Abstract
Isolating the variable or set of variables responsible for an out-of-control signal is a challenging task in multivariate statistical process control. Several fault isolation approaches have been proposed. However, all assumed a multivariate normal distribution on the process data, an assumption that limits their applicability in many situations. In the present study we propose a nonparametric fault isolation approach based on a hybrid novelty score (HNS). A simulation study was conducted to examine the performance of our proposed HNS-based fault isolation approach, and its results were compared with both parametric and nonparametric T2 decomposition approaches. The performance of our approach was superior in the simulation to either parametric or nonparametric T2 decompositions. This was especially true in nonnormal situations.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of 2011 IEEE International Conference on Intelligence and Security Informatics, ISI 2011 |
| Pages | 261-266 |
| Number of pages | 6 |
| DOIs | |
| Publication status | Published - 2011 Sep 22 |
| Event | 2011 IEEE International Conference on Intelligence and Security Informatics, ISI 2011 - Beijing, China Duration: 2011 Jul 10 → 2011 Jul 12 |
Other
| Other | 2011 IEEE International Conference on Intelligence and Security Informatics, ISI 2011 |
|---|---|
| Country | China |
| City | Beijing |
| Period | 11/7/10 → 11/7/12 |
Fingerprint
Keywords
- Decomposition
- Fault-isolation
- Multivariate statistical process control
- Nonparametric
- Novelty score
ASJC Scopus subject areas
- Artificial Intelligence
- Information Systems
Cite this
A nonparametric fault isolation approach through hybrid novelty score. / Tuerhong, Gulanbaier; Kim, Seoung Bum.
Proceedings of 2011 IEEE International Conference on Intelligence and Security Informatics, ISI 2011. 2011. p. 261-266 5984094.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - A nonparametric fault isolation approach through hybrid novelty score
AU - Tuerhong, Gulanbaier
AU - Kim, Seoung Bum
PY - 2011/9/22
Y1 - 2011/9/22
N2 - Isolating the variable or set of variables responsible for an out-of-control signal is a challenging task in multivariate statistical process control. Several fault isolation approaches have been proposed. However, all assumed a multivariate normal distribution on the process data, an assumption that limits their applicability in many situations. In the present study we propose a nonparametric fault isolation approach based on a hybrid novelty score (HNS). A simulation study was conducted to examine the performance of our proposed HNS-based fault isolation approach, and its results were compared with both parametric and nonparametric T2 decomposition approaches. The performance of our approach was superior in the simulation to either parametric or nonparametric T2 decompositions. This was especially true in nonnormal situations.
AB - Isolating the variable or set of variables responsible for an out-of-control signal is a challenging task in multivariate statistical process control. Several fault isolation approaches have been proposed. However, all assumed a multivariate normal distribution on the process data, an assumption that limits their applicability in many situations. In the present study we propose a nonparametric fault isolation approach based on a hybrid novelty score (HNS). A simulation study was conducted to examine the performance of our proposed HNS-based fault isolation approach, and its results were compared with both parametric and nonparametric T2 decomposition approaches. The performance of our approach was superior in the simulation to either parametric or nonparametric T2 decompositions. This was especially true in nonnormal situations.
KW - Decomposition
KW - Fault-isolation
KW - Multivariate statistical process control
KW - Nonparametric
KW - Novelty score
UR - http://www.scopus.com/inward/record.url?scp=80052892844&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=80052892844&partnerID=8YFLogxK
U2 - 10.1109/ISI.2011.5984094
DO - 10.1109/ISI.2011.5984094
M3 - Conference contribution
AN - SCOPUS:80052892844
SN - 9781457700828
SP - 261
EP - 266
BT - Proceedings of 2011 IEEE International Conference on Intelligence and Security Informatics, ISI 2011
ER -