FAULT DETECTION BASED ON GAUSSIAN PROCESS MODELS - An Application to the Rolling Mill

Dani Juricic, Pavel Ettler, Jus Kocijan

2011

Abstract

In this paper a fault detection approach based on Gaussian process model is proposed. The problem we raise is how to deal with insufficiently validated models during surveillance of nonlinear plants given the fact that tentative model-plant miss-match in such a case can cause false alarms. To avoid the risk, a novel model validity index is suggested in order to quantify the level of confidence associated to the detection results. This index is based on estimated ‘distance’ between the current process data from data employed in the learning set. The effectiveness of the test is demonstrated on data records obtained from operating cold rolling mill.

Paper Citation

in Harvard Style

Juricic D., Ettler P. and Kocijan J. (2011). FAULT DETECTION BASED ON GAUSSIAN PROCESS MODELS - An Application to the Rolling Mill . In Proceedings of the 8th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO, ISBN 978-989-8425-74-4, pages 437-440. DOI: 10.5220/0003541304370440

in Bibtex Style

@conference{icinco11,
author={Dani Juricic and Pavel Ettler and Jus Kocijan},
title={FAULT DETECTION BASED ON GAUSSIAN PROCESS MODELS - An Application to the Rolling Mill},
booktitle={Proceedings of the 8th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,},
year={2011},
pages={437-440},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003541304370440},
isbn={978-989-8425-74-4},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 8th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,
TI - FAULT DETECTION BASED ON GAUSSIAN PROCESS MODELS - An Application to the Rolling Mill
SN - 978-989-8425-74-4
AU - Juricic D.
AU - Ettler P.
AU - Kocijan J.
PY - 2011
SP - 437
EP - 440
DO - 10.5220/0003541304370440