0
Research Papers: Internal Combustion Engines

VGT and EGR Control of Common-Rail Diesel Engines Using an Artificial Neural Network

[+] Author and Article Information
Byounggul Oh

Advanced Combustion & Engine
Technology Team,
Institute of Technology,
Doosan Infracore Co., Ltd.,
39-3, Sungbok-Dong,
Suji-Gu, Yongin-Si,
Gyeonggi-Do 448-795, Korea

Jeongwon Sohn

Department of Automotive Engineering,
Hanyang University,
222 Wangsimni-ro, Seongdong-gu,
Seoul 133-791, Korea

Jongseob Won

Department of Mechanical and
Automotive Engineering,
Jeonju University,
303 Cheonjam-ro, Wansan-gu,
Jeonju 560-759, Korea

Myoungho Sunwoo

Department of Automotive Engineering,
Hanyang University,
222 Wangsimni-ro, Seongdong-gu,
Seoul 133-791, Korea
e-mail: msunwoo@hanyang.ac.kr

1Corresponding author.

Contributed by the IC Engine Division of ASME for publication in the JOURNAL OF ENGINEERING FOR GAS TURBINES AND POWER. Manuscript received February 29, 2012; final manuscript received August 6, 2012; published online November 21, 2012. Assoc. Editor: Christopher J. Rutland.

J. Eng. Gas Turbines Power 135(1), 012801 (Nov 21, 2012) (9 pages) Paper No: GTP-12-1062; doi: 10.1115/1.4007541 History: Received February 29, 2012; Revised August 06, 2012

In diesel engines, variable geometry turbocharger (VGT) and exhaust gas recirculation (EGR) systems are used to increase engine specific power and reduce NOx emissions, respectively. Because the dynamics of both the VGT and EGR are highly nonlinear and coupled to each other, better performance may be attained by substituting nonlinear multiple input, multiple output (MIMO) controllers for the existing conventional lookup table-based linear controllers. This paper presents a coordinated VGT/EGR control system for common-rail direct injection diesel engines. The objective of the control system is to track target mass air flow and target intake manifold pressure by adjusting the EGR and VGT actuator positions. We designed a nonlinear MIMO control system using a neural control scheme that adopts an indirect adaptive control approach. The neural control system is comprised of a neural network identifier, which mimics the target air system, and a neural network controller, which calculates the actuator positions. The proposed control system has been validated with engine experiments under transient operating conditions. It was demonstrated from experimental results that the proposed control system shows improved target value tracking performance over conventional VGT/EGR control system.

FIGURES IN THIS ARTICLE
<>
Copyright © 2013 by ASME
Your Session has timed out. Please sign back in to continue.

