NONPARAMETRIC VIRTUAL SENSORS FOR SEMICONDUCTOR MANUFACTURING - Using Information Theoretic Learning and Kernel Machines

Andrea Schirru, Simone Pampuri, Cristina De Luca, Giuseppe De Nicolao

2011

Abstract

In this paper, a novel learning methodology is presented and discussed with reference to the application of virtual sensors in the semiconductor manufacturing environment. Density estimation techniques are used jointly with Renyi’s entropy to define a loss function for the learning problem (relying on Information Theoretic Learning concepts). Furthermore, Reproducing Kernel Hilbert Spaces (RKHS) theory is employed to handle nonlinearities and include regularization capabilities in the model. The proposed algorithm allows to estimate the structure of the predictive model, as well as the associated probabilistic uncertainty, in a nonparametric fashion. The methodology is then validated using simulation studies and process data from the semiconductor manufacturing industry. The proposed approach proves to be especially effective in strongly nongaussian environments and presents notable outlier filtering capabilities.

Paper Citation

in Harvard Style

Schirru A., Pampuri S., De Luca C. and De Nicolao G. (2011). NONPARAMETRIC VIRTUAL SENSORS FOR SEMICONDUCTOR MANUFACTURING - Using Information Theoretic Learning and Kernel Machines . In Proceedings of the 8th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO, ISBN 978-989-8425-75-1, pages 349-358. DOI: 10.5220/0003520403490358

in Bibtex Style

@conference{icinco11,
author={Andrea Schirru and Simone Pampuri and Cristina De Luca and Giuseppe De Nicolao},
title={NONPARAMETRIC VIRTUAL SENSORS FOR SEMICONDUCTOR MANUFACTURING - Using Information Theoretic Learning and Kernel Machines},
booktitle={Proceedings of the 8th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,},
year={2011},
pages={349-358},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003520403490358},
isbn={978-989-8425-75-1},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 8th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,
TI - NONPARAMETRIC VIRTUAL SENSORS FOR SEMICONDUCTOR MANUFACTURING - Using Information Theoretic Learning and Kernel Machines
SN - 978-989-8425-75-1
AU - Schirru A.
AU - Pampuri S.
AU - De Luca C.
AU - De Nicolao G.
PY - 2011
SP - 349
EP - 358
DO - 10.5220/0003520403490358