Combining artificial neural network and multi-objective optimization to reduce a heavy-duty diesel engine emissions and fuel consumption

Abstract

Nondominated sorting genetic algorithm II (NSGA-II) is well known for engine optimization problem. Artificial neural networks (ANNs) followed by multi-objective optimization including a NSGA-II and strength pareto evolutionary algorithm (SPEA2) were used to optimize the operating parameters of a compression ignition (CI) heavy-duty diesel engine. First, a multi-layer perception (MLP) network was used for the ANN modeling and the back propagation algorithm was utilized as training algorithm. Then, two different multi-objective evolutionary algorithms were implemented to determine the optimal engine parameters. The objective of the present study is to decide which algorithm is preferable in terms of performance in engine emission and fuel consumption optimization problem.

Keywords

engine / fuel consumption / emissions / neural networks / multi objective optimization

References

[1] DecJ E. Advanced compression-ignition engines—Understanding the in-cylinder processes [J]. Proceedings of the Combustion Institute, 2009, 32: 2727-2742

[2] StoneRIntroduction to internal combustion engines [M], 20124London, UKSAE International and Macmillan Press45-76

[3] PaykaniA, KhoshbakhtiS R, Shervani-TabarM T, Mohammadi-KoushaA. Effect of exhaust gas recirculation and intake pre-heating on performance and emission characteristics of dual fuel engines at part loads [J]. Journal of Central South University, 2012, 19(5): 1346-1352

[4] ShiY, GeH W, ReitzR DComputational optimization of internal combustion engines [M], 2011BerlinSpringer-Verlag London Limited9-36

[5] FausettL VFundamentals of neural network [M], 1993Upper Saddle River, NJ, USAPrentice Hall66-101

[6] HeY, RutlandC J. Application of artificial neural networks in engine modeling [J]. International Journal of Engine Research, 2004, 5(4): 281-296

[7] DesantesJ M, BenajesJ V, MolinaS A, HernÁNdezL. Multi-objective optimization of heavy-duty diesel engines under stationary conditions [J]. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, 2005, 219(1): 77-87

[8] ParlakA, IslamogluY, YasarH, EgrisogutA. Application of artificial neural network to predict specific fuel consumption and exhaust temperature for a diesel engine [J]. Applied Thermal Engineering, 2006, 26(8/9): 824-828

[9] HashemiN, ClarkN N. Artificial neural network as a predictive tool for emissions from heavy-duty diesel vehicles in southern California [J]. International Journal of Engine Research, 2007, 8: 321-336

[10] NajafiG, GhobadianB, TavakoliT, ButtsworthD R, YusafT F, FaizollahnejadM. Performance and exhaust emissions of a gasoline engine with ethanol blended gasoline fuels using artificial neural network [J]. Applied Energy, 2009, 86: 630-639

[11] YusafT F, ButtsworthD R, SalehK H, YousifB F. CNG-diesel engine performance and exhaust emission analysis with the aid of artificial neural network [J]. Applied Energy, 2010, 87: 1661-1669

[12] ShivakumarP, SrinivasaP B R, ShrinivasaR. Artificial neural network based prediction of performance and emission characteristics of a variable compression ratio CI engine using WCO as a biodiesel at different injection timings [J]. Applied Energy, 2011, 88: 2344-2354

[13] AydoganH, AltunA A, OzcelikA E. Performance analysis of a turbocharged diesel engine using biodiesel with back propagation artificial neural network [J]. Energy Education Science and Technology Part A: Energy Science and Research, 2011, 28(1): 459-468

[14] IsmailH M, NgH K, QueckC H W, GanS. Artificial neural networks modelling of engine-out responses for a light-duty diesel engine fuelled with biodiesel blends [J]. Applied Energy, 2012, 92: 769-777

[15] AlonsoJ M, AlvarruizF, DesantesJ M, HernÁNdezL, HernÁNdezV, MoltÓG. Combining neural networks and genetic algorithms to predict and reduce diesel engine emissions [J]. IEEE Transactions on Evolutionary Computation, 2007, 11(1): 46-55