References

Daisho, Y., Uchida, N., Morita, K., Shimogata, S., and Saito, T., 1994, “Effects of Supercharging and EGR on Diesel Combustion and Emissions,” International Symposium COMODIA, Yokohama, Japan, July 11–14, pp. 281–286.
Gao, Z., and Schreiber, W., 2001, “The Effects of EGR and Split Fuel Injection on Diesel Engine Emission,” Int. J. Automot. Technol., 2(4), pp. 123–133.
Simoson, C., and Wagner, J., 2008, “Effects of Cooled EGR on a Small Displacement Diesel Engine: A Reduced-Order Dynamic Model and Experimental Study,” Trans. ASME J. Energy Resour. Technol., 130(1), p. 0111021. [CrossRef]
Zheng, M., Reader, G. T., and Hawley, J. G., 2004, “Diesel Engine Exhaust Gas Recirculation—A Review on Advanced and Novel Concepts,” Energy Convers. Manage, 45(6), pp. 883–900. [CrossRef]
Chun, K., 2006, “EGR Technology,” Auto J., 28(6), pp. 46–51.
Ham, Y., and Chun, K., 2002, “Engine Cycle Simulation for the Effects of EGR on Combustion and Emissions in a DI Diesel Engine,” Trans. KSAE, 10(4), pp. 51–59.
Yao, M., Zhang, B., Zheng, Z., Chen, Z., and Xing, Y., 2007, “Effects of Exhaust Gas Recirculation on Combustion and Emissions of a Homogeneous Charge Compression Ignition Engine Fuelled with Primary Reference Fuels,” Proc. Inst. Mech. Eng., Part D (J. Automob. Eng.), 221(2), pp. 197–213. [CrossRef]
Guzzella, L., and Amstutz, A., 1998, “Control of Diesel Engines,” IEEE Control Syst. Mag., 18(5), pp. 53–71. [CrossRef]
Stefanopoulou, A. G., Kolmanovsky, I., and Freudenberg, J. S., 2000, “Control of Variable Geometry Turbocharged Diesel Engines for Reduced Emissions,” IEEE Trans. Control Syst. Technol., 8(4), pp. 733–745. [CrossRef]
Jankovic, M., and Kolmanovsky, I., 1998, “Robust Nonlinear Controller for Turbocharged Diesel Engines,” Proceedings of the American Control Conference, Philadelphia, PA, June 24–26, pp. 1389–1394. [CrossRef]
Upadhyay, D., Utkin, V., and Rizzoni, G., 2002, “Multivariable Control Design for Intake Flow Regulation of a Diesel Engine Using Sliding Mode,” Proceedings of the 15th Triennial World Congress of the International Federation of Automatic Control, Barcelona, Spain, July 21–26.
Utkin, V. L., Chang, H. C., Kolmanovsky, I., and Cook, J. A., 2000, “Sliding Mode Control for Variable Geometry Turbocharged Diesel Engines,” Proceedings of the American Control Conference, Chicago, IL, June 28–30, pp. 584–588. [CrossRef]
Ayadi, M., Langlois, N., and Chafouk, H., 2004, “Polynomial Control of Nonlinear Turbocharged Diesel Engine Model,” Proceedings of the IEEE International Conference on Industrial Technology, (ICIT'04), Hammamet, Tunisia, December 8–10, pp. 1384–1389. [CrossRef]
Gayaka, S., Yao, B., and Meckl, P. H., 2006, “A Multivariable Approach to EGR-VGT Actuator Control Problem,” ASME Proceedings of International Mechanical Engineering Congress and Exposition, Chicago, IL, November 5–10, ASME Paper No. IMECE2006-14311, pp. 307–314. [CrossRef]
Plianos, A., Achir, A., Stobart, R., Langlois, N., and Chafouk, H., 2007, “Dynamic Feedback Linearization Based Control Synthesis of the Turbocharged Diesel Engine,” Proceedings of the American Control Conference, New York, July 9–13, pp. 4407–4412. [CrossRef]
van Nieuwstadt, M. J., Kolmanovsky, I. V., Moraal, P. E., Stefanopoulou, A., and Jankovic, M., 2000, “EGR-VGT Control Schemes: Experimental Comparison for a High-Speed Diesel Engine,” IEEE Control Syst. Mag., 20(3), pp. 64–79. [CrossRef]
Heywood, J., 1988, Internal Combustion Engine Fundamentals, McGraw-Hill, New York.
Chung, N., Kim, S., and Sunwoo, M., 2005, “Nonlinear Dynamic Model of a Turbocharged Diesel Engine,” Proceedings of the SAE World Congress and Exhibition, SAE Paper No. 2005-01-0017. [CrossRef]
Yoon, P., and Sunwoo, M., 2001, “A Nonlinear Dynamic Modelling of SI Engines for Controller Design,” Int. J. Vehicle. Des., 26(2-3), pp. 277–297.
Bai, L., and Yang, M., 2002, “Coordinated Control of EGR and VNT in Turbocharged Diesel Engine Based on Intake Air Mass Observer,” Proceedings of the SAE World Congress and Exhibition, Detroit, MI, March 4, SAE Paper No. 2002-01-1292. [CrossRef]
Zhao, H., 2010, Advanced Direct Injection Combustion Engine Technologies and Development, 1st ed., Vol. 2, Woodhead Publishing Limited, Cambridge, UK.
Simani, S., and Bonfe, M., “Fuzzy Modelling and Control of the Air System of a Diesel Engine,” Adv. Fuzzy Syst., 2009, p. 450259. [CrossRef]
Hjalmarsson, H., Gevers, M., and de Bruyne, F., 1996, “For Model-Based Control Design, Closed-Loop Identification Gives Better Performance,” Automatica, 32(12), pp. 1659–1673. [CrossRef]
Hornik, K., Stinchcombe, M., and White, H., 1989, “Multilayer Feedforward Networks are Universal Approximators,” Neural Networks, 2(5), pp. 359–366. [CrossRef]
Leitch, R., 1992, “Artificial Intelligence in Control: Some Myths, Some Fears but Plenty Prospects,” Comput. Control Eng. J., 3(4), pp. 153–163. [CrossRef]
Liu, G. P., 2001, Nonlinear Identification and Control: A Neural Network Approach, Springer, New York.
Narendra, K. S., and Parthasarathy, K., 1990, “Identification and Control of Dynamical Systems Using Neural Networks,” IEEE Trans. Neural Networks, 1(1), pp. 4–27. [CrossRef]
Willis, M. J., Montague, G. A., Di Massimo, C., Tham, M. T., and Morris, A. J., 1992, “Artificial Neural Networks in Process Estimation and Control,” Automatica, 28(6), pp. 1181–1187. [CrossRef]
Jeon, G. J., and Lee, I., 1996, “Neural Network Indirect Adaptive Control With Fast Learning Algorithm,” Neurocomputing, 13(2-4), pp. 185–199. [CrossRef]
Chu, S. R., Shoureshi, R., and Tenorio, M., 1990, “Neural Networks for System Identification,” IEEE Control Syst. Mag., 10(3), pp. 31–35. [CrossRef]
Guez, A., Eilbert, J. L., and Kam, M., 1988, “Neural Network Architecture for Control,” IEEE Control Syst. Mag., 8(2), pp. 22–25. [CrossRef]
Hagan, M. T., Demuth, H. B., and Beale, M. H., 1995, Neural Network Design, PWS Publishing Company, Boston.
Psaltis, D., Sideris, A., and Yamamura, A. A., 1988, “A Multilayered Neural Network Controller,” IEEE Control Syst. Mag., 8(2), pp. 17–21. [CrossRef]
Fu, K. S., 1970, “Learning Control Systems–Review and Outlook,” IEEE Trans. Automat. Control, 15(2), pp. 210–221. [CrossRef]
Miller, W. T., Sutton, R. S., and Werbos, P. J., 1995, Neural Networks for Control, MIT Press, Cambridge, MA.
Poggio, T., and Girosi, F., 1990, “Regularization Algorithms for Learning That are Equivalent to Multilayer Networks,” Science, 247(4945), pp. 978–982. [CrossRef] [PubMed]
Werbos, P. J., 1990, “Backpropagation Through Time: What It Does and How to Do It,” Proc. IEEE, 78(10), pp. 1550–1560. [CrossRef]

