Autoignition model optimized based on simple artificial brain

Ken Naitoh, Tairo Ise

Research output: Contribution to journalConference article

Abstract

A well-known auto-ignition model for gasoline, which was proposed by Halstead et al, is automatically optimized on computers by using a simple artificial brain including genetic algorithm as learning theory and an intuition model. Arbitrary constants inside the mathematical equations of highly-nonlinear chemical reaction processes can be fitted by using the experimental time-evolutions of several components. Thus, ignition delay, the interval from compression start to ignition occurrence, can be accurately calculated for different types of fuel, production regions, and engine test benches. The intuition model clarifies whether the arbitrary constants are optimized or not. The present approach will be important for building up several types of virtual engines, which are based on zero-dimensional thermodynamic models, ensemble-averaged flow simulators, and large eddy simulation (LES).

Original languageEnglish
JournalSAE Technical Papers
DOIs
Publication statusPublished - 2003 Jan 1
EventPowertrain and Fluid Systems Conference and Exhibition - Pittsburgh, PA, United States
Duration: 2003 Oct 272003 Oct 30

Fingerprint

Brain
Ignition
Engines
Large eddy simulation
Gasoline
Chemical reactions
Simulators
Genetic algorithms
Thermodynamics

ASJC Scopus subject areas

  • Automotive Engineering
  • Safety, Risk, Reliability and Quality
  • Pollution
  • Industrial and Manufacturing Engineering

Cite this

Autoignition model optimized based on simple artificial brain. / Naitoh, Ken; Ise, Tairo.

In: SAE Technical Papers, 01.01.2003.

Research output: Contribution to journalConference article

@article{ae98fc461ade46bdb6ee8d60042b1540,
title = "Autoignition model optimized based on simple artificial brain",
abstract = "A well-known auto-ignition model for gasoline, which was proposed by Halstead et al, is automatically optimized on computers by using a simple artificial brain including genetic algorithm as learning theory and an intuition model. Arbitrary constants inside the mathematical equations of highly-nonlinear chemical reaction processes can be fitted by using the experimental time-evolutions of several components. Thus, ignition delay, the interval from compression start to ignition occurrence, can be accurately calculated for different types of fuel, production regions, and engine test benches. The intuition model clarifies whether the arbitrary constants are optimized or not. The present approach will be important for building up several types of virtual engines, which are based on zero-dimensional thermodynamic models, ensemble-averaged flow simulators, and large eddy simulation (LES).",
author = "Ken Naitoh and Tairo Ise",
year = "2003",
month = "1",
day = "1",
doi = "10.4271/2003-01-3229",
language = "English",
journal = "SAE Technical Papers",
issn = "0148-7191",
publisher = "SAE International",

}

TY - JOUR

T1 - Autoignition model optimized based on simple artificial brain

AU - Naitoh, Ken

AU - Ise, Tairo

PY - 2003/1/1

Y1 - 2003/1/1

N2 - A well-known auto-ignition model for gasoline, which was proposed by Halstead et al, is automatically optimized on computers by using a simple artificial brain including genetic algorithm as learning theory and an intuition model. Arbitrary constants inside the mathematical equations of highly-nonlinear chemical reaction processes can be fitted by using the experimental time-evolutions of several components. Thus, ignition delay, the interval from compression start to ignition occurrence, can be accurately calculated for different types of fuel, production regions, and engine test benches. The intuition model clarifies whether the arbitrary constants are optimized or not. The present approach will be important for building up several types of virtual engines, which are based on zero-dimensional thermodynamic models, ensemble-averaged flow simulators, and large eddy simulation (LES).

AB - A well-known auto-ignition model for gasoline, which was proposed by Halstead et al, is automatically optimized on computers by using a simple artificial brain including genetic algorithm as learning theory and an intuition model. Arbitrary constants inside the mathematical equations of highly-nonlinear chemical reaction processes can be fitted by using the experimental time-evolutions of several components. Thus, ignition delay, the interval from compression start to ignition occurrence, can be accurately calculated for different types of fuel, production regions, and engine test benches. The intuition model clarifies whether the arbitrary constants are optimized or not. The present approach will be important for building up several types of virtual engines, which are based on zero-dimensional thermodynamic models, ensemble-averaged flow simulators, and large eddy simulation (LES).

UR - http://www.scopus.com/inward/record.url?scp=85072440879&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072440879&partnerID=8YFLogxK

U2 - 10.4271/2003-01-3229

DO - 10.4271/2003-01-3229

M3 - Conference article

JO - SAE Technical Papers

JF - SAE Technical Papers

SN - 0148-7191

ER -