. Compared with the experimental data, the relative error of the prediction results is nearly within 5%, which shows that the model has high model accuracy and good generalization ability.
- back propagation (BP) neural network,
- Fischer-Tropsch fuel,
- engine,
- emission,
- model

FullText(HTML)

References(15)

References

[1]	夏勇, 商斌梁, 张振仁, 等. 神经网络在内燃机故障诊断中的应用研究[J] . 机械科学与技术,2000,19:108 − 110. doi: 10.3321/j.issn:1003-8728.2000.01.040
[2]	侯志祥, 吴义虎, 邓华, 等. 车用汽油机过渡工况空燃比的神经网络控制研究[J] . 内燃机工程,2006,27(5):33 − 36. doi: 10.3969/j.issn.1000-0925.2006.05.008
[3]	杨继红, 张宗杰, 方昌良. 柴油机运行工况的神经网络分析[J] . 柴油机设计与制造,2000(3):21 − 24.
[4]	高洪滨, 欧阳光耀, 张萍. 基于BP神经网络的柴油机气缸压力重构[J] . 内燃机工程,2005,26(1):68 − 70. doi: 10.3969/j.issn.1000-0925.2005.01.017
[5]	张向军, 桂长林. 内燃机摩擦学智能设计中人工神经网络的应用[J] . 机械科学与技术,2001,20(3):459 − 460. doi: 10.3321/j.issn:1003-8728.2001.03.058
[6]	侯国祥, 徐凯, 朱梅林, 等. 应用神经网络-蒙特卡罗法的可靠性分析方法[J] . 华中科技大学学报(自然科学版),2002,30(4):84 − 86. doi: 10.13245/j.hust.2002.04.029
[7]	BALAWENDER K, USTRZYCKI A, LEJDA K, et al. Modeling of unburned hydrocarbon emission in a DI diesel engine using neural networks [C]//Proceedings of SAE Powertrains, Fuels & Lubricants Meeting. Krakow: Society of Automotive Engineers, 2020.
[8]	ARCAKLIOGLU E, CELIKTEN I. A diesel engine's performance and exhaust emissions[J] . Applied Energy,2005,80(1):11 − 22. doi: 10.1016/j.apenergy.2004.03.004
[9]	SAYIN C, ERTUNC H M, HOSOZ M, et al. Performance and exhaust emissions of a gasoline engine using artificial neural network[J] . Applied Thermal Engineering,2007,27(1):46 − 54. doi: 10.1016/j.applthermaleng.2006.05.016
[10]	CANAKCI M, ERDIL A, ARCAKLIOGLU E. Performance and exhaust emissions of a biodiesel engine[J] . Applied Energy,2006,83(6):594 − 605. doi: 10.1016/j.apenergy.2005.05.003
[11]	李捷辉, 周大伟, 段畅. BP神经网络在双燃料发动机排放预测中的应用[J] . 机械设计与制造,2018(3):127 − 130. doi: 10.3969/j.issn.1001-3997.2018.03.038
[12]	孙俊, 高孝洪. BP网络在双燃料发动机排放预测中的应用研究[J] . 武汉理工大学学报(交通科学与工程版),2003,27(3):350 − 353.
[13]	VOSLOO A C. Fischer-Tropsch: A futuristic view[J] . Fuel Processing Technology,2001,71(1-3):149 − 155. doi: 10.1016/S0378-3820(01)00143-6
[14]	张德丰. MATLAB神经网络应用设计[M]. 2版. 北京: 机械工业出版社, 2011: 79.
[15]	WU T, HUANG Z, ZHANG W, et al. Physical and chemical properties of GTL-diesel fuel blends and their effects on performance and emissions of a multi-cylinder di compression ignition engine[J] . Energy and Fuels,2007,21(4):1908 − 1914. doi: 10.1021/ef0606512