Statistical pattern recognition for TWC diagnosis

Ted Kostek; Matthew Franchek

doi:10.4271/2005-01-1092

Statistical pattern recognition for TWC diagnosis

Ted Kostek, Matthew Franchek

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Ideas from statistical pattern recognition are applied to the problem of diagnosing degraded automotive three-way catalysts using oxygen sensors. A brief overview of statistical pattern recognition is given. A novel method of processing the oxygen sensor signals converts the time signals into ensembles of vectors. Using the tools of pattern recognition, the ensembles are described statistically, and classifiers are derived from the statistical descriptions. The resulting classifiers are tested against four different aging categories, and the performance is quantified via the operating characteristic. Techniques to achieve arbitrary levels of performance are discussed.

Original language	English
Title of host publication	SAE Technical Papers
DOIs	https://doi.org/10.4271/2005-01-1092
State	Published - Dec 1 2005
Event	2005 SAE World Congress - Detroit, MI, United States Duration: Apr 11 2005 → Apr 14 2005

Other

Other	2005 SAE World Congress
Country/Territory	United States
City	Detroit, MI
Period	4/11/05 → 4/14/05

ASJC Scopus subject areas

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

Access to Document

10.4271/2005-01-1092

Cite this

@inproceedings{4e539294d4084c73bfdd42d1202f0666,

title = "Statistical pattern recognition for TWC diagnosis",

abstract = "Ideas from statistical pattern recognition are applied to the problem of diagnosing degraded automotive three-way catalysts using oxygen sensors. A brief overview of statistical pattern recognition is given. A novel method of processing the oxygen sensor signals converts the time signals into ensembles of vectors. Using the tools of pattern recognition, the ensembles are described statistically, and classifiers are derived from the statistical descriptions. The resulting classifiers are tested against four different aging categories, and the performance is quantified via the operating characteristic. Techniques to achieve arbitrary levels of performance are discussed.",

author = "Ted Kostek and Matthew Franchek",

year = "2005",

month = dec,

day = "1",

doi = "10.4271/2005-01-1092",

language = "English",

booktitle = "SAE Technical Papers",

note = "null ; Conference date: 11-04-2005 Through 14-04-2005",

}

TY - GEN

T1 - Statistical pattern recognition for TWC diagnosis

AU - Kostek, Ted

AU - Franchek, Matthew

PY - 2005/12/1

Y1 - 2005/12/1

N2 - Ideas from statistical pattern recognition are applied to the problem of diagnosing degraded automotive three-way catalysts using oxygen sensors. A brief overview of statistical pattern recognition is given. A novel method of processing the oxygen sensor signals converts the time signals into ensembles of vectors. Using the tools of pattern recognition, the ensembles are described statistically, and classifiers are derived from the statistical descriptions. The resulting classifiers are tested against four different aging categories, and the performance is quantified via the operating characteristic. Techniques to achieve arbitrary levels of performance are discussed.

AB - Ideas from statistical pattern recognition are applied to the problem of diagnosing degraded automotive three-way catalysts using oxygen sensors. A brief overview of statistical pattern recognition is given. A novel method of processing the oxygen sensor signals converts the time signals into ensembles of vectors. Using the tools of pattern recognition, the ensembles are described statistically, and classifiers are derived from the statistical descriptions. The resulting classifiers are tested against four different aging categories, and the performance is quantified via the operating characteristic. Techniques to achieve arbitrary levels of performance are discussed.

UR - http://www.scopus.com/inward/record.url?scp=84877484904&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84877484904&partnerID=8YFLogxK

U2 - 10.4271/2005-01-1092

DO - 10.4271/2005-01-1092

M3 - Conference contribution

BT - SAE Technical Papers

Y2 - 11 April 2005 through 14 April 2005

ER -

Statistical pattern recognition for TWC diagnosis

Abstract

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this