Implementation of computationally efficient Taguchi robust design procedure for development of ANN fuel consumption prediction models
Reduction of passenger cars fuel consumption and associated emissions are two major goals of sustainable transport over the last years. Passenger car fuel consumption is directly related to a number of technological aspects of a given car, driver behaviour, road and weather conditions and, especially at urban level, road structure and traffic flow and conditions. In this paper, passenger car fuel consumption was assumed to be a function of three input variables, i.e. day of week, hour of day and city zone. Over the period of 6 months (during 2015) a car was driven in the randomly chosen routes in the city of Niš (Serbia) in the period from 8 to 23 h. The fuel consumption data recorded through on-board diagnostics equipment were used for the development of Artificial Neural Network (ANN) models. In order to efficiently deal with a number of ANN design issues, to avoid usual trial and error procedure and develop robust, high performance ANN models, the Taguchi method was applied. For experimentation with ANN design parameters (transfer function, the number of neurons in the first hidden layer, the number of neurons in the second hidden layer, training algorithm), the standard L18 orthogonal array with two replications was selected. Statistical results indicate the dominant influence of the training algorithm, followed by the ANN topology, i.e. interaction of the number of neurons in hidden layers, on the ANN models performance. It has been observed that 3-8-8-1 ANN model represents an optimal model for prediction of passenger car fuel consumption. This model has logistic sigmoid transfer functions in hidden layers trained with scaled conjugate gradient algorithm. By using the Taguchi optimized ANN models, analysis of passenger car fuel consumption has been discussed based on traffic conditions, i.e. different days of the week and hours of the day, for each city zone and separately for summer and winter periods.
Keyword : fuel consumption, traffic conditions, artificial neural network, Taguchi method, on-board measurements, city traffic modelling, prediction model
This work is licensed under a Creative Commons Attribution 4.0 International License.
Aliev, R. A.; Aliev, R. R. 2001. Soft Computing and Its Applications. World Scientific Pub Co Inc. 450 p.
Arcaklioğlu, E.; Çelıkten, İ. 2005. A diesel engine’s performance and exhaust emissions, Applied Energy 80(1): 11–22. https://doi.org/10.1016/j.apenergy.2004.03.004
Baker, M. 1994. Fuel Consumption and Emission Models for Evaluating Traffic Control and Route Guidance Strategies: Master Thesis. Queen’s University, Kingston, Ontario, Canada.
Bouamrane, K.; Tahon, C.; Sevaux, M.; Beldjilali, B. 2005. Decision making system for regulation of a bimodal urban transportation network, associating a classical and a multi-agent approaches, Informatica 16(4): 473–502.
Cartenì, A.; Cantarella, G. E.; De Luca, S. 2010. A methodology for estimating traffic fuel consumption and vehicle emissions for urban planning, in 12th World Conference on Transport Research: WCTR 2010, 11–15 July 2010, Lisbon, Portugal, 52–71.
Çay, Y.; Korkmaz, I.; Çiçek, A.; Kara, F. 2013. Prediction of engine performance and exhaust emissions for gasoline and methanol using artificial neural network, Energy 50: 177–186. https://doi.org/10.1016/j.energy.2012.10.052
Cybenko, G. 1989. Approximation by superpositions of a sigmoidal function, Mathematics of Control, Signals and Systems 2(4): 303–314. https://doi.org/10.1007/BF02551274
Dallmeyer, J.; Taubert, C.; Lattner, A. D.; Timm, I. J. 2012. Fuel consumption and emission modeling for urban scenarios, in ECMS 2012: Proceedings of the 26th European Conference on Modelling and Simulation, 29 May– 1 June 2012, Koblenz, Germany, 574–580. https://doi.org/10.7148/2012-0574-0580
Demuth, H.; Beale, M.; Hagan, M. 2008. Neural Network Toolbox™ 6: User’s Guide. The MathWorks, Inc. 907 p.
Duarte, G. O.; Gonçalves, G. A.; Farias, T. L. 2016. Analysis of fuel consumption and pollutant emissions of regulated and alternative driving cycles based on real-world measurements, Transportation Research Part D: Transport and Environment 44: 43–54. https://doi.org/10.1016/j.trd.2016.02.009
Duch, W.; Jankowski, N. 1997. New neural transfer functions, International Journal of Applied Mathematics and Computer Science 7(3): 639–658.
