Reduction in the nitrogen oxide and soot emissions in a diesel engine combustion system using an approximate optimization method

Abstract

The present study explores how to optimize a common-rail diesel engine to minimize nitrogen oxide and soot emissions with constraints on hydrocarbon and carbon monoxide emissions. A numerical diesel engine combustion and emission analysis is conducted using the zero-dimensional model. The simulation data are approximated, which accommodates the combustion characteristics of common-rail diesel engines and exhaust. The back-propagation neural network is used not only as a global function approximation tool for predicting non-linear characteristics but also for a global sensitivity analysis to examine causality between the input variables and the output responses. Given an engine operating condition, constrained bi-objective Pareto-optimal solutions are identified by the non-dominated sorting genetic algorithm II. Optimal designs to minimize the nitrogen oxide and soot emissions subject to the hydrocarbon and carbon monoxide emissions requirements are identified. By comparing the number of Pareto solutions with a baseline design, a reduction in both nitrogen oxide emissions and soot emissions is achieved and these back-propagation-neural-network-based approximate designs are verified using the actual zero-dimensional model data.

Keywords

Diesel engine combustion system nitrogen oxide and soot emissions zero-dimensional model back-propagation neural network approximate optimization non-dominated sorting genetic algorithm II

Get full access to this article

View all access options for this article.

References

Traver

Atkinson

. Neural network-based diesel engine emissions prediction using in-cylinder combustion pressure. SAE paper 1999-01-1532, 1999.

Gurupatham

. Architecture design and analysis of diesel engine exhaust aftertreatment system and comparative study with close-coupled DOC–DPF system. SAE paper 2008-01-1756, 2008.

Gamo

Ouladsine

Rachid

. Diesel engine exhaust emissions modeling using artificial neural networks. SAE paper 1999-01-1163, 1999.

Krijnsen

H C

Kooten

WEJ

Calis

HPA

. Prediction of NO_x emissions from a transiently operating diesel engine using an artificial neural network. Chem Engng Technol 1999; 22(7): 601–607.

Rutland

. Application of artificial neural networks in engine modeling. Int J Engine Res 2004; 5(4): 281–296.

Jarrett

Clark

. Weighting of parameters in artificial neural network prediction of heavy-duty diesel engine emissions. SAE paper 2002-01-2878, 2002.

Brahma

Rutland

Foster

. A new approach to system level soot modeling. SAE paper 2005-01-1122, 2005.

Brahma

Rutland

. Improvement of neural network accuracy for engine simulations. SAE paper 2003-01-3227, 2003.

Traver

Atkinson

. Neural network based diesel engine emissions prediction using in-cylinder combustion pressure. SAE paper 1999-01-1532, 1999.

10.

Janakiraman

Rao

Ampath

. Prediction of CI engine emissions from combustion chamber pressure characteristics. SAE paper 2007-01-1121, 2007.

11.

Desantes

López

García

Hernández

. Application of neural networks for prediction and optimization of exhaust emissions in a HD diesel engine. SAE paper 2002-01-1144, 2002.

12.

Brahma

Rutland

. Optimization of diesel engine operating parameters using neural networks. SAE paper 2003-01-3228, 2003.

13.

Hiroyasu

Miki

Kim

. Reduction of heavy duty diesel engine emission and fuel economy with multi-objective genetic algorithm and phenomenological model. SAE paper 2004-01-0531, 2004.

14.

Kiani

Ghobadian

. Application of artificial neural networks for the prediction of performance and exhaust emissions in SI engine using ethanol–gasoline blends. Energy 2010; 35(1): 65–69.

15.

Alonso

Alvarruiz

Desantes

. Combining neural networks and genetic algorithms to predict and reduce diesel engine emissions. IEEE Trans Evolutionary Comput 2007; 11(1): 46–55.

16.

D’Errico

Cerri

Pertusi

. Multi-objective optimization of internal combustion engine by means of 1D fluid-dynamic models. Appl Energy 2011; 88(3): 767–777.

17.

Guerrassi

Dupraz

. A common rail injection system for high speed direct injection diesel engines. SAE paper 980803, 1998.

18.

Bosch Group. http://www.bosch.com.

19.

Kwon

Seo

Lee

Huh

. Zero-dimensional simulation of diesel engine combustion and emissions based on CMC model and skeletal reaction mechanism. SAE paper 2011-01-0845, 2011.

20.

Liu

Hewson

Chen

Pitsch

. Effects of strain rate on high-pressure nonpremixed n-heptane auto ignition in counter flow. Combust Flame 2004; 137(3): 320–339.

21.

Lee

Jeong

Choi

. An enhancement of constraint feasibility in BPN based approximate optimization. Comput Meth Appl Mech Engng 2007; 196(17) : 2147–2160.

22.

Lee

Jeong

Kang

. Derivative and GA based methods in meta-modeling of back-propagation neural networks for constrained approximate optimization. Struct Multidisciplinary Optimization 2008; 35(1): 29–40.

23.

Kim

Lee

. System decomposition techniques in multidisciplinary design optimization problems using genetic algorithms and neural networks. J Comput Struct Engng Inst Korea 1999; 12: 619–627.

24.

Lee

Shin

. Parameter design of water jet nozzle utilizing independence axiom. Proc IMechE Part E: J Process Mechanical Engineering 2008; 222(3): 157–169.

25.

Deb

Pratap

Agarwal

Meyarivan

. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans Evolutionary Comput 2002; 6(2): 182–197.

26.

Deb

Gupta

. Searching for robust Pareto-optimal solutions in multi-objective optimization. In: 3rd international conference on evolutionary multicriterion optimization, Guanojuato, Mexico, 9–11 March 2005, Lecture Notes in Computer Science, vol. 3410, pp.150–164. Berlin: Springer.