Neural network control for reducing engine speed fluctuation at idle

Dae Eun Kim, Jaehong Park

Research output: Contribution to journalConference article

8 Citations (Scopus)

Abstract

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
JournalProceedings of the IEEE International Conference on Systems, Man and Cybernetics
Volume4
Publication statusPublished - 1999 Dec 1
Event1999 IEEE International Conference on Systems, Man, and Cybernetics 'Human Communication and Cybernetics' - Tokyo, Jpn
Duration: 1999 Oct 121999 Oct 15

Fingerprint

Engines
Neural networks
Engine cylinders
Sensor arrays
Speed control
Electric sparks
Neurons
Ignition
Torque
Genetic algorithms
Control systems

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Hardware and Architecture

Cite this

@article{decbf670ce544b0ebbceaa03301931ef,
title = "Neural network control for reducing engine speed fluctuation at idle",
abstract = "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.",
author = "Kim, {Dae Eun} and Jaehong Park",
year = "1999",
month = "12",
day = "1",
language = "English",
volume = "4",
journal = "Proceedings of the IEEE International Conference on Systems, Man and Cybernetics",
issn = "0884-3627",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Neural network control for reducing engine speed fluctuation at idle. / Kim, Dae Eun; Park, Jaehong.

In: Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, Vol. 4, 01.12.1999.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Neural network control for reducing engine speed fluctuation at idle

AU - Kim, Dae Eun

AU - Park, Jaehong

PY - 1999/12/1

Y1 - 1999/12/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=0033329385&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033329385&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0033329385

VL - 4

JO - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

JF - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

SN - 0884-3627

ER -