Application of DoE evaluation to introduce the optimum injection strategy-chamber geometry of diesel engine using surrogate epsilon-SVR

Abstract With the advance of computational fluid dynamic methods for simulation of diesel engines, the requirement is felt to find the optimal operational design by scanning through various design points. In this sense, a design of experiment technique was applied to a baseline 1.8 L Ford diesel engine by defining a multi-objective function that is consisted of sub-objectives of NO x emission and spray droplet diameter. The success of the optimization procedure is contingent upon reduction of emission and enhancement of the spraying characteristics. It is determined that the effect of adjustment in injection strategy is more important than that of the engine modification. A slight reduction of inner bowl diameter and bowl radius should be concomitant with decrement of spray cone angle and injection angle with respect to the baseline engine. The best design configuration is achieved at Run ID 22 (R4/Di/injection angle/spray cone angle = 5.77 mm/43.7 mm/121.9 deg/4.11 deg). DoE method using Sobol sequence is used incorporating with the support vector regression to predict output parameters with acceptable accuracy in this research project.

[1]  Bernhard Schölkopf,et al.  Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond , 2005, IEEE Transactions on Neural Networks.

[2]  Dimitrios T. Hountalas,et al.  Experimental investigation concerning the effect of natural gas percentage on performance and emissions of a DI dual fuel diesel engine , 2003 .

[3]  R. Reitz,et al.  An experimental study on the effects of oxygenated fuel blends and multiple injection strategies on DI diesel engine emissions , 1999 .

[4]  H. Taghavifar,et al.  Diesel engine spray characteristics prediction with hybridized artificial neural network optimized by genetic algorithm , 2014 .

[5]  Shahaboddin Shamshirband,et al.  Support vector regression methodology for wind turbine reaction torque prediction with power-split hydrostatic continuous variable transmission , 2014 .

[6]  Hamid Taghavifar,et al.  Exhaust emissions prognostication for DI diesel group-hole injectors using a supervised artificial neural network approach , 2014 .

[7]  Zuohua Huang,et al.  Experimental investigation on regulated and unregulated emissions of a diesel engine fueled with ultra-low sulfur diesel fuel blended with biodiesel from waste cooking oil. , 2009, The Science of the total environment.

[8]  Shahaboddin Shamshirband,et al.  RETRACTED ARTICLE: Support vector regression methodology for prediction of input displacement of adaptive compliant robotic gripper , 2014, Applied Intelligence.

[9]  J G Hawley,et al.  An experimental study of the application of variable-geometry turbocharging and high-pressure common rail to an automotive diesel engine , 2001 .

[10]  Yue Chen,et al.  The multi-objective optimization of combustion chamber of DI diesel engine by NLPQL algorithm , 2014 .

[11]  Shahaboddin Shamshirband,et al.  Support vector machine firefly algorithm based optimization of lens system. , 2015, Applied optics.

[12]  Bai-Fu Lin,et al.  Experimental study of the effects of vegetable oil methyl ester on DI diesel engine performance characteristics and pollutant emissions , 2009 .

[13]  Hamid Taghavifar,et al.  Appraisal of artificial neural networks to the emission analysis and prediction of CO2, soot, and NOx of n-heptane fueled engine , 2016 .

[14]  Hamid Taghavifar,et al.  Modeling the impact of in-cylinder combustion parameters of DI engines on soot and NOx emissions at rated EGR levels using ANN approach , 2014 .

[15]  Rolf D. Reitz,et al.  Modeling the Effect of Engine Speed on the Combustion Process and Emissions in a DI Diesel Engine , 1996 .

[16]  Shigeru Obayashi,et al.  Optimization of Combustion Chamber for Diesel Engine Using Kriging Model , 2006 .

[17]  Samad Jafarmadar,et al.  Adaptive neuro-fuzzy system (ANFIS) based appraisal of accumulated heat from hydrogen-fueled engine , 2015 .

[18]  Anthony Paul Roskilly,et al.  An analytic study of applying Miller cycle to reduce NOx emission from petrol engine , 2007 .

[19]  Sibendu Som,et al.  Effect of nozzle orifice geometry on spray, combustion, and emission characteristics under diesel engine conditions , 2011 .

[20]  Shahaboddin Shamshirband,et al.  Sensor Data Fusion by Support Vector Regression Methodology—A Comparative Study , 2015, IEEE Sensors Journal.

[21]  Shahaboddin Shamshirband,et al.  Evaluation of modulation transfer function of optical lens system by support vector regression methodologies A comparative study , 2014 .

[22]  Samad Jafarmadar,et al.  Numerical energetic and exergetic analysis of CI diesel engine performance for different fuels of hydrogen, dimethyl ether, and diesel under various engine speeds , 2014 .

[23]  R. Reitz,et al.  MODELING SPRAY ATOMIZATION WITH THE KELVIN-HELMHOLTZ/RAYLEIGH-TAYLOR HYBRID MODEL , 1999 .

[24]  Raouf Mobasheri,et al.  Analysis the effect of advanced injection strategies on engine performance and pollutant emissions in a heavy duty DI-diesel engine by CFD modeling , 2012 .

[25]  J. Dukowicz.  A particle-fluid numerical model for liquid sprays , 1980 .

[26]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[27]  S. Gunn.  Support Vector Machines for Classification and Regression , 1998 .