An application of supervised multivariate control charts on a power plant data

Thuntee Sukchotrat; Seoung Bum Kim; Victoria C.P. Chen; Clint Carter; William Dockery; Robert Tapia

An application of supervised multivariate control charts on a power plant data

Thuntee Sukchotrat, Seoung Bum Kim, Victoria C.P. Chen, Clint Carter, William Dockery, Robert Tapia

Research output: Contribution to conference › Paper › peer-review

Abstract

We propose a supervised data mining approach that takes advantage of available out-of-control data. By using classification techniques, our proposed approach can utilize both the in-control and out-of-control data information to construct a control chart. The probability that a data point belongs to a certain class from the classification result is plotted and the control limits can be established. A real power plant data set is used to illustrate our proposed approach. The comparative study shows that our proposed approach performs better than traditional multivariate control chart techniques.

Original language	English
Pages	851-856
Number of pages	6
Publication status	Published - 2008
Externally published	Yes
Event	IIE Annual Conference and Expo 2008 - Vancouver, BC, Canada Duration: 2008 May 17 → 2008 May 21

Other

Other	IIE Annual Conference and Expo 2008
Country/Territory	Canada
City	Vancouver, BC
Period	08/5/17 → 08/5/21

Keywords

Classification analysis
Data mining
Multivariate control chart
Power plant
Supervised method

ASJC Scopus subject areas

Computer Science Applications
Software
Industrial and Manufacturing Engineering

Cite this

@conference{1ed1468743774beea8d840def9d07701,

title = "An application of supervised multivariate control charts on a power plant data",

abstract = "We propose a supervised data mining approach that takes advantage of available out-of-control data. By using classification techniques, our proposed approach can utilize both the in-control and out-of-control data information to construct a control chart. The probability that a data point belongs to a certain class from the classification result is plotted and the control limits can be established. A real power plant data set is used to illustrate our proposed approach. The comparative study shows that our proposed approach performs better than traditional multivariate control chart techniques.",

keywords = "Classification analysis, Data mining, Multivariate control chart, Power plant, Supervised method",

author = "Thuntee Sukchotrat and Kim, {Seoung Bum} and Chen, {Victoria C.P.} and Clint Carter and William Dockery and Robert Tapia",

year = "2008",

language = "English",

pages = "851--856",

note = "IIE Annual Conference and Expo 2008 ; Conference date: 17-05-2008 Through 21-05-2008",

}

TY - CONF

T1 - An application of supervised multivariate control charts on a power plant data

AU - Sukchotrat, Thuntee

AU - Kim, Seoung Bum

AU - Chen, Victoria C.P.

AU - Carter, Clint

AU - Dockery, William

AU - Tapia, Robert

PY - 2008

Y1 - 2008

N2 - We propose a supervised data mining approach that takes advantage of available out-of-control data. By using classification techniques, our proposed approach can utilize both the in-control and out-of-control data information to construct a control chart. The probability that a data point belongs to a certain class from the classification result is plotted and the control limits can be established. A real power plant data set is used to illustrate our proposed approach. The comparative study shows that our proposed approach performs better than traditional multivariate control chart techniques.

AB - We propose a supervised data mining approach that takes advantage of available out-of-control data. By using classification techniques, our proposed approach can utilize both the in-control and out-of-control data information to construct a control chart. The probability that a data point belongs to a certain class from the classification result is plotted and the control limits can be established. A real power plant data set is used to illustrate our proposed approach. The comparative study shows that our proposed approach performs better than traditional multivariate control chart techniques.

KW - Classification analysis

KW - Data mining

KW - Multivariate control chart

KW - Power plant

KW - Supervised method

UR - http://www.scopus.com/inward/record.url?scp=63849125194&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:63849125194

SP - 851

EP - 856

T2 - IIE Annual Conference and Expo 2008

Y2 - 17 May 2008 through 21 May 2008

ER -

An application of supervised multivariate control charts on a power plant data

Abstract

Other

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this