Abstract
This study includes the design of an autonomous exhaust gas recirculation (EGR) cooling system and implementation of the system on diesel engine by using deep neural network (DNN)-based controller. The NOx formation and BSFC were optimized as output variables considering engine speed, load, EGR ratio and the exhaust gas temperature entering the intake manifold as input variables using deep and traditional NN modelling method. The DNN modelling method has stronger prediction capability than traditional NN and can deal with the modelling problem in the complex ICE data. The developed NN models were compared with the relative error analysis to verify the effectiveness of the deep NN modelling method. The activation function, the number of neurons, learning rate and backpropagation optimization method were considered as algorithm performance parameters for the design of optimum network by using the searching method. R2, MSE, MAE and RAE are used to evaluate the output performance of the deep and traditional NN model. Then, the autonomous and independent EGR cooling system is designed apart from the main cooling system of the engine with electric pump and fan components, unlike conventional systems. PID controllers are designed for these components, and the parameters of the controller are determined by pattern search optimization method. In this way, the exhaust gas temperature entering the intake manifold and EGR ratio are set to the desired value according to the BSFC and NOx output parameters under different operating conditions of the engine. Experimental results showed that the designed DNN controller-based autonomous EGR cooling system outperforms compared to the conventional system in terms of reducing the NOx and BSFC, with a 5.751% and 2.997% reduction, respectively.
Similar content being viewed by others
Change history
27 February 2021
A Correction to this paper has been published: https://doi.org/10.1007/s00521-020-05380-x
Abbreviations
- ANN:
-
Artificial neural network
- BMEP:
-
Brake mean effective pressure
- BSFC:
-
Brake-specific fuel consumption
- DNN:
-
Deep neural network
- EGR:
-
Exhaust gas recirculation
- ICE:
-
Internal combustion engine
- MSE:
-
Mean squared error
- MAE:
-
Mean absolute error
- NOx:
-
Oxides of nitrogen
- NN:
-
Neural network
- PID:
-
Proportional, integral, derivative
- RAE:
-
Relative absolute error
- R 2 :
-
Coefficient of determination
- SGD:
-
Stochastic gradient descent
References
Zheng M, Reader GT, Hawley JG (2004) Diesel engine exhaust gas recirculation—a review on advanced and novel concepts. Energy Convers Manag 45:883–900. https://doi.org/10.1016/S0196-8904(03)00194-8
John H (1988) Internal combustion engine fundamentals. McGraw Hill, New York
Kreso AM, Johnson JH, Gratz LD et al (1998) A study of the effects of exhaust gas recirculation on heavy-duty diesel engine emissions. SAE Trans 107:665–680
Fan C, Sun Y, Zhao Y et al (2019) Deep learning-based feature engineering methods for improved building energy prediction. Appl Energy 240:35–45. https://doi.org/10.1016/j.apenergy.2019.02.052
Zhao H, Hu J, Ladommatos N (2000) In-cylinder studies of the effects of CO2 in exhaust gas recirculation on diesel combustion and emissions. Proc Inst Mech Eng Part D J Automob Eng 214:405–419. https://doi.org/10.1243/0954407001527727
Jo Y, Min K, Jung D et al (2019) Comparative study of the artificial neural network with three hyper-parameter optimization methods for the precise LP-EGR estimation using in-cylinder pressure in a turbocharged GDI engine. Appl Therm Eng 149:1324–1334. https://doi.org/10.1016/j.applthermaleng.2018.12.139
Ji W, Li A, Lu X et al (2019) Numerical study on NOx and ISFC co-optimization for a low-speed two-stroke engine via Miller cycle, EGR, intake air humidification, and injection strategy implementation. Appl Therm Eng 153:398–408. https://doi.org/10.1016/j.applthermaleng.2019.03.035
McTaggart-Cowan GP, Rogak SN, Hill PG et al (2004) Effect of operating condition on particulate matter and nitrogen oxides emissions from a heavy-duty direct injection natural gas engine using cooled exhaust gas recirculation. Int J Engine Res 5:499–511. https://doi.org/10.1177/146808740400500602
Ladommatos N, Abdelhalim SM, Zhao H, Hu Z (1997) The dilution, chemical, and thermal effects of exhaust gas recirculation on disesel engine emissions-part 4: effects of carbon dioxide and water vapour. SAE Technical Paper
Maiboom A, Tauzia X, Hétet J-F (2008) Experimental study of various effects of exhaust gas recirculation (EGR) on combustion and emissions of an automotive direct injection diesel engine. Energy 33:22–34. https://doi.org/10.1016/j.energy.2007.08.010
Shen K, Li F, Zhang Z et al (2017) Effects of LP and HP cooled EGR on performance and emissions in turbocharged GDI engine. Appl Therm Eng 125:746–755. https://doi.org/10.1016/j.applthermaleng.2017.07.064
Lapuerta M, Martos FJ, Herreros JM (2007) Effect of engine operating conditions on the size of primary particles composing diesel soot agglomerates. J Aerosol Sci 38:455–466. https://doi.org/10.1016/j.jaerosci.2007.02.001
Li X, Xu Z, Guan C, Huang Z (2014) Impact of exhaust gas recirculation (EGR) on soot reactivity from a diesel engine operating at high load. Appl Therm Eng 68:100–106. https://doi.org/10.1016/j.applthermaleng.2014.04.029
