On the application of artificial neural networks for the prediction of NOxemissions from a high-speed direct injection diesel engine

被引:27
作者
Fang, XiaoHang [1 ]
Papaioannou, Nick [1 ]
Leach, Felix [1 ]
Davy, Martin H. [1 ]
机构
[1] Univ Oxford, Dept Engn Sci, Oxford OX1 3PJ, England
基金
英国工程与自然科学研究理事会;
关键词
Deep learning; artificial neural networks; internal combustion engines; diesel; NOx; EXHAUST EMISSIONS; DESIGN; PERFORMANCE;
D O I
10.1177/1468087420929768
中图分类号
O414.1 [热力学];
学科分类号
摘要
This article considers the application and refinement of artificial neural network methods for the prediction of NO(x)emissions from a high-speed direct injection diesel engine over a wide range of engine operating conditions. The relative computational cost and performance of two backpropagation algorithms, Levenberg-Marquardt and Bayesian regularization, for this application are compared, with the Levenberg-Marquardt algorithm demonstrating a significant cost advantage. This work also assesses the performance of two alternative filtering approaches, ap-value test and the Pearson correlation coefficient, for reducing the required number of input variables to the model. Thep-value test identified 32 input parameters of significance, whereas the Pearson correlation test highlighted 14 significant parameters while additionally providing a ranking of their relative importance. Finally, the article compares the predictive performance of the models generated by the two filtering methods. Overall, both models show good agreement to the experimental data with the model created using the Pearson correlation test showing improved performance in the low-NO(x)region.
引用
收藏
页码:1808 / 1824
页数:17
相关论文
共 50 条
[41]   Application of artificial neural networks for operating speed prediction at horizontal curves: A case study in Egypt [J].
Semeida A.M. .
Journal of Modern Transportation, 2014, 22 (1) :20-29
[42]   Application of artificial neural networks for operating speed prediction at horizontal curves: a case study in Egypt [J].
Ahmed Mohamed Semeida .
Journal of Modern Transportation, 2014, (01) :20-29
[43]   Prediction of torque and specific fuel consumption of a gasoline engine by using artificial neural networks [J].
Togun, Necla Kara ;
Baysec, Sedat .
APPLIED ENERGY, 2010, 87 (01) :349-355
[44]   A Study on Static Features of a High-speed Solenoid Valve Used in Diesel Engine [J].
Chen, Na ;
Wang, Yansong ;
Guo, Hui ;
Lei, Jie ;
Zhang, Tao .
FRONTIER IN INFORMATION ENGINEERING FOR MECHANICS AND MATERIALS, 2012, 189 :393-397
[45]   Performance Prediction of Application Mapping in Manycore Systems with Artificial Neural Networks [J].
Gamatie, Abdoulaye ;
Ursu, Roman ;
Selva, Manuel ;
Sassatelli, Gilles .
2016 IEEE 10TH INTERNATIONAL SYMPOSIUM ON EMBEDDED MULTICORE/MANY-CORE SYSTEMS-ON-CHIP (MCSOC), 2016, :185-192
[46]   Artificial neural networks modelling of engine-out responses for a light-duty diesel engine fuelled with biodiesel blends [J].
Ismail, Harun Mohamed ;
Ng, Hoon Kiat ;
Queck, Cheen Wei ;
Gan, Suyin .
APPLIED ENERGY, 2012, 92 :769-777
[47]   Application of Artificial Neural Networks for Prediction of Photocatalytic Reactor [J].
Delnavaz, Mohammad .
WATER ENVIRONMENT RESEARCH, 2015, 87 (02) :113-122
[48]   Influence of properties of various common bio-fuels on the combustion and emission characteristics of high-speed DI (direct injection) diesel engine: Vegetable oil, bio-diesel, ethanol, n-butanol, diethyl ether [J].
Rakopoulos, Dimitrios C. ;
Rakopoulos, Constantine D. ;
Giakoumis, Evangelos G. ;
Papagiannakis, Roussos G. ;
Kyritsis, Dimitrios C. .
ENERGY, 2014, 73 :354-366
[49]   Thermodynamics analysis of a turbojet engine integrated with a fuel cell and steam injection for high-speed flight [J].
Ji, Zhixing ;
Qin, Jiang ;
Cheng, Kunlin ;
Guo, Fafu ;
Zhang, Silong ;
Dong, Peng .
ENERGY, 2019, 185 :190-201
[50]   Artificial neural networks modeling of combustion parameters for a diesel engine fueled with biodiesel fuel [J].
Can, Ozer ;
Baklacioglu, Tolga ;
Ozturk, Erkan ;
Turan, Onder .
ENERGY, 2022, 247