Estimation of the COVIMEP Variation in a HCCI Engine

Year 2020, Volume: 23 Issue: 3, 721 - 727, 01.09.2020

Seyfi Polat , Hamit Solmaz , Alper Calam , Emre Yılmaz

https://doi.org/10.2339/politeknik.567865

Cited By: 6

Abstract

In this study,
variation of the COV_IMEP was tried to be predicted by using the
artificial neural network method for 4-stroke, 4-cylinder, direct injection and
supercharged HCCI engine experimental data obtained by using n-heptane fuel at
60 ^oC intake air temperature, 1000 rpm engine speed at different
inlet air intake pressure. Intake air inlet pressure and lambda were used as
input data in artificial neural network model. The COV_IMEP value was
used as the target. Three layers and five neurons were used to construct the
network using the Levenberg-Marquardt algorithm. Correlation between targets
and outputs for teaching, accuracy and testing were obtained as 0.97989, 0.9504
and 0.91644, respectively. Total correlation factor was found as 0.96983. As a
result of the study, it was seen that the stored data and the estimated COV_IMEP
data were compatible.

Keywords

HCCI Engine, Low Temperature Combustion, Artificial Neural Network

Estimation of the COVIMEP Variation in a HCCI Engine

Abstract

In this study, variation of the COV_IMEP was tried to be predicted by using the artificial neural network method for 4-stroke, 4-cylinder, direct injection and supercharged HCCI engine experimental data obtained by using n-heptane fuel at 60 ^oC intake air temperature, 1000 rpm engine speed at different inlet air intake pressure. Intake air inlet pressure and lambda were used as input data in artificial neural network model. The COV_IMEP value was used as the target. Three layers and five neurons were used to construct the network using the Levenberg-Marquardt algorithm. Correlation between targets and outputs for teaching, accuracy and testing were obtained as 0.97989, 0.9504 and 0.91644, respectively. Total correlation factor was found as 0.96983. As a result of the study, it was seen that the stored data and the estimated COV_IMEP data were compatible.

Keywords

HCCI Engine, Low Temperature Combustion, Artificial Neural Network

References

• [1] Zhao, H. (2007). HCCI and CAI engines for the automotive industry. Woodhead Publishing Ltd., Cambridge England.
• [2] Heywood, J. B. (1988). Internal combustion engine Fundamentals. McGraw- Hill, New York.
• [3] Hasan, M.M., Rahman, M.M., Kadirgama, K. (2015). A review on homogeneous charge compression ignition engine performance using biodiesel-diesel blend as a fuel. International Journal of Automotive and Mechanical Engineering, vol.11, p.2199 - 2211.
• [4] Hairuddin, A.A., Wandel, A.P., Yusaf, T. (2014). An introduction to a homogeneous charge compression ignition engine. Journal of Mechanical Engineering and Sciences, vol. 7, p.1042-1052.
• [5] Baumgarter, C. (2006). Mixture formation in internal combustion engines. Springer, Heat and Mass transfer series, p. 253-286.
• [6] Uyumaz, A. (2014). Investigation of the effects of valve lift in a homogenous charged compression ignition gasoline engine on combustion and performance, Ph. D. Thesis, Gazi University, p. 3-12.
• [7] Polat, S. (2015). An investigation of the effects of operation parameters on combustion in a HCCI engine, Ph. D. Thesis, Gazi University, p. 4-15.
• [8] Khandelwal, M., Singh T.N. (2006). Prediction of blast induced ground vibrations and frequency in opencast mine: A neural network approach. Journal of Sound and Vibration, vol.289, no.4-5, p. 711-725.
• [9] Luger, G.F. (2002). Artifical Intelligence: Structures and Strategies for Complex Problem Solving. 4th edition, Addison-Wesley.
• [10] Ismail, H.M., Ng, H.K., Queck, C.W., Gan, S. (2012). Artificial neural networks modelling of engine-out responses for a light-duty diesel engine fuelled with biodiesel blends. Applied Energy, vol.92, p.769–777.
• [11] Rezaei, J., Shahbakhti, M., Bahri, B., Aziz, A.A. (2015). Performance prediction of HCCI engines with oxygenated fuels using artificial neural networks. Applied Energy, vol.138, no.460–473.
• [12] Nabiyev, V.V., (2016).Yapay Zeka, Seçkin Yayıncılık, Ankara, 2016, pp 598.
• [13] Marquardt, D., (1963). An Algorithm for Least-Squares Estimation of Nonlinear Parameters, SIAM Journal on Applied Mathematics, Vol. 11, No. 2, June 1963, pp 431–441.
• [14] Hagan, M.T., and M. Menhaj, ‘Training feed-forward networks with the Marquardt algorithm’, IEEE Transactions on Neural Networks, Vol. 5, No. 6, 1999, pp 989–993, 1994.