[16] Martinez-MoralesJ D, Palacios-HernÁNdezE R, VelÁZquez-CarrilloG A. Modeling and multi-objective optimization of a gasoline engine using neural networks and evolutionary algorithms [J]. Journal of Zhejiang University-Science A (Applied Physics & Engineering), 2013, 14(9): 657-670

[17] ShiY, ReitzR D. Assessment of optimization methodologies to study the effects of bowl geometry, spray targeting and swirl ratio for a heavy-duty diesel engine operated at high-load [J]. SAE Technical Paper, 2008

[18] CoelloC A, PulidoG TA micro-genetic algorithm for multiobjective optimization [C]// First International Conference on Evolutionary Multi-Criterion Optimization, Lecture Notes in Computer Science, 2001, 1993: 126-140

[19] DebK, PratapA, AgarwalS, MeyarivanT. A fast and elitist multiobjective genetic algorithm: NSGA-II [J]. IEEE Transactions on Evolutionary Computation, 2002, 6(2): 182-197

[20] SasakiD, ObayashiS. Efficient search for trade-offs by adaptive range multi-objective genetic algorithms [J]. Journal of Aerospace Computing, Information, and Communication, 2005, 2(1): 44-64

[21] GeH W, ShiYU, ReitzR D, WickmanD D, ZhuG, ZhangH, KalishY. Heavy-duty diesel combustion optimization using multi-objective genetic algorithm and multi-dimensional modeling [J]. SAE Technical Papers, 2009

[22] GeH W, ShiYU, ReitzR D, WickmanD D, WillemsW. Optimization of a HSDI diesel engine for passenger cars using a multi-objective genetic algorithm and multi-dimensional modeling [J]. SAE International Journal of Engines, 2009, 2(1): 691-713

[23] ShiY, ReitzR D. Optimization of a heavy-duty compression–ignition engine fueled with diesel and gasoline-like fuels [J]. Fuel, 2010, 89: 3416-3430

[24] ShiY, ReitzR D. Assessment of multiobjective genetic algorithms with different niching strategies and regression methods for engine optimization and design [J]. Journal of Engineering for Gas Turbines and Power, 2010, 132(5): 052801

[25] BrahmaI, RutlandC J. Optimization of diesel engine operating parameters using neural networks [J]. SAE Technical Paper, 2003

[26] HowardD, MarkB, MartinH. Neural network toolbox 6, User’s Guide [M]. MathWorks, Inc, 20065-85

[27] CoelloC A, LamontG B, van VeldhuizenA AEvolutionary algorithms for solving multi-objective problems [M], 2007BerlinSpringer201-265

[28] CortÉSO, UrquizaG, HernÁNdezJ A. Optimization of operating conditions for compressor performance by means of neural network inverse [J]. Applied Energy, 2009, 86: 2487-2493

[29] ZitzlerE, ThieleL. Multi objective evolutionary algorithms: A comparative case study and the strength pareto approach [J]. IEEE Transactions on Evolutionary Computation, 1999, 3(4): 257-271

[30] ZitzlerMLAUMANNSSPEA2: Improving the strength pareto evolutionary algorithm, Computer Engineering and Networks Laboratory (TIK) [R], 2001SwitzerlandSwiss Federal Institute of Technology (ETH) Zurich

[31] HiroyasuT, NakayamaS, MikiMComparison study of SPEA2+, SPEA2, and NSGA-II in diesel engine emissions and fuel economy problem [C]// 2005 IEEE^Congress on Evolutionary Computation, 2005236-242

[32] SrinivasN, DebK. Multiobjective optimization using nondominated sorting in genetic algorithms [J]. Evolutionary Computation, 1994, 2(3): 221-248

[33] ZitzlerE, DebK, ThieleL. Comparison of multiobjective evolutionary algorithms: Empirical results [J]. Evolutionary Computation, 2000, 8(2): 173-195

[34] LakshminarayanaP A, AghavY VModelling diesel combustion [M], 2010BerlinSpringer5-32

[35] Martinez-MoralesJ D, Palacios-HernÁNdezE R, VelÁZquez-CarrilloG A, JosÉD. Artificial neural network based on genetic algorithm for emissions prediction of a SI gasoline engine [J]. Journal of Mechanical Science and Technology, 2014, 28(6): 2417-2427