Determining optimal artificial neural network training method in predicting the performance and emission parameters of a biodiesel-fueled diesel generator

Öz

Artificial neural network (ANN) methods were employed and suggested in modeling the emissions and performance of a diesel generator fueled with waste cooking oil derived biodiesel during steady-state operation. These papers are generally built on determining optimal network structure, but the modelling accuracy of an ANN is also highly dependent on employed training method. In modeling, operating conditions and fuel blend ratio were used as the inputs while the performance and emission parameters were the outputs. The modeling results obtained by conventional ANNs that were trained by back propagation (BP) learning algorithm, radial basis function (RBF), and extreme learning machine (ELM) were compared with experimental results and each other. The accuracy of the estimations by ELM was above 95% for all the output parameters except for specific fuel consumption and thermal efficiency. Moreover, ELM performed better than BP and RBF with lower mean relative error (MRE) in case where the emissions were estimated. The ELM provided correlation coefficients of 0.987, 0.950 and 0.996 for unburned hydrocarbons (HCs), nitrogen oxides (NOx) and smoke opacity (SO), respectively, while for BP, they were 0.973, 0.818, 0.993, and for RBF, 0.975, 0.640 and 0.981. The most suitable training function for each emission and performance parameters of diesel generator was determined based on obtained accuracies.

Anahtar Kelimeler

• Extreme learning machine,Artificial Neural Network; Radial Basis Function; Back propagation; Biodiesel; Diesel generator; Emissions

Kaynakça

1. C. Sayin, M. Canakci, Effects of injection timing on the engine performance and exhaust emissions of a dual-fuel diesel engine, Energ. Convers. Manage. 50(1) (2009) 203-13.
2. A. Mucak, M. Karabektas, C. Hasimoglu, G. Ergen, Performance and Emission Characteristics of a Diesel Engine Fuelled with Emulsified Biodiesel-Diesel Fuel Blends. International Journal of Automotive Engineering and Technologies, 5(4), (2016), 176-185.
3. C. Haşimoğlu, M. Ciniviz, İ. Özsert, Y. İçingür, A. Parlak, M. S. Salman, Performance characteristics of a low heat rejection diesel engine operating with biodiesel. Renewable energy, 33(7), (2008) 1709-1715.
4. M.S. Graboski, R.L. McCormick, Combustion of fat and vegetable oil derived fuels in diesel engines, Progress Energy Combust Sci. 24(2) (1998) 125-64.
5. EC European Commission, Directive 2009/28/EC of the European Parliament and of the Council of 23 April 2009 on the promotion of the use of energy from renewable sources and amending and subsequently repealing Directives 2001/77/EC and 2003/30, Official Journal of the European Union Belgium (2009).
6. Venkata Ramanan, M., Yuvarajan, D., Emission analysis on the influence of magnetite nanofluid on methylester in diesel engine, Atmospheric Pollution Research (2015), http://dx.doi.org/10.1016/j.apr.2015.12.001.
7. Ş. Altun, C. Öner, Gaseous emission comparison of a compression–ignition engine fueled with different biodiesels, International J Environ. Sci. Techn. 10(2) (2013) 371-6.
8. M. Lapuerta, J.M. Herreros, L.L. Lyons, R. García-Contreras, Y. Briceño, Effect of the alcohol type used in the production of waste cooking oil biodiesel on diesel performance and emissions, Fuel 87(15) (2008) 3161-9.

