Support vector machine to predict diesel engine performance and emission parameters fueled with nano-particles additive to diesel fuel

This paper studies the use of adaptive Support Vector Machine (SVM) to predict the performance parameters and exhaust emissions of a diesel engine operating on nanodiesel blended fuels. In order to predict the engine parameters, the whole experimental data were randomly divided into training and testing data. For SVM modelling, different values for radial basis function (RBF) kernel width and penalty parameters (C) were considered and the optimum values were then found. The results demonstrate that SVM is capable of predicting the diesel engine performance and emissions. In the experimental step, Carbon nano tubes (CNT) (40, 80 and 120 ppm) and nano silver particles (40, 80 and 120 ppm) with nanostructure were prepared and added as additive to the diesel fuel. Six cylinders, four-stroke diesel engine was fuelled with these new blended fuels and operated at different engine speeds. Experimental test results indicated the fact that adding nano particles to diesel fuel, increased diesel engine power and torque output. For nano-diesel it was found that the brake specific fuel consumption (bsfc) was decreased compared to the net diesel fuel. The results proved that with increase of nano particles concentrations (from 40 ppm to 120 ppm) in diesel fuel, CO2 emission increased. CO emission in diesel fuel with nano-particles was lower significantly compared to pure diesel fuel. UHC emission with silver nano-diesel blended fuel decreased while with fuels that contains CNT nano particles increased. The trend of NOx emission was inverse compared to the UHC emission. With adding nano particles to the blended fuels, NOx increased compared to the net diesel fuel. The tests revealed that silver & CNT nano particles can be used as additive in diesel fuel to improve complete combustion of the fuel and reduce the exhaust emissions significantly.

[1]  Shijin Shuai,et al.  The effect of ethanol blended diesel fuels on emissions from a diesel engine , 2003 .

[2]  Qin Zhang,et al.  Ethanol-diesel fuel blends -- a review. , 2005, Bioresource technology.

[3]  Pak Kin Wong,et al.  Modeling and optimization of biodiesel engine performance using kernel-based extreme learning machine and cuckoo search , 2015 .

[4]  M. Sugeno,et al.  Structure identification of fuzzy model , 1988 .

[5]  G. Vaitilingom,et al.  Interest of combining an additive with diesel–ethanol blends for use in diesel engines , 2001 .

[6]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[7]  K. Karuppasamy,et al.  Biodiesel production and prediction of engine performance using SIMULINK model of trained neural network , 2012 .

[8]  Richard Van Basshuysen,et al.  Gasoline Engine with Direct Injection: Processes, Systems, Development, Potential , 2009 .

[9]  H. Zhen,et al.  Effect of cetane number improver on heat release rate and emissions of high speed diesel engine fueled with ethanol–diesel blend fuel , 2004 .

[10]  Murat Hosoz,et al.  ANFIS modelling of the performance and emissions of a diesel engine using diesel fuel and biodiesel blends , 2013 .

[11]  Yusuf Çay,et al.  Prediction of a gasoline engine performance with artificial neural network , 2013 .

[12]  Moh'd Abu-Qudais,et al.  The effect of alcohol fumigation on diesel engine performance and emissions , 2000 .

[13]  Galen J. Suppes,et al.  Miscibility of ethanol in diesel fuels , 2001 .

[14]  Avram Hershko,et al.  Past, Present, and Future Perspectives , 1998 .

[15]  S. W. Lee,et al.  Emission reduction potential from the combustion of soy methyl ester fuel blended with petroleum distillate fuel , 2004 .

[16]  Gholamhassan Najafi,et al.  Performance and exhaust emissions of a gasoline engine with ethanol blended gasoline fuels using artificial neural network , 2009 .

[17]  A. Kondo,et al.  Biodiesel fuel production by transesterification of oils. , 2001, Journal of bioscience and bioengineering.

[18]  Özer Can,et al.  Effects of ethanol addition on performance and emissions of a turbocharged indirect injection Diesel engine running at different injection pressures , 2004 .

[19]  Bo-Suk Yang,et al.  Machine health prognostics using survival probability and support vector machine , 2011, Expert Syst. Appl..

[20]  R. Brereton,et al.  Support vector machines for classification and regression. , 2010, The Analyst.

[21]  E. A. Ajav,et al.  Performance of a stationary diesel engine using vapourized ethanol as supplementary fuel , 1998 .

[22]  Bo-Suk Yang,et al.  Support vector machine in machine condition monitoring and fault diagnosis , 2007 .

[23]  Lakhmi C. Jain,et al.  ANFISunfoldedintime for multivariate time series forecasting , 2004, Neurocomputing.

[24]  Mustafa Canakci,et al.  Performance and exhaust emissions of a gasoline engine using artificial neural network , 2007 .

[25]  Noboru Noguchi,et al.  Performance improvement by control of flow rates and diesel injection timing on dual-fuel engine with ethanol , 1996 .

[26]  Adem Çiçek,et al.  Prediction of engine performance and exhaust emissions for gasoline and methanol using artificial neural network , 2013 .

[27]  M. Jayabharata Reddy,et al.  A Wavelet-neuro-fuzzy Combined Approach for Digital Relaying of Transmission Line Faults , 2007 .

[28]  E. A. Ajav,et al.  Thermal balance of a single cylinder diesel engine operating on alternative fuels , 2000 .

[29]  J V Tu,et al.  Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. , 1996, Journal of clinical epidemiology.

[30]  Deli Li,et al.  Physico-chemical properties of ethanol–diesel blend fuel and its effect on performance and emissions of diesel engines , 2005 .