International Journal of Automotive Technology

, Volume 19, Issue 4, pp 635–642 | Cite as

Gaussian Process Regression Feedforward Controller for Diesel Engine Airpath

  • Volkan Aran
  • Mustafa UnelEmail author


Gaussian Process Regression (GPR) provides emerging modeling opportunities for diesel engine control. Recent serial production hardwares increase online calculation capabilities of the engine control units. This paper presents a GPR modeling for feedforward part of the diesel engine airpath controller. A variable geotmetry turbine (VGT) and an exhaust gas recirculation (EGR) valve outer loop controllers are developed. The GPR feedforward models are trained with a series of mapping data with physically related inputs instead of speed and torque utilized in conventional control schemes. A physical model-free and calibratable controller structure is proposed for hardware flexibility. Furthermore, a discrete time sliding mode controller (SMC) is utilized as a feedback controller. Feedforward modeling and the subsequent airpath controller (SMC+GPR) are implemented on the physical diesel engine model and the performance of the proposed controller is compared with a conventional PID controller with table based feedforward.

Key Words

Gaussian process regression Feedforward control Discrete time sliding mode control Airpath control 





intake manifold pressure


exhaust manifold pressure


compressor power


ambient pressure


ideal gas constant


intake manifold temperature


exhaust manifold temperature


ambient temperature


intake manifold volume


turbocharger time constant


compressor mass airflow


exhaust gas recirculation mass flow


engine inlet gas mass flow


turbine inlet gas mass flow


fuel mass flow


isentropic compressor efficiency


turbine total efficiency


specific heat of air


feedforward control term


feedback control component


exhaust gas recirculation valve area


exhaust gas enthalpy


controlled input 1, area of EGR


controlled input 2, area of VGT


isentropic ratio


VGT vane position


EGR valve position


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Aran, V. and Unel, M. (2016). Feedforward mapping for engine control. Proc. IEEE Industrial Electronics Society, IECON Annual Conf., 154–159Google Scholar
  2. Bischoff, B., Nguyen-Tuong, D., Koller, T., Markert, H. and Knoll, A. (2013). Learning throttle valve control using policy search. Lecture Notes in Computer Science, 8188, 49–64CrossRefGoogle Scholar
  3. Calandra, R., Peters, J., Rasmussen, C. E. and Deisenroth, M. P. (2014). Manifold gaussian processes for regression. arXiv: 1402.5876v4 [stat.ML].Google Scholar
  4. Heywood, J. (2000). Internal Combustion Engine Fundamentals. McGraw-Hill. New York, USA.Google Scholar
  5. Jankovic, M. and Kolmanovsky, I. (1998). Robust nonlinear controller for turbocharged diesel engines. Proc. American Control Conf., Philadelphia, Pennsylvania, USA.Google Scholar
  6. Jung, M., Glover, K. and Christen, U. (2005). Comparison of uncertainty param-eterisations for H infinity robust control of turbocharged diesel engines. Control Engineering Practice 13, 1, 15–25CrossRefGoogle Scholar
  7. Kolmanovsky, I. (1997). Issues in modelling and control of intake flow in variable geometry turbocharged engines. Proc. 18th IFIP Conf. System Modeling and Optimization, 436–445Google Scholar
  8. Mancini, G., Asprion, J., Cavina, N., Onder, C. and Guzzella, L. (2014). Dynamic feedforward control of a diesel engine based on optimal transient compensation maps. Energies 7, 8, 5400–5424CrossRefGoogle Scholar
  9. Nieuwstadt, M. J., Kolmanovsky, I. V., Moraal, P. E., Stefanopoulou, A. and Jankovic, M. (2000). EGR-VGT control schemes: Experimental comparison for a highspeed diesel engine. IEEE Control Systems 20, 3, 63–79CrossRefGoogle Scholar
  10. Rasmussen, C. E. and Williams, C. (2006). Gaussian Processes for Machine Learning. MIT Press. Cambridge, Massachusetts, USA.zbMATHGoogle Scholar
  11. Sabanovic, A., Sabanovic, N. and Jezernik, K. (2003). Sliding modes in sampled data systems. Automatika: J. Control, Measurement, Electronics, Computing and Communications 44, 3–4, 163–181zbMATHGoogle Scholar
  12. Schreiter, J., Nguyen-Tuong, D. and Toussaint, M. (2016). Efficient sparsification for Gaussian process regression. Neurocomputing, 192, 29–37CrossRefGoogle Scholar
  13. Tietze, N. (2015). Model-based Calibration of Engine Control Units Using Gaussian Process Regression. Ph. D. Dissertation. Technical University Darmstadt. Darmstadt, Germany.Google Scholar
  14. UN ECE (2013). E/ECE/324/Rev.1/Add.48/Rev.6-E/ECE/TRANS/505/Rev.1/Add.48/Rev.Google Scholar
  15. Unver, B., Koyuncuoglu, Y., Gokasan, M. and Bogosyan, S. (2016). Modeling and validation of turbocharged diesel engine airpath and combustion systems. Int. J. Automotive Technology 17, 1, 13–34CrossRefGoogle Scholar
  16. Wahlstrom, J. and Eriksson, L. (2011). Modelling diesel engines with a variable-geometry turbocharger and exhaust gas recirculation by optimization of model parameters for capturing non-linear system dynamics. Proc. Institution of Mechanical Engineers, Part D: J. Automobile Engineering 225, 7, 960–986Google Scholar
  17. Wahlstrom, J. and Eriksson, L. (2013). Output selection and its implications for MPC of EGR and VGT in diesel engines. IEEE Trans. Control Systems Technology 21, 3, 932–940CrossRefGoogle Scholar

Copyright information

© The Korean Society of Automotive Engineers and Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Sancaktepe Engineering CenterFORD OTOSAN, Akpınar Mah. SancaktepeIstanbulTurkey
  2. 2.Integrated Manufacturing Technologies Research and Application CenterSabanci UniversityIstanbulTurkey
  3. 3.Faculty of Engineering and Natural SciencesSabancı UniversityIstanbulTurkey

Personalised recommendations