A RBF neural network model for cylinder pressure reconstruction in internal combustion engines

F. Gu, P. J. Jacob, A. D. Ball

Research output: Contribution to journalConference article

3 Citations (Scopus)

Abstract

This paper proposes the use of a non-parametric RBF neural network to model the relationship between the instantaneous angular velocity of the crankshaft and the pressure in the cylinders of an internal combustion engine. The structure of the model and the training procedure of the networ is outlined. The application of the model is demonstrated on a four cylinder DI diesel engine with data from a wide range of speed and load settings. The prediction capabilities of the model once trained can be validated against measured data. An example is given of the application of this model to aid in the diagnosis of a fault in one of the cylinders.

Original languageEnglish
Pages (from-to)4/1-411
JournalIEE Colloquium (Digest)
Volume1996
Issue number260
DOIs
Publication statusPublished - 1 Dec 1996
Externally publishedYes
EventProceedings of the 1997 IEE Colloquium on Modelling and Signal Processing for Fault Diagnosis - London, UK
Duration: 18 Sep 199618 Sep 1996

Fingerprint

Engine cylinders
Internal combustion engines
Neural networks
Crankshafts
Angular velocity
Diesel engines

Cite this

@article{b94823e38cf24e3d8177b6ffbae6d36a,
title = "A RBF neural network model for cylinder pressure reconstruction in internal combustion engines",
abstract = "This paper proposes the use of a non-parametric RBF neural network to model the relationship between the instantaneous angular velocity of the crankshaft and the pressure in the cylinders of an internal combustion engine. The structure of the model and the training procedure of the networ is outlined. The application of the model is demonstrated on a four cylinder DI diesel engine with data from a wide range of speed and load settings. The prediction capabilities of the model once trained can be validated against measured data. An example is given of the application of this model to aid in the diagnosis of a fault in one of the cylinders.",
keywords = "internal combustion engines, waveform analysis, angukar velocity measurement, fault diagnosis, pattern recognition, feedforward neural nets, magnetic sensors",
author = "F. Gu and Jacob, {P. J.} and Ball, {A. D.}",
year = "1996",
month = "12",
day = "1",
doi = "10.1049/ic:19961374",
language = "English",
volume = "1996",
pages = "4/1--411",
journal = "IEE Colloquium (Digest)",
issn = "0963-3308",
publisher = "Institute of Electrical Engineers",
number = "260",

}

A RBF neural network model for cylinder pressure reconstruction in internal combustion engines. / Gu, F.; Jacob, P. J.; Ball, A. D.

In: IEE Colloquium (Digest), Vol. 1996, No. 260, 01.12.1996, p. 4/1-411.

Research output: Contribution to journalConference article

TY - JOUR

T1 - A RBF neural network model for cylinder pressure reconstruction in internal combustion engines

AU - Gu, F.

AU - Jacob, P. J.

AU - Ball, A. D.

PY - 1996/12/1

Y1 - 1996/12/1

N2 - This paper proposes the use of a non-parametric RBF neural network to model the relationship between the instantaneous angular velocity of the crankshaft and the pressure in the cylinders of an internal combustion engine. The structure of the model and the training procedure of the networ is outlined. The application of the model is demonstrated on a four cylinder DI diesel engine with data from a wide range of speed and load settings. The prediction capabilities of the model once trained can be validated against measured data. An example is given of the application of this model to aid in the diagnosis of a fault in one of the cylinders.

AB - This paper proposes the use of a non-parametric RBF neural network to model the relationship between the instantaneous angular velocity of the crankshaft and the pressure in the cylinders of an internal combustion engine. The structure of the model and the training procedure of the networ is outlined. The application of the model is demonstrated on a four cylinder DI diesel engine with data from a wide range of speed and load settings. The prediction capabilities of the model once trained can be validated against measured data. An example is given of the application of this model to aid in the diagnosis of a fault in one of the cylinders.

KW - internal combustion engines

KW - waveform analysis

KW - angukar velocity measurement

KW - fault diagnosis

KW - pattern recognition

KW - feedforward neural nets

KW - magnetic sensors

UR - http://www.scopus.com/inward/record.url?scp=30144440395&partnerID=8YFLogxK

U2 - 10.1049/ic:19961374

DO - 10.1049/ic:19961374

M3 - Conference article

VL - 1996

SP - 4/1-411

JO - IEE Colloquium (Digest)

JF - IEE Colloquium (Digest)

SN - 0963-3308

IS - 260

ER -