Semi-empirical modeling of volumetric efficiency in engines equipped with variable valve timing system

Abstract

Volumetric efficiency and air charge estimation is one of the most demanding tasks in control of today’s internal combustion engines. Specifically, using three-way catalytic converter involves strict control of the air/fuel ratio around the stoichiometric point and hence requires an accurate model for air charge estimation. However, high degrees of complexity and nonlinearity of the gas flow in the internal combustion engine make air charge estimation a challenging task. This is more obvious in engines with variable valve timing systems in which gas flow is more complex and depends on more functional variables. This results in models that are either quite empirical (such as look-up tables), not having interpretability and extrapolation capability, or physically based models which are not appropriate for onboard applications. Solving these problems, a novel semi-empirical model was proposed in this work which only needed engine speed, load, and valves timings for volumetric efficiency prediction. The accuracy and generalizability of the model is shown by its test on numerical and experimental data from three distinct engines. Normalized test errors are 0.0316, 0.0152 and 0.24 for the three engines, respectively. Also the performance and complexity of the model were compared with neural networks as typical black box models. While the complexity of the model is less than half of the complexity of neural networks, and its computational cost is approximately 0.12 of that of neural networks and its prediction capability in the considered case studies is usually more. These results show the superiority of the proposed model over conventional black box models such as neural networks in terms of accuracy, generalizability and computational cost.

Keywords

engine modeling / modeling and simulation / spark ignition engine / volumetric efficiency / variable valve timing

References

[1] JankovicM, MagnerS W. Cylinder air-charge estimation for advanced intake valve operation in variable cam timing engines [J]. JSAE Review, 2001, 22: 445-452

[2] van NieuwstadtM J, KolmanovskyI V, HaghgooieM, HammoudMAir charge estimation in camless engines [C]//, 2001

[3] KocherL, KoeberleinE, van AlstineD G, StrickerK, ShaverG. Physically based volumetric efficiency model for diesel engines utilizing variable intake valve actuation [J]. International Journal of Engine Research, 2011, 13: 169-184

[4] MalkhedeD, KhalaneHMaximizing volumetric efficiency of IC engine through intake manifold tuning [C], 2015

[5] LeroyT, ChauvinJ, PetitN. Airpath control of a SI engine with variable valve timing actuators [C]. American Control Conference, 20082076-2083

[6] MasiM, GobbatoP. Measure of the volumetric efficiency and evaporator device performance for a liquefied petroleum gas spark ignition engine [J]. Energy Conversion and Management, 2012, 60: 18-27

[7] NellesONonlinear system identification: From classsical approaches to neural networks and fuzzy models [M], 2001BerlinSpringer

[8] KakaeeA H, MashadiB, GhajarM. General semiempirical engine model for control and simulation of active safety systems [J]. Arabian Journal for Science and Engineering, 2015, 40(5): 1517-1527

[9] ZhangR, ChangM, TurinR CVolumetric efficiency model for variable cam-phasing and variable valve lift applications [C], 2008

[10] LeroyT, AlixG, ChauvinJ, DuparchyA, le BerrF. Modeling fresh air charge and residual gas fraction on a dual independent variable valve timing SI engine [J]. SAE International Journal of Engines, 2008, 1: 627-635

[11] MårtenssonJ, FlärdhOModeling the effect of variable cam phasing on volumetric efficiency, scavenging and torque generation [C], 2010

[12] GolcuM, SekmenY, ErduranliP, SalmanM S. Artificial neural-network based modeling of variable valve-timing in a spark-ignition engine [J]. Applied Energy, 2005, 81: 187-197

[13] IsmailH M, KiatN H, QueckC W, GanS. Artificial neural networks modelling of engine-out responses for a light-duty diesel engine fuelled with biodiesel blends [J]. Applied Energy, 2012, 92: 769-777

[14] TasdemirS, SaritasI, CinivizM, AllahverdiM. Artificial neural network and fuzzy expert system comparison for prediction of performance and emission parameters on a gasoline engine [J]. Expert Systems with Applications, 2011, 38: 13912-13923

[15] Martinez-MoralesJ D, PalaciosbE, CarrilG A. Modeling of internal combustion engine emissions by LOLIMOT algorithm [J]. Procedia Technology, 2012, 3: 251-258

[16] JakubekS, HametnerC, KeuthN. Total least squares in fuzzy system identification: An application to an industrial engine [J]. Engineering Applications of Artificial Intelligence, 2008, 21: 1277-1288

[17] HametnerC, NebelM. Operating regime based dynamic engine modelling [J]. Control Engineering Practice, 2012, 20: 397-407

[18] de NicolaoG, RossiC, ScattoliniR, SuffrittiM. Identification and idle speed control of internal combustion engines [J]. Control Engineering Practice, 1999, 7: 1061-1069

[19] el HadefJ, ColinG, TalonV, ChamaillardYNeural model for real-time engine volumetric efficiency estimation [C], 2013

[20] MalaczynskiG, MuellerM, PfeifferJ, CabushDReplacing volumetric efficiency calibration look-up tables with artificial neural network-based algorithm for variable valve actuation [C], 2010

[21] GuzzellaL, OnderC HIntroduction to modeling and control of internal combustion engine systems [M], 2004BerlinSpringer36

[22] ChauvinJ, PetitN, RouchonP, CordeG, VigildCAir path estimation on diesel HCCI engine [C], 2006

[23] LeroyT, ChauvinJ. Control-oriented aspirated masses model for variable-valve-actuation engines [J]. Control Engineering Practice, 2013, 21: 1744-1755

[24] IsermannR, HafnerM. Mechatronic combustion engines: From modeling to optimal control [J]. Eurpean Journal of Control, 2001, 7(2/3): 220-247

[25] LiF, ZhangJ, OkoE, WangM. Modelling of a post-combustion CO₂ capture process using neural networks [J]. Fuel, 2015, 151: 156-163

[26] HafnerM, SchulerM, NellesO, IsermannR. Fast neural networks for diesel engine control design [J]. Control Engineering Practice, 2000, 8: 11-21

[27] SvečkoR, KusićD. Feedforward neural network position control of a piezoelectric actuator based on a BAT search algorithm [J]. Expert Systems with Applications, 2015, 42: 5416-5423

[28] BenA J, SaidiL, MouelhiA, Chebel-MorelloB, FnaiechF. Linear feature selection and classification using PNN and SFAM neural networks for a nearly online diagnosis of bearing naturally progressing degradations [J]. Engineering Applications of Artificial Intelligence, 2015, 42: 67-81

[29] SharkeyA J C, ChandrothG O, SharkeyN E. A multi-net system for the fault diagnosis of a diesel engine [J]. Neural Computing Applications, 2000, 9(2): 152-160

[30] WangH, GaoJ, JiangZ, ZhangJ. Rotating machinery fault diagnosis based on EEMD time-frequency energy and SOM nural ntwork [J]. Arabian Journal for Science and Engineering, 2014, 39(6): 5207-5217