Diesel Engine Combustion Control Based on Cerebellar Model Articulation Controller (CMAC) in Feedback Error Learning

Xinyu Zhang, Makoto Eguchi, Hiromitsu Ohmori

Research output: Contribution to journalArticle

Abstract

The trend started in 1997 with the introduction of common rail injection and after some protocols set new targets for overall CO2 emissions. As the diesel engine emits less CO2 than its gasoline counterpart, it kept conquering more and more market shares. Conventional diesel engine control design is mainly based on the maps techniques which required too much time, money and human resources under the number of experiments under various environmental conditions. This makes increasing system complexity. In our authors group, we have proposed that the control structure has the feedback error learning, two-degree-of-freedom controller configuration, with advanced neural networks (NNs) as the feedforward controller along the model-based control method. On the other hand, a cerebellar model articulation controller (CMAC) is a non-fully connected perceptron like associative memory network with overlapping receptive fields, which is used to resolve problems that involve rapid growth and the learning difficulty. Then CMACs have the advantages of good generalization capability, fast learning ability, and simple computation. To our best knowledge, this is new introduce the cerebellar model articulation controller (CMAC) for the control diesel engine combustion control. The effectiveness of the proposed method will be confirmed through numerical simulations based on the Tokyo University diesel engine model with triple fuel injections.

Original languageEnglish
Pages (from-to)516-521
Number of pages6
JournalIFAC-PapersOnLine
Volume51
Issue number31
DOIs
Publication statusPublished - 2018 Jan 1

Fingerprint

Diesel engines
Feedback
Controllers
Neural networks
Fuel injection
Gasoline
Rails
Personnel
Data storage equipment
Computer simulation
Experiments

Keywords

  • CMAC
  • Combustion Control
  • Control Design
  • Engine Control
  • FEL
  • Inverse system
  • Robust adaptive control
  • Two-degree-of-freedom control system

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

Diesel Engine Combustion Control Based on Cerebellar Model Articulation Controller (CMAC) in Feedback Error Learning. / Zhang, Xinyu; Eguchi, Makoto; Ohmori, Hiromitsu.

In: IFAC-PapersOnLine, Vol. 51, No. 31, 01.01.2018, p. 516-521.

Research output: Contribution to journalArticle

@article{6e73e2854ab74c4aa30bb76cc8f2b1d9,
title = "Diesel Engine Combustion Control Based on Cerebellar Model Articulation Controller (CMAC) in Feedback Error Learning",
abstract = "The trend started in 1997 with the introduction of common rail injection and after some protocols set new targets for overall CO2 emissions. As the diesel engine emits less CO2 than its gasoline counterpart, it kept conquering more and more market shares. Conventional diesel engine control design is mainly based on the maps techniques which required too much time, money and human resources under the number of experiments under various environmental conditions. This makes increasing system complexity. In our authors group, we have proposed that the control structure has the feedback error learning, two-degree-of-freedom controller configuration, with advanced neural networks (NNs) as the feedforward controller along the model-based control method. On the other hand, a cerebellar model articulation controller (CMAC) is a non-fully connected perceptron like associative memory network with overlapping receptive fields, which is used to resolve problems that involve rapid growth and the learning difficulty. Then CMACs have the advantages of good generalization capability, fast learning ability, and simple computation. To our best knowledge, this is new introduce the cerebellar model articulation controller (CMAC) for the control diesel engine combustion control. The effectiveness of the proposed method will be confirmed through numerical simulations based on the Tokyo University diesel engine model with triple fuel injections.",
keywords = "CMAC, Combustion Control, Control Design, Engine Control, FEL, Inverse system, Robust adaptive control, Two-degree-of-freedom control system",
author = "Xinyu Zhang and Makoto Eguchi and Hiromitsu Ohmori",
year = "2018",
month = "1",
day = "1",
doi = "10.1016/j.ifacol.2018.10.112",
language = "English",
volume = "51",
pages = "516--521",
journal = "IFAC-PapersOnLine",
issn = "2405-8963",
publisher = "IFAC Secretariat",
number = "31",

}

TY - JOUR

T1 - Diesel Engine Combustion Control Based on Cerebellar Model Articulation Controller (CMAC) in Feedback Error Learning

AU - Zhang, Xinyu

AU - Eguchi, Makoto

AU - Ohmori, Hiromitsu

PY - 2018/1/1

Y1 - 2018/1/1

N2 - The trend started in 1997 with the introduction of common rail injection and after some protocols set new targets for overall CO2 emissions. As the diesel engine emits less CO2 than its gasoline counterpart, it kept conquering more and more market shares. Conventional diesel engine control design is mainly based on the maps techniques which required too much time, money and human resources under the number of experiments under various environmental conditions. This makes increasing system complexity. In our authors group, we have proposed that the control structure has the feedback error learning, two-degree-of-freedom controller configuration, with advanced neural networks (NNs) as the feedforward controller along the model-based control method. On the other hand, a cerebellar model articulation controller (CMAC) is a non-fully connected perceptron like associative memory network with overlapping receptive fields, which is used to resolve problems that involve rapid growth and the learning difficulty. Then CMACs have the advantages of good generalization capability, fast learning ability, and simple computation. To our best knowledge, this is new introduce the cerebellar model articulation controller (CMAC) for the control diesel engine combustion control. The effectiveness of the proposed method will be confirmed through numerical simulations based on the Tokyo University diesel engine model with triple fuel injections.

AB - The trend started in 1997 with the introduction of common rail injection and after some protocols set new targets for overall CO2 emissions. As the diesel engine emits less CO2 than its gasoline counterpart, it kept conquering more and more market shares. Conventional diesel engine control design is mainly based on the maps techniques which required too much time, money and human resources under the number of experiments under various environmental conditions. This makes increasing system complexity. In our authors group, we have proposed that the control structure has the feedback error learning, two-degree-of-freedom controller configuration, with advanced neural networks (NNs) as the feedforward controller along the model-based control method. On the other hand, a cerebellar model articulation controller (CMAC) is a non-fully connected perceptron like associative memory network with overlapping receptive fields, which is used to resolve problems that involve rapid growth and the learning difficulty. Then CMACs have the advantages of good generalization capability, fast learning ability, and simple computation. To our best knowledge, this is new introduce the cerebellar model articulation controller (CMAC) for the control diesel engine combustion control. The effectiveness of the proposed method will be confirmed through numerical simulations based on the Tokyo University diesel engine model with triple fuel injections.

KW - CMAC

KW - Combustion Control

KW - Control Design

KW - Engine Control

KW - FEL

KW - Inverse system

KW - Robust adaptive control

KW - Two-degree-of-freedom control system

UR - http://www.scopus.com/inward/record.url?scp=85056150881&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056150881&partnerID=8YFLogxK

U2 - 10.1016/j.ifacol.2018.10.112

DO - 10.1016/j.ifacol.2018.10.112

M3 - Article

AN - SCOPUS:85056150881

VL - 51

SP - 516

EP - 521

JO - IFAC-PapersOnLine

JF - IFAC-PapersOnLine

SN - 2405-8963

IS - 31

ER -