Nonlinear partial least squares with Hellinger distance for nonlinear process monitoring

Fouzi Harrou; Muddu Madakyaru; Ying Sun

doi:10.1109/SSCI.2016.7849878

Nonlinear partial least squares with Hellinger distance for nonlinear process monitoring

Fouzi Harrou, Muddu Madakyaru, Ying Sun

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

1 Scopus citations

Abstract

This paper proposes an efficient data-based anomaly detection method that can be used for monitoring nonlinear processes. The proposed method merges advantages of nonlinear projection to latent structures (NLPLS) modeling and those of Hellinger distance (HD) metric to identify abnormal changes in highly correlated multivariate data. Specifically, the HD is used to quantify the dissimilarity between current NLPLS-based residual and reference probability distributions. The performances of the developed anomaly detection using NLPLS-based HD technique is illustrated using simulated plug flow reactor data.

Original language	English (US)
Title of host publication	2016 IEEE Symposium Series on Computational Intelligence (SSCI)
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
ISBN (Print)	9781509042401
DOIs	https://doi.org/10.1109/SSCI.2016.7849878
State	Published - Feb 16 2017

Bibliographical note

KAUST Repository Item: Exported on 2020-10-01
Acknowledged KAUST grant number(s): OSR-2015-CRG4-2582
Acknowledgements: This publication is based upon work supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) under Award No: OSR-2015-CRG4-2582.

Access to Document

10.1109/SSCI.2016.7849878

https://repository.kaust.edu.sa/bitstream/10754/623873/1/Nonlinear%20Partial%20Least%20Squares%20with%20Hellinger%20Distance.pdf

Cite this

@inproceedings{570026dbcc6d49cab4d5cf964dca7729,

title = "Nonlinear partial least squares with Hellinger distance for nonlinear process monitoring",

abstract = "This paper proposes an efficient data-based anomaly detection method that can be used for monitoring nonlinear processes. The proposed method merges advantages of nonlinear projection to latent structures (NLPLS) modeling and those of Hellinger distance (HD) metric to identify abnormal changes in highly correlated multivariate data. Specifically, the HD is used to quantify the dissimilarity between current NLPLS-based residual and reference probability distributions. The performances of the developed anomaly detection using NLPLS-based HD technique is illustrated using simulated plug flow reactor data.",

author = "Fouzi Harrou and Muddu Madakyaru and Ying Sun",

note = "KAUST Repository Item: Exported on 2020-10-01 Acknowledged KAUST grant number(s): OSR-2015-CRG4-2582 Acknowledgements: This publication is based upon work supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) under Award No: OSR-2015-CRG4-2582.",

year = "2017",

month = feb,

day = "16",

doi = "10.1109/SSCI.2016.7849878",

language = "English (US)",

isbn = "9781509042401",

booktitle = "2016 IEEE Symposium Series on Computational Intelligence (SSCI)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

}

TY - GEN

T1 - Nonlinear partial least squares with Hellinger distance for nonlinear process monitoring

AU - Harrou, Fouzi

AU - Madakyaru, Muddu

AU - Sun, Ying

N1 - KAUST Repository Item: Exported on 2020-10-01 Acknowledged KAUST grant number(s): OSR-2015-CRG4-2582 Acknowledgements: This publication is based upon work supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) under Award No: OSR-2015-CRG4-2582.

PY - 2017/2/16

Y1 - 2017/2/16

N2 - This paper proposes an efficient data-based anomaly detection method that can be used for monitoring nonlinear processes. The proposed method merges advantages of nonlinear projection to latent structures (NLPLS) modeling and those of Hellinger distance (HD) metric to identify abnormal changes in highly correlated multivariate data. Specifically, the HD is used to quantify the dissimilarity between current NLPLS-based residual and reference probability distributions. The performances of the developed anomaly detection using NLPLS-based HD technique is illustrated using simulated plug flow reactor data.

AB - This paper proposes an efficient data-based anomaly detection method that can be used for monitoring nonlinear processes. The proposed method merges advantages of nonlinear projection to latent structures (NLPLS) modeling and those of Hellinger distance (HD) metric to identify abnormal changes in highly correlated multivariate data. Specifically, the HD is used to quantify the dissimilarity between current NLPLS-based residual and reference probability distributions. The performances of the developed anomaly detection using NLPLS-based HD technique is illustrated using simulated plug flow reactor data.

UR - http://hdl.handle.net/10754/623873

UR - http://ieeexplore.ieee.org/document/7849878/

UR - http://www.scopus.com/inward/record.url?scp=85016073168&partnerID=8YFLogxK

U2 - 10.1109/SSCI.2016.7849878

DO - 10.1109/SSCI.2016.7849878

M3 - Conference contribution

SN - 9781509042401

BT - 2016 IEEE Symposium Series on Computational Intelligence (SSCI)

PB - Institute of Electrical and Electronics Engineers (IEEE)

ER -

Nonlinear partial least squares with Hellinger distance for nonlinear process monitoring

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this