Development of a neural network model for selective catalytic reduction (SCR) catalytic converter and ammonia dosing optimization using multi objective genetic algorithm

In this paper, a mathematical model of the SCR catalytic converter is replaced with the neural network model to accelerate the optimization process. The Euro steady state calibration test data set is used to simulate the inlet properties of the SCR catalytic converter. For each chosen condition, a separate neural network is developed. In order to generate sufficient data to form a neural network for each condition, the original mathematical model was run several times at the temperature and inlet NOx concentration of each condition with a range of different ammonia concentrations. Subsequently, using MATLAB ® software, the neural network model is trained and tested for each condition. Ammonia dosing optimization is performed using multi objective genetic algorithm module of MATLAB

[1]  Martin Elsener,et al.  Recent Advances in the Development of Urea-SCR for Automotive Applications , 2001 .

[2]  Paul Spurk,et al.  Modeling of SCR DeNOx Catalyst - Looking at the Impact of Substrate Attributes , 2003 .

[3]  Teuvo Maunula,et al.  NOx reduction by urea in the presence of NO2 on metal substrated SCR catalysts for heavy-duty vehicles , 2003 .

[4]  J. N. Chi,et al.  Modeling and Control of a Urea-SCR Aftertreatment System , 2005 .

[5]  Grégoire Allaire,et al.  Numerical analysis and optimization : an introduction to mathematical modelling and numerical simulation , 2007 .

[6]  Tomoyuki Hiroyasu,et al.  Multi-Objective Optimization of Diesel Engine Emissions and Fuel Economy using Genetic Algorithms and Phenomenological Model , 2002 .

[7]  Grégoire Allaire,et al.  Numerical analysis and optimization , 2007 .

[8]  Pio Forzatti,et al.  Present status and perspectives in de-NOx SCR catalysis , 2001 .

[9]  In-Sik Nam,et al.  Direct Use of Kinetic Parameters for Modeling and Simulation of a Selective Catalytic Reduction Process , 2000 .

[10]  Paul Greening.  European Vehicle Emission Legislation—Present and Future , 2001 .

[11]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[12]  Guy Richard Chandler,et al.  Investigations into NOx Aftertreatment with Urea SCR for Light-Duty Diesel Vehicles , 2001 .

[13]  DebK.,et al.  A fast and elitist multiobjective genetic algorithm , 2002 .

[14]  George Zhu,et al.  Model-based Closed-loop Control of Urea SCR Exhaust Aftertreatment System for Diesel Engine , 2002 .

[15]  Lothar Thiele,et al.  Multiobjective evolutionary algorithms: a comparative case study and the strength Pareto approach , 1999, IEEE Trans. Evol. Comput..

[16]  William E. Schiesser,et al.  A Compendium of Partial Differential Equation Models: Method of Lines Analysis with Matlab , 2009 .

[17]  Christine Kay Lambert,et al.  Laboratory Studies and Mathematical Modeling of Urea SCR Catalyst Performance , 2007 .

[18]  Tomoyuki Hiroyasu,et al.  Reduction of Heavy Duty Diesel Engine Emission and Fuel Economy with Multi-Objective Genetic Algorithm and Phenomenological Model , 2004 .

[19]  David W. Coit,et al.  Multi-objective optimization using genetic algorithms: A tutorial , 2006, Reliab. Eng. Syst. Saf..