A Neural Network Based Soft Sensors Scheme for Spark-Ignitions Engines

Conference paper

Abstract

With the coming of massive application on autonomous vehicles, the safeness has been one of the features with highest development priority, which are considered in the design of automotive control systems. The development of intelligent sensors is an effective way to achieve this goal. For spark-ignition engines, the regualation of air fuel ratio and the control of engine speed are the keys to obtain reliable engine performance. This paper proposes a neural network (NN) based soft sensor scheme for air/fuel ratio sensor and crankshaft speed sensor, which are two important measurements for the control in spark-ignition engines. The modeling results show that satisfactory modeling performance can be obtained with moderate computational load.

Keywords

Air fuel ratio Automotive control systems Engine performance Intelligent sensors Neural networks Spark-ignition 

Notes

Acknowledgements

This research was financially supported by the Centre for Smart Grid and Information Convergence (CeSGIC) at Xian Jiaotong-Liverpool University. The authors would like to thank all the parties concerned.

References

  1. 1.
    Y. Zhai, K.L. Man, S. Lee, F. Xue, A neural network based soft sensor for air fuel ratio dynamics in SI engines lecture notes in engineering and computer science, in Proceedings of the International MultiConference of Engineers and Computer Scientists, (Hong Kong, 2017), 15–17 March 2017, pp. 719–722Google Scholar
  2. 2.
    Institution of mechanical engineers, ford reveals autonomous taxi plan, http://www.imeche.org/news/news-article/ford-reveals-autonomous-taxi-plan
  3. 3.
    AutoblogGreen, Tesla D is, as expected, an AWD Model S but new autopilot features surprise, http://www.autoblog.com/2014/10/09/tesla-d-awd-model-s-new-autopilot-surprise/
  4. 4.
    W. Zhu, J. Miao, J. Hu, L. Qing, Vehicle detection in driving simulation using extreme learning machine. Neurocomput. 128, 160–165 (2014), https://doi.org/10.1016/j.neucom.2013.05.052
  5. 5.
    P. Reiner, B.M. Wilamowski, Efficient incremental construction of RBF networks using quasi-gradient method, in Special Issue on Information Processing and Machine Learning for Applications of Engineering, Vol. 150, Part B, 20 Feb 2015, pp. 349–356Google Scholar
  6. 6.
    C. Lebreton, M. Benne, C. Damour, N. Yousfi-Steiner, B. Grondin-Perez, D, Hissel, J.-P. Chabriat, Fault tolerant control strategy applied to pemfc water management. Int. J. Hydrogen Energy 40, 10636–10646 (2015)Google Scholar
  7. 7.
    J. Jiang, X. Yu, Fault-tolerant control systems: a comparative study between active and passive approaches. Ann. Rev. Control 36, 60–72 (2012)Google Scholar
  8. 8.
    E. Hendricks, D. Engler, M.A Fam, Generic mean value engine model for spark ignition engines, in Proceedings of 41st Simulation Conference, (DTU Lyngby, Denmark, SIMS, 2000)Google Scholar
  9. 9.
    C. Manzie, M. Palaniswami, H. Watson, Gaussian networks for fuel injection control. Proc. Inst. Mech. Eng. J. Automobile Eng. 215(10), 1053–1068 (2001)Google Scholar
  10. 10.
    C. Manzie, M. Palaniswami, D. Ralph, H. Watson, X. Yi, Model predictive control of a fuel injection system with a radial basis function network observer. J. Dyn. Syst. Measur. Control Trans. ASME 124(4), 648–658 (2002)Google Scholar
  11. 11.
    O. Nelles, Nonlinear System Identification (Springer, 2001)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  • Yujia Zhai
    • 1
  • Ka Lok Man
    • 2
  • Sanghyuk Lee
    • 1
  • Fei Xue
    • 1
  1. 1.Department of Electrical and Electronic EngineeringXi’an Jiaotong-Liverpool UniversitySuzhouChina
  2. 2.Department of Computer ScienceXi’an Jiaotong-Liverpool UniversitySuzhouChina

Personalised recommendations