Fontaras, G.; Zacharof, N.-G.; Ciuffo, B. 2017. Fuel consumption and CO2 emissions from passenger cars in Europe – Laboratory versus real-world emissions, Progress in Energy and Combustion Science 60: 97–131. https://doi.org/10.1016/j.pecs.2016.12.004
Ghosh, R.; Ghosh, M.; Yearwood, J.; Bagirov, A. 2005. Determining regularization parameters for derivative free neural learning, Lecture Notes in Computer Science 3587: 71–79. https://doi.org/10.1007/11510888_8
Haq, G.; Weiss, M. 2016. CO2 labelling of passenger cars in Europe: status, challenges, and future prospects, Energy Policy 95: 324–335. https://doi.org/10.1016/j.enpol.2016.04.043
Haykin, S. 1998. Neural Networks: a Comprehensive Foundation. 2nd edition. Prentice Hall. 842 p.
Huang, J.; Wang, Y.; Liu, Z.; Guan, B.; Long, D.; Du, X. 2016. On modeling microscopic vehicle fuel consumption using radial basis function neural network, Soft Computing 20(7): 2771–2779. https://doi.org/10.1007/s00500-015-1676-7
Igliński, H. 2009. Kongestia transportowa w Poznaniu i wybrane sposoby jej ograniczenia, Transport Miejski i Regionalny 3: 2–10. (in Polish).
Kannan, G. R.; Balasubramanian, K. R.; Anand, R. 2013. Artificial neural network approach to study the effect of injection pressure and timing on diesel engine performance fueled with biodiesel, International Journal of Automotive Technology 14(4): 507–519. https://doi.org/10.1007/s12239-013-0055-6
Kara Togun, N.; Baysec, S. 2010. Prediction of torque and specific fuel consumption of a gasoline engine by using artificial neural networks, Applied Energy 87(1): 349–355. https://doi.org/10.1016/j.apenergy.2009.08.016
Kumar, S.; Pai, P. S.; Rao, B. R. S.; Vijay, G. S. 2016. Prediction of performance and emission characteristics in a biodiesel engine using WCO ester: a comparative study of neural networks, Soft Computing 20(7): 2665–2676. https://doi.org/10.1007/s00500-015-1666-9
Marinković, V.; Madić, M. 2011. Optimization of surface roughness in turning alloy steel by using Taguchi method, Scientific Research and Essays 6(16): 3474–3484. https://doi.org/10.5897/SRE11.704
Masikos, M.; Demestichas, K.; Adamopoulou, E.; Theologou, M. 2014. Reliable vehicular consumption prediction based on machine learning, Neural Network World 24(4): 333–342. https://doi.org/10.14311/NNW.2014.24.019
Møller, M. F. 1993. A scaled conjugate gradient algorithm for fast supervised learning, Neural Networks 6(4): 525–533. https://doi.org/10.1016/S0893-6080(05)80056-5
Moret, S.; Bierlaire, M.; Maréchal, F. 2016. Robust optimization for strategic energy planning, Informatica 27(3): 625–648. https://doi.org/10.15388/Informatica.2016.103
Murrell, D. 1980. Passenger Car Fuel Economy: EPA and Road: a Report to the Congress. No EPA-460/3-80-010. United States Environmental Protection Agency (EPA). 310 p.
Oğuz, H.; Sarıtas, I.; Baydan, H. E. 2010. Prediction of diesel engine performance using biofuels with artificial neural network, Expert Systems with Applications 37(9): 6579–6586. https://doi.org/10.1016/j.eswa.2010.02.128
Özener, O.; Yüksek, L.; Özkan, M. 2013. Artificial neural network approach to predicting engine-out emissions and performance parameters of a turbo charged diesel engine, Thermal Science 17(1):153–166. https://doi.org/10.2298/TSCI120321220O
Parlak, A.; Islamoglu, Y.; Yasar, H.; Egrisogut, A. 2006. Application of artificial neural network to predict specific fuel consumption and exhaust temperature for a Diesel engine, Applied Thermal Engineering 26(8–9): 824–828. https://doi.org/10.1016/j.applthermaleng.2005.10.006
Patterson, D. W. 1996. Artificial Neural Networks: Theory and Applications. Prentice-Hall. 477 p.