9. B. Kegl, NOx and Particulate Matter (PM) Emissions Reduction Potential by Biodiesel Usage, Energy Fuels 21 (2007) 3310–16.
10. O.S. Valente, V.M.D. Pasa, C.R.P. Belchior, J.R. Sodré, Exhaust emissions from a diesel power generator fuelled by waste cooking oil biodiesel, Sci Total Environ. 431 (2012) 57-61.
11. Ş. Altun, Effect of the degree of unsaturation of biodiesel fuels on the exhaust emissions of a diesel power generator, Fuel 117 (2014) 450-7.
12. E. Alpaydin, Introduction to machine learning, 2nd Ed. MIT press (2010) 273-318.
13. W. S. McCulloch, W. Pitts, A logical calculus of the ideas immanent in nervous activity, The bulletin of mathematical biophysics, 5(4) (1943) 115-33.
14. W.K. Yap, V. Karri, Comparative analysis of artificial neural networks and dynamic models as virtual sensors, Appl. Soft Computing 13(1) (2013) 181-8.
15. G. Kokkulunk, E. Akdogan, V. Ayhan, Prediction of emissions and exhaust temperature for direct injection diesel engine with emulsified fuel using ANN, Turkish J Electrical Engineering and Computer Sciences 21 (2013) 2141-52.
16. R.S. Kumar, R. Manimaran, V. Gopalakrishnan, Performance and Emission Analysis Using Pongamia Oil Biodiesel Fuel with an Artificial Neural Network, Advanced Engineering and Applied Sciences: An International Journal 3(1) (2013) 17-20.
17. K.B. Patel, T.M. Patel, Performance Modeling of Single Cylinder Diesel Engine for Pyrolysis Oil and Diesel Blend using Neural Networks, International Journal of Emerging Technology and Advanced Engineering 3(1) (2013) 193-5.
18. S. Kumar, P. S. Pai, B. R. Rao, Radial-basis-function-network-based prediction of performance and emission characteristics in a bio diesel engine run on WCO ester, Advances in Artificial Intelligence 10 (2012) 1-7.
19. W. Shi, J. Yang, T. Tang, RBF NN based marine diesel engine generator modeling, in: American Control Conference, 2005, pp. 2745-9.
20. G.B. Huang, Q.Y. Zhu, C.K. Siew, Extreme learning machine: a new learning scheme of feedforward neural networks, in: Proceedings of the 2004 International Joint Conference on Neural Networks, vol. 2, 2004, pp. 985–90.
21. G. B. Huang, Q. Y. Zhu, C. K. Siew, Extreme learning machine: theory and applications, Neurocomputing 70(1) (2006) 489-501.
22. K. I. Wong, P. K. Wong, C. S. Cheung, C. M. Vong, Modeling and optimization of biodiesel engine performance using advanced machine learning methods, Energy 55 (2013) 519-28.
23. K. I. Wong, P. K. Wong, C. S. Cheung, C. M. Vong, Modelling of diesel engine performance using advanced machine learning methods under scarce and exponential data set, Applied Soft Computing 13(11) (2013) 4428-41.
24. Ş. Altun, F. Yasar, A comparison of performance and emissions of a diesel power generator fueled with biodiesels from waste frying oils, in: Proceedings of EuroTecS-2013, vol. 1, 2013, pp.139-143. Sarajevo, Bosnia and Herzegovina.
25. S. Tasdemir, I. Saritas, M. Ciniviz, N. Allahverdi, Artificial neural network and fuzzy expert system comparison for prediction of performance and emission parameters on a gasoline engine. Expert Systems with Applications, 38(11), (2011), 13912-13923.
26. İ. Örs, V. Bakırcıoğlu, An Experimental and ANNs Study of the Effects of Safflower Oil Biodiesel on Engine Performance and Exhaust Emissions in a CI Engine. International Journal of Automotive Engineering and Technologies, 5(3), (2016), 125-135.
27. ÖF. Ertuğrul, Y. Kaya, A detailed analysis on extreme learning machine and novel approaches based on ELM, American Journal of Computer Science and Engineering 1(5), (2014) 43-50.,
28. ÖF. Ertuğrul, Ş. Altun, Developing Correlations by Extreme Learning Machine for Calculating Higher Heating Values of Waste Frying Oils from their Physical Properties, Neural Computing and Applications, (2016), DOI: 10.1007/s00521-016-2233-8.
29. D.E. Rumelhat, G.E. Hinon, R.J. Williams, Learning representations by back-propagating errors, Nature 323 (1986) 533-6.
30. D. S. Broomhead, D. Lowe, Radial basis functions, multi-variable functional interpolation and adaptive networks (No.RSRE-MEMO-4148), Royal Signals and Radar Establishment Malvern, UK (1988).
31. G. B. Huang, H. A. Babri, Upper bounds on the number of hidden neurons in feedforward networks with arbitrary bounded nonlinear activation functions, Neural Networks 9(1) (1998) 224-229.
32. R. Kohavi, A study of cross-validation and bootstrap for accuracy estimation and model selection, IJCAI 14(2) (1995) 1137-1145.
33. W. Mao, Y. Wang, X. Cao, Y. Zheng, Mixture Regression Estimation based on Extreme Learning Machine, Journal of Computers, 8(11) (2013) 2925-2933.