Figures

Grahic Jump Location
Fig. 1

Trade-off between particulate matter (PM) emission and nitrogen oxide (NOx) emission with respect to the EGR rate

Grahic Jump Location
Fig. 2

Schematic diagram of the diesel engine air path

Grahic Jump Location
Fig. 3

Schematic diagram of a conventional VGT/EGR control algorithm

Grahic Jump Location
Fig. 4

VGT/EGR control algorithm based on indirect adaptive control neural network

Grahic Jump Location
Fig. 5

Input and output spaces of the neural networks (top: identifier, bottom: controller)

Grahic Jump Location
Fig. 6

Experimental apparatus for the proposed MAP and MAF control algorithm

Grahic Jump Location
Fig. 7

Function approximation performance of the MAP identifier during neural network training

Grahic Jump Location
Fig. 8

Function approximation performance of the MAF identifier during neural network training

Grahic Jump Location
Fig. 9

Target value tracking performance of the MAP and MAF control system during neural network training (APS change)

Grahic Jump Location
Fig. 10

Target value tracking performance of the MAP and MAF control system during neural network training (RPM change)

Grahic Jump Location
Fig. 11

Target value tracking performance of the MAP and MAF controller when control algorithm is switched from neural network to conventional control (switch occurs at 112 s, APS change)

Grahic Jump Location
Fig. 12

Target value tracking performance of the MAP and MAF controller when control algorithm is switched from neural network to conventional control (switch occurs at 250 s, RPM change)

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In