Phadke, M. S. 1989. Quality Engineering Using Robust Design. Prentice Hall. 333 p.
Rahimi-Ajdadi, F.; Abbaspour-Gilandeh, Y. 2011. Artificial neural network and stepwise multiple range regression methods for prediction of tractor fuel consumption, Measurement 44(10): 2104–2111. https://doi.org/10.1016/j.measurement.2011.08.006
Ross, P. J. 1995. Taguchi Techniques for Quality Engineering. McGraw-Hill Professional. 329 p.
Sayin, C.; Ertunc, H. M.; Hosoz, M.; Kilicaslan, I.; Canakci, M. 2007. Performance and exhaust emissions of a gasoline engine using artificial neural network, Applied Thermal Engineering 27(1): 46–54. https://doi.org/10.1016/j.applthermaleng.2006.05.016
Sha, W.; Edwards, K. L. 2007. The use of artificial neural networks in materials science based research, Materials & Design 28(6): 1747–1752. https://doi.org/10.1016/j.matdes.2007.02.009
Siami-Irdemoosa, E.; Dindarloo, S. R. 2015. Prediction of fuel consumption of mining dump trucks: a neural networks approach, Applied Energy 151: 77–84. https://doi.org/10.1016/j.apenergy.2015.04.064
Slowik, A.; Bialko, M. 2008. Training of artificial neural networks using differential evolution algorithm, in 2008 Conference on Human System Interactions, 25–27 May 2008, Krakow, Poland, 60–65. https://doi.org/10.1109/HSI.2008.4581409
Taguchi, G.; Chowdhury, S.; Wu, Y. 2004. Taguchi’s Quality Engineering Handbook. Wiley-Interscience. 1696 p.
Tietge, U.; Mock, P.; Franco, V.; Zacharof, N. 2017. From laboratory to road: modeling the divergence between official and real-world fuel consumption and CO2 emission values in the German passenger car market for the years 2001–2014, Energy Policy 103: 212–222. https://doi.org/10.1016/j.enpol.2017.01.021
Uzun, A. 2012. A parametric study for specific fuel consumption of an intercooled diesel engine using a neural network, Fuel 93: 189–199. https://doi.org/10.1016/j.fuel.2011.11.004
Van den Brink, R. M. M.; Van Wee, B. 2001. Why has car-fleet specific fuel consumption not shown any decrease since 1990? Quantitative analysis of Dutch passenger car-fleet specific fuel consumption, Transportation Research Part D: Transport and Environment 6(2): 75–93. https://doi.org/10.1016/S1361-9209(00)00014-6
Wilson, D. R.; Martinez, T. R. 2003. The general inefficiency of batch training for gradient descent learning, Neural Networks 16(10): 1429–1451. https://doi.org/10.1016/S0893-6080(03)00138-2
Wu, J.-D.; Liu, J.-C. 2012. A forecasting system for car fuel consumption using a radial basis function neural network, Expert Systems with Applications 39(2): 1883–1888. https://doi.org/10.1016/j.eswa.2011.07.139
Wu, J.-D.; Liu, J.-C. 2011. Development of a predictive system for car fuel consumption using an artificial neural network, Expert Systems with Applications 38(5): 4967–4971. https://doi.org/10.1016/j.eswa.2010.09.155
Yu, H.; Wilamowski, B. M. 2011. Levenberg–Marquardt training, in B. M. Wilamowski, J. D. Irwin (Eds.). The Industrial Electronics Handbook, 12.1–12.15. https://doi.org/10.1201/b10604-15
Yusaf, T. F.; Buttsworth, D. R.; Saleh, K. H.; Yousif, B. F. 2010. CNG-diesel engine performance and exhaust emission analysis with the aid of artificial neural network, Applied Energy 87(5): 1661–1669. https://doi.org/10.1016/j.apenergy.2009.10.009
Zurada, J. M. 1992. Introduction to Artificial Neural Systems. West Group. 758 p.