Nonlinear Partial Least Squares with Hellinger Distance for Nonlinear Process Monitoring

Harrou, Fouzi and Madakyaru, Muddu and Sun, Ying (2016) Nonlinear Partial Least Squares with Hellinger Distance for Nonlinear Process Monitoring. In: IEEE Symposium Series on Computational Intelligence, 06/12/2016, Royal Olympic Hotel , ATHENS, GREECE.

[img] PDF
681.pdf - Published Version
Restricted to Registered users only

Download (571kB) | Request a copy
Official URL: http://ssci2016.cs.surrey.ac.uk/Venue.htm

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

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: NLPLS, HD
Subjects: Engineering > MIT Manipal > Chemical
Depositing User: MIT Library
Date Deposited: 13 Mar 2017 05:31
Last Modified: 13 Mar 2017 05:31
URI: http://eprints.manipal.edu/id/eprint/148359

Actions (login required)

View Item View Item