Residual generation and statistical pattern recognition for engine misfire diagnostics

Andrew W. Osburn; Theodore M. Kostek; Matthew A. Franchek

doi:10.1016/j.ymssp.2005.06.002

Residual generation and statistical pattern recognition for engine misfire diagnostics

Andrew W. Osburn, Theodore M. Kostek, Matthew A. Franchek

Research output: Contribution to journal › Article › peer-review

35 Scopus citations

Abstract

Methods for diagnosing misfire in internal combustion engines are presented in this paper. Crank-angle domain digital filters are used to extract features from the measured engine speed signal that are characteristic of misfire. Features for intermittent and continuous misfires are developed separately, since the engine speed responses for intermittent and continuous misfires are distinctly different. Also, the influence of crankshaft torsional vibration and repeatable measurement errors must be addressed differently in each case. The outputs from the digital filters serve as inputs to a pattern recognition network based on linear parametric classifiers. Experimental results from implementation on a Ford 4.6L V-8 engine are provided.

Original language	English (US)
Pages (from-to)	2232-2258
Number of pages	27
Journal	Mechanical Systems and Signal Processing
Volume	20
Issue number	8
DOIs	https://doi.org/10.1016/j.ymssp.2005.06.002
State	Published - Nov 2006

Keywords

Internal combustion engines
Misfire diagnostics
Statistical pattern recognition

ASJC Scopus subject areas

Signal Processing
Mechanical Engineering

Access to Document

10.1016/j.ymssp.2005.06.002

Cite this

@article{0a737680336146148893a707b476e393,

title = "Residual generation and statistical pattern recognition for engine misfire diagnostics",

abstract = "Methods for diagnosing misfire in internal combustion engines are presented in this paper. Crank-angle domain digital filters are used to extract features from the measured engine speed signal that are characteristic of misfire. Features for intermittent and continuous misfires are developed separately, since the engine speed responses for intermittent and continuous misfires are distinctly different. Also, the influence of crankshaft torsional vibration and repeatable measurement errors must be addressed differently in each case. The outputs from the digital filters serve as inputs to a pattern recognition network based on linear parametric classifiers. Experimental results from implementation on a Ford 4.6L V-8 engine are provided.",

keywords = "Internal combustion engines, Misfire diagnostics, Statistical pattern recognition",

author = "Osburn, {Andrew W.} and Kostek, {Theodore M.} and Franchek, {Matthew A.}",

year = "2006",

month = nov,

doi = "10.1016/j.ymssp.2005.06.002",

language = "English (US)",

volume = "20",

pages = "2232--2258",

journal = "Mechanical Systems and Signal Processing",

issn = "0888-3270",

publisher = "Academic Press",

number = "8",

}

TY - JOUR

T1 - Residual generation and statistical pattern recognition for engine misfire diagnostics

AU - Osburn, Andrew W.

AU - Kostek, Theodore M.

AU - Franchek, Matthew A.

PY - 2006/11

Y1 - 2006/11

N2 - Methods for diagnosing misfire in internal combustion engines are presented in this paper. Crank-angle domain digital filters are used to extract features from the measured engine speed signal that are characteristic of misfire. Features for intermittent and continuous misfires are developed separately, since the engine speed responses for intermittent and continuous misfires are distinctly different. Also, the influence of crankshaft torsional vibration and repeatable measurement errors must be addressed differently in each case. The outputs from the digital filters serve as inputs to a pattern recognition network based on linear parametric classifiers. Experimental results from implementation on a Ford 4.6L V-8 engine are provided.

AB - Methods for diagnosing misfire in internal combustion engines are presented in this paper. Crank-angle domain digital filters are used to extract features from the measured engine speed signal that are characteristic of misfire. Features for intermittent and continuous misfires are developed separately, since the engine speed responses for intermittent and continuous misfires are distinctly different. Also, the influence of crankshaft torsional vibration and repeatable measurement errors must be addressed differently in each case. The outputs from the digital filters serve as inputs to a pattern recognition network based on linear parametric classifiers. Experimental results from implementation on a Ford 4.6L V-8 engine are provided.

KW - Internal combustion engines

KW - Misfire diagnostics

KW - Statistical pattern recognition

UR - http://www.scopus.com/inward/record.url?scp=33746985993&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33746985993&partnerID=8YFLogxK

U2 - 10.1016/j.ymssp.2005.06.002

DO - 10.1016/j.ymssp.2005.06.002

M3 - Article

AN - SCOPUS:33746985993

SN - 0888-3270

VL - 20

SP - 2232

EP - 2258

JO - Mechanical Systems and Signal Processing

JF - Mechanical Systems and Signal Processing

IS - 8

ER -

Residual generation and statistical pattern recognition for engine misfire diagnostics

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this