Kakoi Y, Tsutsui Y, Ono N et al (1998) Emission reduction technologies applied to high-speed direct injection diesel engine. SAE Tech Paper. https://doi.org/10.4271/980173
Ishiki K, Oshida S, Takiguchi M, Urabe M (2000) A study of abnormal wear in power cylinder of diesel engine with EGR-wear mechanism of soot contaminated in lubricating oil. SAE Tech Paper. https://doi.org/10.4271/2000-01-0925
Agarwal D, Singh SK, Agarwal AK (2011) Effect of exhaust gas recirculation (EGR) on performance, emissions, deposits and durability of a constant speed compression ignition engine. Applied Energy 88:2900–2907. https://doi.org/10.1016/j.apenergy.2011.01.066
Aldajah S, Ajayi OO, Fenske GR, Goldblatt IL (2007) Effect of exhaust gas recirculation (EGR) contamination of diesel engine oil on wear. Wear 263:93–98. https://doi.org/10.1016/j.wear.2006.12.055
Chalgren RD, Parker GG, Arici O, Johnson JH (2002) A controlled EGR cooling system for heavy duty diesel applications using the vehicle engine cooling system simulation. SAE Tech Paper. https://doi.org/10.4271/2002-01-0076
Zhi L, Zhu Y, Wang H et al (2016) A recurrent neural network for modeling crack growth of aluminium alloy. Neural Comput Appl 27:197–203. https://doi.org/10.1007/s00521-014-1712-z
Nasiri A, Taheri-Garavand A, Omid M, Carlomagno GM (2019) Intelligent fault diagnosis of cooling radiator based on deep learning analysis of infrared thermal images. Appl Therm Eng 163:114410. https://doi.org/10.1016/j.applthermaleng.2019.114410
Wen L, Li X, Gao L (2019) A transfer convolutional neural network for fault diagnosis based on ResNet-50. Neural Comput Appl. https://doi.org/10.1007/s00521-019-04097-w
Oh S, Ki H (2019) Deep learning model for predicting hardness distribution in laser heat treatment of AISI H13 tool steel. Appl Therm Eng 153:583–595. https://doi.org/10.1016/j.applthermaleng.2019.01.050
Taghavifar H, Mardani A, Mohebbi A, Taghavifar H (2014) Investigating the effect of combustion properties on the accumulated heat release of di engines at rated EGR levels using the ANN approach. Fuel 137:1–10. https://doi.org/10.1016/j.fuel.2014.07.073
Liu B, Zhao C, Zhang F et al (2013) Misfire detection of a turbocharged diesel engine by using artificial neural networks. Appl Therm Eng 55:26–32. https://doi.org/10.1016/j.applthermaleng.2013.02.032
Çay Y, Çiçek A, Kara F, Saǧiroǧlu S (2012) Prediction of engine performance for an alternative fuel using artificial neural network. Appl Therm Eng 37:217–225. https://doi.org/10.1016/j.applthermaleng.2011.11.019
Sayin C, Ertunc HM, Hosoz M et al (2007) Performance and exhaust emissions of a gasoline engine using artificial neural network. Appl Therm Eng 27:46–54. https://doi.org/10.1016/j.applthermaleng.2006.05.016
Saraswati S, Chand S (2010) Online linearization-based neural predictive control of air-fuel ratio in SI engines with PID feedback correction scheme. Neural Comput Appl 19:919–933. https://doi.org/10.1007/s00521-010-0419-z
Asad U, Zheng M (2014) Exhaust gas recirculation for advanced diesel combustion cycles. Appl Energy 123:242–252
Agrawal AK, Singh SK, Sinha S, Shukla MK (2004) Effect of EGR on the exhaust gas temperature and exhaustopacity in compression ignition engines. Indian Acad Sci 29:275–284. https://doi.org/10.1007/BF02703777
Rakopoulos CD, Hountalas DT (1998) Development and validation of a 3-D multi-zone combustion model for the prediction of DI diesel engines performance and pollutants emissions. SAE Technical Paper
Haghighat AK, Roumi S, Madani N et al (2018) An intelligent cooling system and control model for improved engine thermal management. Appl Therm Eng 128:253–263. https://doi.org/10.1016/j.applthermaleng.2017.08.102
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv Prepr arXiv14126980
Rahimi-Ajdadi F, Abbaspour-Gilandeh Y (2011) Artificial neural network and stepwise multiple range regression methods for prediction of tractor fuel consumption. Measurement 44:2104–2111. https://doi.org/10.1016/j.measurement.2011.08.006
Taghavifar H, Taghavifar H, Mardani A, Mohebbi A (2014) Modeling the impact of in-cylinder combustion parameters of DI engines on soot and NOx emissions at rated EGR levels using ANN approach. Energy Convers Manag 87:1–9. https://doi.org/10.1016/j.enconman.2014.07.005
Chalgren RD, Parker GG, Arici O, Johnson JH (2002) A controlled EGR cooling system for heavy duty diesel applications using the vehicle engine cooling system simulation. In: SAE Technical Papers. SAE International
Turkson RF, Yan F, Ali MKA, Hu J (2016) Artificial neural network applications in the calibration of spark-ignition engines: an overview. Eng Sci Technol. Int. J. 19:1346–1359
Acknowledgements
This work has been supported by the scientific research projects of Ataturk University (project no: 2015/362).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Akolaş, H.İ., Kaleli, A. & Bakirci, K. Design and implementation of an autonomous EGR cooling system using deep neural network prediction to reduce NOx emission and fuel consumption of diesel engine. Neural Comput & Applic 33, 1655–1670 (2021). https://doi.org/10.1007/s00521-020-05104-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-020-05104-1