In this paper, a feedforward—feedback control is developed for the air—fuel ratio (AFR) of spark ignition engines using neural network estimators. To maintain the AFR at stoichiometric value, the throttle angle change is seen as a disturbance, from which the air flowrate is predicted. The injected fuel is also predicted using the inverse of the fuel injection dynamics. The proposed method is evaluated on an engine simulation benchmark and the performance is shown much improved over proportional—integral control. The new method needs moderate computation and therefore has strong potential to be used in production engines.
WeathersT.HunterC. C. Automotive computers and control systems, 1984 (Prentice-Hall, Englewood Cliffs, New Jersey).
2.
AlippiC.de RussisC.PiuriV. A neural-network based control solution to air-fuel ratio control for automotive fuel-injection systems. IEEE Trans. Systems Man Cybernetics, 2003, 33(2), 259–268.
3.
GansertW.BertramT.PfaffW.RichterG.SporckmannB.Automotive electrics and electronics, 1999 (SAE International, Robert Bosch GmbH, New York).
4.
ManzieC.PalaniswamiM.WatsonH. Gaussian networks for fuel injection control. Proc. Instn Mech. Engrs Part D: J. Automobile Engineering, 2001, 215(10), 1053–1068.
5.
ManzieC.PalaniswamiM.RalphD.WatsonH.YiX. Model predictive control of a fuel injection system with a radial basis function network observer. Trans. ASME J. Dynamic Systems Measmt Control, 2002, 124(4), 648–658.
6.
BalluchiA.BenvenutiL.Di BenedettoM. D.PinelloC.Sangiovanni-VincentelliA. L. Automotive engine control and hybrid systems: Challenges and opportunities. Proc. IEEE, 2000, 88(7), 888–912.
7.
De NicolaoG.ScattoliniR.SivieroC. Modelling the volumetric efficiency of IC engines: Parametric, non-parametric and neural techniques. Control Engng Practice, 1996, 4(10), 1405–1415.
VinsonneauJ. A. F.ShieldsD. N.KingP. J.BurnhamK. J. Polynomial and neural network spark ignition engine intake manifold modelling. In Proceedings of the Conference on Systems Engineering (ICSE) Coventry UK, 2003, vol. 2, pp. 718–723.
10.
BehamM.Modelling, calibration and control of VVT SI engines using neural networks PhD Thesis, Liverpool John Moores University, 2004.
11.
OnderC. H.GeeringH. P. Model-based multivariable speed and air-to-fuel ratio control of an SI engine. SAE technical paper 930859, 1993.
12.
ChoiS. B.HendricksJ. K. An observer-based controller design method for improving air-fuel characteristics of spark ignition engines. IEEE Trans. Control Systems Technol., 1998, 6(3), 325–334.
13.
WonM.ChoiS. B.HendrickJ. K.Air-to-fuel ratio control of spark ignition engines using Gaussian network sliding control. IEEE Trans. Control Systems Technol., 1998, 6(5), 678–688.
14.
GeS.ZhangJ.Neural-network control of nonaffine nonlinear system with zero dynamics by state and output feedback. IEEE Trans. Neural Networks, 2003, 14(7), 900–918.
15.
GirosiF.PoggioT. Network and the best approximation property. Biol. Cybernetics, 1999, 63, 169–176.
16.
HendricksE.EnglerD.FamM. A generic mean value engine model for spark ignition engines. In Proceedings of the 41st Simulation Conference, Lyngby, Denmark, 2000 (available on CD-ROM).
17.
TianZ.BellK. L.Van TreesH. L. A recursive least squares implementation for lcmp beamforming under quadratic constraint. IEEE Trans. Signal Processing, 2001, 49(6), 1138–1145.
18.
HeywoodJ. B. Internal combustion engine fundamentals, 1988 (McGraw-Hill, New York).
19.
LeeT. H.HuangS. N.TangK. Z.TanK. K.Al MamunA.PID control incorporating RBF-neural network for servo mechanical systems. In Proceedings of the 29th Annual Conference of the IEEE, November 2003, vol. 3 pp. 2789–2793 (IEEE, New York).
20.
ScottG. M.ShavlikJ. W.RayW. H.Refining PID controllers using neural networks. Technical Report, Working Paper 91–3, Machine Learning Research Group, Madison, Wisconsin, 1991.
21.
FranklinG. F.PowellJ. D.WorkmanM.Digital control of dynamic systems, 3rd edition, 2001 (Addison-Wesley, Reading, Massachusetts).
