Neural network control for reducing engine speed fluctuation at idle

Dae Eun Kim, Jaehong Park

Research output: Contribution to journalConference articlepeer-review

11 Citations (Scopus)


Long term average idle speed control has been studied in most of engine idle control systems in automotive engines, but they allow undesirable short-term engine speed fluctuation even under steady idle conditions. Actually the difference in the torque production among cylinders influences the idle stability by making the fluctuation of engine speed ripples. In this paper, we suggest that the control of the spark ignition timing for each cylinder based on neural network reduce the unbalanced combustion among cylinders, and maintain uniform and stable engine speed. We apply genetic algorithm to neural network structure with oscillatory neurons in sensor array in order to decrease the engine speed fluctuation efficiently.

Original languageEnglish
Pages (from-to)IV-629 - IV-634
JournalProceedings of the IEEE International Conference on Systems, Man and Cybernetics
Publication statusPublished - 1999
Event1999 IEEE International Conference on Systems, Man, and Cybernetics 'Human Communication and Cybernetics' - Tokyo, Jpn
Duration: 1999 Oct 121999 Oct 15

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Hardware and Architecture


Dive into the research topics of 'Neural network control for reducing engine speed fluctuation at idle'. Together they form a unique fingerprint.

Cite this