Performance and Emission Prediction in a Biodiesel Engine Fuelled with Honge Methyl Ester Using RBF Neural Networks

In the present study, RBF neural networks were used for predicting the performance and emission parameters of a biodiesel engine. Engine experiments were carried out in a 4 stroke diesel engine using blends of diesel and Honge methyl ester as the fuel. Performance parameters like BTE, BSEC, Tex and emissions from the engine were measured. These experimental results were used for ANN modeling. RBF center initialization was done by random selection and by using Clustered techniques. Network was trained by using fixed and varying widths for the RBF units. It was observed that RBF results were having a good agreement with the experimental results. Networks trained by using clustering technique gave better results than using random selection of centers in terms of reduced MRE and increased prediction accuracy. The average MRE for the performance parameters was 3.25% with the prediction accuracy of 98% and for emissions it was 10.4% with a prediction accuracy of 80%.

Authors:

• Shivakumar
• G. S. Vijay
• P. Srinivas Pai
• B. R. Shrinivasa Rao

Keywords:

• Radial Basis Function networks
• emissions
• Performance parameters
• Fuzzy c means.

References:

[1] A. K. Hossain & P. A. Davies, “Plant oils as fuels for CI engines- A
technical review and life cycle analysis”, Renewable Energy, Vol 35,
2010, pp. 1-13.
[2] A. K. Babu and G. Devaradjane, “Vegetable oils and their derivatives as
fuels for CI engines”, SAE paper, 2003-01- 0767, pp.406-418.
[3] A. K Agarwal & L. M. Das, “Biodiesel development and
characterization for use as a fuel in CI engines”, ASME Journal of
Engineering for Gas Turbines and Power, Vol 123, 2001, pp. 440- 447.
[4] Narayan Reddy & A. Ramesh, “Parametric studies for improving the
performance of a jathropa oil fuelled compression ignition engine”,
Renewable Energy, Vol 31, 2006, pp.-1194-2016.
[5] Baiju, M. K Naik & L. M. Das, “A comparative evaluation of
compression ignition characteristics using methyl and ethyl esters of
karanja oil”, Renewable Energy, Vol 34, 2009, pp.1616-1621.
[6] Heywood, J. Internal Combustion Engine fundamentals, McGraw Hill,
Inc. New York, 1988.
[7] Cenk Sayin, H. Metin Ertunc & Mustafa Canakci, “Performance and
exhaust emissions from a gasoline engine using ANN”, Applied Thermal
Engineering, Vol 27, 2007, pp. 46-54. [8] Mustafa Canakci, Ahmet Erdil & Erol Arcakliglu, “Performance and
exhaust emissions of a biodiesel engine”, Applied Energy, Vol 83, 2006,
pp.594-604.
[9] Gholamhassn Najafi, Barat Ghobadian & Talal Y. Yusafand Hadi
Rahim, “Combustion analysis of a CI engine performance using waste
cooking oil with artificial neural network”, American Journal of Applied
Science, Vol 4, No 10, 2007, pp. 756- 764.
[10] Erol Arcaklioglu & E. Celikten, “A diesel engine performance and
exhaust emissions using ANN”, Applied Energy, Vol 80, 2005, pp. 11-
22.
[11] Jose M. D Esantes, Jose J. Lopez & Jose M. Garcia, “Application of
neural networks for prediction and optimization of exhaust emissions in
a H.D diesel engine”, SAE paper 1144, 2002, pp. 1993-2001.
[12] Simon Haykin, 1999, Neural Networks- A Comprehensive Foundation,
Pearson Education Publishing.
[13] T. N. Nagabhushana, Course material- Advances in Neural Computing,
Short Term Training Program, sponsored by AICTE-ISTE- New Delhi,
India, 1999.
[14] Srinivasa Pai. P, Acoustic Emission based Tool Wear Monitoring using
some improved neural network methodologies, Ph.D Thesis, S.J.
College of Engineering, University of Mysore, Mysore, 2004.