Learning Based Approaches to Engine Mapping and Calibration Optimization

  • Dimitar Filev
  • Yan Wang
  • Ilya Kolmanovsky
Part of the Lecture Notes in Control and Information Sciences book series (LNCIS, volume 455)


In this chapter we consider a class of optimization problems arising in the process of automotive engine mapping and calibration. Fast optimization algorithms applicable to high fidelity simulation models or experimental engines can reduce the time, effort and costs required for calibration. Our approach to these problems is based on iterations between local model identification and calibration parameter (set-points and actuator settings) improvements based on the learned surrogate model. Several approaches to algorithm implementation are considered. In the first approach, the surrogate model is defined in a linear incremental form and its identification reduces to Jacobian Learning. Then quadratic programming is applied to adjust the calibration parameters. In the second approach, we consider a predictor-corrector algorithm that estimates the change in the minimizer based on changing operating conditions before correcting it. Case studies are described that illustrate the applications of algorithms.


Engine Speed Engine Load Engine Model Brake Specific Fuel Consumption Engine Mapping 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



The authors wish to thank Rohit Gupta and Heyongjun Park of the University of Michigan and John Michelini of Ford Research and Advanced Engineering for their contributions to research reflected in this chapter.


  1. 1.
    Astrom K, Wittenmark B (1989) Adaptive control. Addison-Wesley, ReadingGoogle Scholar
  2. 2.
    Buskens C, Maurer H (2001) Sensitivity analysis and real-time optimization of parametric nonlinear programming problems. In: Grotschel M, Krumke M, Rambau J (eds) Online optimization of large scale systems. Springer, BerlinGoogle Scholar
  3. 3.
    Cameo Powertrain Calibration Tool (2013).
  4. 4.
    Chen W-K (1993) Linear networks and systems. Wadsworth, Belmont, pp 123–135Google Scholar
  5. 5.
    Di Cairano S, Liang W, Kolmanovsky IV, Kuang ML, Phillips AM (2013) Power smoothing energy management with applications to a series hybrid powertrain. IEEE Trans Control Syst Technol 21(6):2091–2103Google Scholar
  6. 6.
    Fiacco AV (1983) Introduction to sensitivity and stability analysis in nonlinear programming. Mathematics in science and engineering, vol 165. Academic Press, New YorkGoogle Scholar
  7. 7.
    Filev D, Larsson T, Ma L (2000) Intelligent control for automotive manufacturing—Rule based guided adaptation. In: Proceedings of IEEE conference on IECON’00, Nagoya, Japan, pp 283–288Google Scholar
  8. 8.
    Gorinevsky D (1997) An approach to parametric nonlinear least square optimization and application to task-level control. IEEE Trans Autom Control 42(7):912–927CrossRefzbMATHMathSciNetGoogle Scholar
  9. 9.
    Guddat J, Vasquez FG, Jongen HT (eds) (1990) Parametric optimization: singularities, path following and jumps. Wiley, New YorkGoogle Scholar
  10. 10.
    Gupta R, Kolmanovsky IV, Wang Y, Filev DP (2012) On-board learning-based fuel consumption optimization in series hybrid electric vehicles. In: Proceedings of 2012 American control conference, Montreal, Canada, pp 1308–1313Google Scholar
  11. 11.
    Haskara I, Ozguner U, Winkelman J (2000) Extremum control for optimal operating point determination and set-point optimization via sliding modes. ASME J Dyn Syst, Meas Control 122:719–724Google Scholar
  12. 12.
    Hrovat D, Jankovic M, Kolmanovsky I, Magner S, Yanakiev D (2010) Powertain control. In: Levine W (ed.) IEEE Controls Handbook, 2nd edn. CRC Press, Boca RatonGoogle Scholar
  13. 13.
    Jankovic M, Magner S (2004) Optimization and scheduling for automotive powertrains. In: Proceedings of the 2004 American control conference, pp 4054–4059Google Scholar
  14. 14.
    Jankovic M, Magner S (2006) Fuel economy optimization in automotive engines. In: Proceedings of the 2006 American control conference, Minneapolis, MN, pp 1191–1196Google Scholar
  15. 15.
    Konev A, Lezhnev L, Kolmanovsky IV (2006) Control strategy optimization for a series hybrid vehicle. SAE, World Congress, Detroit, MIGoogle Scholar
  16. 16.
    Liung L (1987) System identification—Theory for user. Prentice Hall, Englewood CliffsGoogle Scholar
  17. 17.
    Lyantsev OD, Breikin TV, Kulikov GG, Arkov VY (1993) On-line optimization of aero engine control system. Automatica 39:2115–2121CrossRefMathSciNetGoogle Scholar
  18. 18.
    Malikopoulos A, Papalambros PY, Assanis DN (2007) A learning algorithm for optimal internal combustion engine calibration in real-time. In: Proceedings of the ASME 2007 international design engineering technical conference and computers and information in engineering conference, IDETC/CIE, Las Vegas, NevadaGoogle Scholar
  19. 19.
    Malikopoulos A, Papalambros PY, Assanis DN (2007) Real-time, self-learning optimization of diesel engine calibration. In: Proceedings of 2007 fall technical conference of the ASME internal combustion engine division, ICEF2007-1603, Charleston, South Carolina, USA, 14–17 Oct 2007Google Scholar
  20. 20.
    Pan Y, Ozguner U (2004) Extremum seeking control of a variable valve timing engine. In: IFAC symposium on advances in automotive control, Salerno, Italy, pp 173–178Google Scholar
  21. 21.
    Popovic D, Jankovic M, Magner S, Teel A (2006) Extremum seeking methods for optimization of variable cam timing engine operation. IEEE Trans Control Syst Technol 14(3):398–407CrossRefGoogle Scholar
  22. 22.
    Quoc TD, Savorgnan C, Diehl M (2012) Adjoint-based predictor-corrector sequential convex programming for parametric nonlinear optimization. SIAM J Optim 22(4):1258–1284CrossRefzbMATHMathSciNetGoogle Scholar
  23. 23.
    Ryan J, Speyer J (2010) Peak-seeking control using gradient and hessian estimates. In: Proceedings of American control conference, pp 611–616Google Scholar
  24. 24.
    Tychonoff AN, Arsenin VY (1977) Solution of Ill-posed problems. Winston and Sons, WashingtonGoogle Scholar
  25. 25.
    Zhang C, Ordonez R (2006) Non-gradient extremum seeking control of feedback linearizable systems with application to ABS design. In: Proceedings of the 45th IEEE conference on decision and control, San Diego, CA, pp 6666–6671Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  1. 1.Research and Advanced Engineering, Ford Motor CompanyDearbornUSA
  2. 2.Department of Aerospace EngineeringThe University of MichiganAnn ArborUSA

Personalised recommendations